yaojingang
2123 lines
83 KiB
JSON
2123 lines
83 KiB
JSON
{
|
|
"skill_summary": {
|
|
"name": "yao-meta-skill",
|
|
"title": "Yao Meta Skill",
|
|
"display_name": "Yao Meta Skill",
|
|
"description": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use when asked to create a skill, turn a repeated process into a reusable skill, improve an existing skill, add evals, or package a skill for team reuse.",
|
|
"maturity": "governed",
|
|
"updated_at": "2026-03-31",
|
|
"core_value": "把一次性经验沉淀为可复用、可评估、可迁移的 Skill 包体。",
|
|
"audience": "Skill 作者、复用团队和后续 reviewer。",
|
|
"deliverables": [
|
|
"SKILL.md",
|
|
"agents/interface.yaml",
|
|
"reports/skill-ir.json",
|
|
"reports/compiled_targets.md",
|
|
"reports/output_quality_scorecard.md",
|
|
"reports/output_execution_runs.md",
|
|
"reports/output_blind_review_pack.md",
|
|
"reports/output_review_kit.md",
|
|
"reports/output_review_adjudication.md",
|
|
"reports/benchmark_reproducibility.md",
|
|
"reports/output_blind_answer_key.json",
|
|
"reports/conformance_matrix.md",
|
|
"reports/security_trust_report.md",
|
|
"reports/runtime_permission_probes.md",
|
|
"reports/skill_atlas.html",
|
|
"reports/registry_audit.md",
|
|
"reports/package_verification.md",
|
|
"reports/install_simulation.md",
|
|
"reports/upgrade_check.md",
|
|
"reports/adoption_drift_report.md",
|
|
"reports/review_waivers.md",
|
|
"reports/world_class_evidence_plan.md",
|
|
"reports/world_class_evidence_ledger.md",
|
|
"reports/review_annotations.md",
|
|
"reports/review-studio.html",
|
|
"reports/skill-interpretation.html",
|
|
"reports/skill-overview.html",
|
|
"reports/skill-interpretation.json"
|
|
],
|
|
"flow": [
|
|
"输入材料",
|
|
"Skill 包体",
|
|
"可复用能力"
|
|
]
|
|
},
|
|
"scorecard": {
|
|
"completeness_score": {
|
|
"label": "完整度",
|
|
"score": 100,
|
|
"reasons": [
|
|
"SKILL.md 已存在，是 Skill 的入口。",
|
|
"README.md 已存在，便于人工阅读。",
|
|
"agents/interface.yaml 已存在，便于跨平台适配。",
|
|
"manifest.json 已存在，生命周期信息可追踪。",
|
|
"reports/ 已存在，生成证据可以随包体迁移。"
|
|
]
|
|
},
|
|
"trigger_score": {
|
|
"label": "触发清晰",
|
|
"score": 100,
|
|
"reasons": [
|
|
"frontmatter description 已存在，具备基础路由面。",
|
|
"description 有足够长度说明任务边界。",
|
|
"description 已包含使用场景或排除边界信号。",
|
|
"evals/ 已存在，可承载触发样例或质量检查。",
|
|
"intent-confidence 报告已生成，可辅助判断触发稳定性。"
|
|
]
|
|
},
|
|
"evidence_score": {
|
|
"label": "证据充分",
|
|
"score": 100,
|
|
"reasons": [
|
|
"已生成 20 / 20 类报告证据。",
|
|
"skill-ir.json 已存在。",
|
|
"compiled_targets.json 已存在。",
|
|
"intent-dialogue.json 已存在。"
|
|
]
|
|
},
|
|
"maintainability_score": {
|
|
"label": "可维护性",
|
|
"score": 100,
|
|
"reasons": [
|
|
"SKILL.md 约 356 个词/字。",
|
|
"入口文件保持克制，可维护性较好。",
|
|
"references/ 已承载扩展指导。",
|
|
"scripts/ 已承载确定性逻辑。",
|
|
"evals/ 已承载可迁移检查。"
|
|
]
|
|
},
|
|
"portability_score": {
|
|
"label": "可迁移性",
|
|
"score": 100,
|
|
"reasons": [
|
|
"agents/interface.yaml 已存在。",
|
|
"manifest.json 已存在。",
|
|
"目标平台或 adapter target 已声明。",
|
|
"入口文件未发现明显私有绝对路径。"
|
|
]
|
|
},
|
|
"context_cost": {
|
|
"label": "上下文成本",
|
|
"score": 42,
|
|
"reasons": [
|
|
"入口约 356 个词/字，references 约 16045 个词/字。",
|
|
"分数越高代表上下文成本越低。",
|
|
"上下文成本偏高，建议压缩入口或拆分 references。"
|
|
]
|
|
}
|
|
},
|
|
"capability_profile": {
|
|
"archetype": "governed",
|
|
"task_family": "Execution operation",
|
|
"maturity": "governed",
|
|
"trigger_strength": "手动触发 + description 路由",
|
|
"reuse_scope": "跨平台",
|
|
"matrix": {
|
|
"execution_certainty": 72,
|
|
"knowledge_density": 80
|
|
}
|
|
},
|
|
"principle_model": {
|
|
"nodes": [
|
|
{
|
|
"title": "意图澄清",
|
|
"body": "Turn repeated workflows, prompts, transcripts, runbooks, documents, or existing skill packages into routeable, evaluable, packageable, and governable agent skills for personal, team, library, or governed reuse."
|
|
},
|
|
{
|
|
"title": "边界路由",
|
|
"body": "用 frontmatter description 决定是否触发，并写明相邻非目标。"
|
|
},
|
|
{
|
|
"title": "资产分层",
|
|
"body": "把入口、参考、脚本、评估和报告拆到各自目录，避免 SKILL.md 膨胀。"
|
|
},
|
|
{
|
|
"title": "证据回路",
|
|
"body": "Ask only the highest-leverage clarification before adding package weight."
|
|
},
|
|
{
|
|
"title": "漂移观察",
|
|
"body": "Add near-neighbor exclusions and route evals before expanding workflow steps."
|
|
},
|
|
{
|
|
"title": "杠杆升级",
|
|
"body": "Name the recurring job, expected input, output, and strongest non-goal in compact language."
|
|
}
|
|
],
|
|
"layers": [
|
|
"入口层",
|
|
"参考层",
|
|
"脚本层",
|
|
"评估层",
|
|
"报告层"
|
|
]
|
|
},
|
|
"contract_boundary": {
|
|
"trigger": {
|
|
"description": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use when asked to create a skill, turn a repeated process into a reusable skill, improve an existing skill, add evals, or package a skill for team reuse.",
|
|
"activation": "manual",
|
|
"execution": "inline",
|
|
"shell": "bash"
|
|
},
|
|
"inputs": [
|
|
"rough workflow notes, SOPs, runbooks, prompts, transcripts, documents, or repeated task descriptions",
|
|
"an existing skill directory that needs refactor, evaluation, packaging, or governance hardening",
|
|
"target platform requirements such as OpenAI, Claude, generic Agent Skills, or team distribution",
|
|
"benchmark references, local constraints, desired maturity tier, and review standards"
|
|
],
|
|
"outputs": [
|
|
"A working skill package with lean SKILL.md, aligned agents/interface.yaml, justified references, scripts only when useful, eval evidence, reports, packaging metadata, and clear next iteration recommendations.",
|
|
"结构化 Skill 目录，共 8 类关键资产。"
|
|
],
|
|
"should_trigger": [
|
|
"把重复流程沉淀为可复用的 agent skill。",
|
|
"把分散提示词、对话记录或操作规范整理为稳定能力。",
|
|
"团队复用前，需要明确触发边界、质量证据和维护责任。"
|
|
],
|
|
"should_not_trigger": [
|
|
"只需要一次性回答、没有复用价值的临时请求。",
|
|
"要求直接执行相邻任务，而不是沉淀或使用这个 Skill。",
|
|
"缺少必要事实且用户不允许澄清的场景。"
|
|
],
|
|
"boundary_cards": [
|
|
{
|
|
"label": "Owned",
|
|
"body": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use when asked to create a skill, turn a repeated process into a reusable skill, improve an existing skill, add evals, or package a skill for team reuse."
|
|
},
|
|
{
|
|
"label": "Adjacent",
|
|
"body": "相邻任务需要先确认是否应转为独立 Skill。"
|
|
},
|
|
{
|
|
"label": "Excluded",
|
|
"body": "不替代人工事实核查，也不静默扩大职责。"
|
|
}
|
|
]
|
|
},
|
|
"quality_review": {
|
|
"strengths": [
|
|
"触发面保持精简，并锚定在 frontmatter description。",
|
|
"已生成 Skill IR，核心语义可先于平台打包被审查和迁移。",
|
|
"已生成目标编译报告，可审查 IR 到 OpenAI、Claude、generic 等目标契约的映射。",
|
|
"已生成 Output Eval Lab scorecard，可比较 with-skill 与 baseline 输出质量。",
|
|
"已生成 Output Execution Runs，可区分记录样本、命令执行和模型执行证据。",
|
|
"已生成 Output Review Adjudication，可记录盲评决策、一致率和待评审项。"
|
|
],
|
|
"gaps": [
|
|
"上下文成本需要补强：入口约 356 个词/字，references 约 16045 个词/字。"
|
|
],
|
|
"recommendations": [
|
|
"先改触发边界，再扩展工作流。",
|
|
"只把重复且稳定的步骤沉淀为脚本。",
|
|
"每次升级后重新生成报告并检查分数原因。"
|
|
],
|
|
"artifact_design": {
|
|
"design_system": "metric editorial",
|
|
"highlights": [
|
|
"Execution-focused technical artifact with environment assumptions, copyable commands, expected outputs, and side effects made explicit.",
|
|
"Name the working directory and required inputs for commands.",
|
|
"Mark destructive, networked, or external side-effect operations.",
|
|
"Prefer the smallest runnable snippet over broad framework scaffolding."
|
|
]
|
|
},
|
|
"prompt_quality": {
|
|
"overall_quality_score": 89.0,
|
|
"highlights": [
|
|
"Primary prompt task family: Execution operation.",
|
|
"Complexity: expert — multiple task families plus governance, evaluation, or expert-level constraints",
|
|
"Completeness: 100/100.",
|
|
"Clarity: 85/100."
|
|
]
|
|
},
|
|
"system_model": {
|
|
"stability": {
|
|
"score": 100,
|
|
"band": "system-ready"
|
|
},
|
|
"highlights": [
|
|
"Stability: system-ready (100/100).",
|
|
"Owned job: Turn repeated workflows, prompts, transcripts, runbooks, documents, or existing skill packages into routeable, evaluable, packageable, and governable agent skills for personal, team, library, or governed reuse.",
|
|
"Leverage: Tune the frontmatter description — Name the recurring job, expected input, output, and strongest non-goal in compact language.",
|
|
"Leverage: Install output self-repair checks — Add only the checks that prevent recurring output mistakes."
|
|
]
|
|
}
|
|
},
|
|
"risk_governance": {
|
|
"risks": [
|
|
{
|
|
"name": "误触发风险",
|
|
"impact": 3,
|
|
"probability": 1,
|
|
"signal": "frontmatter description 已存在，具备基础路由面。",
|
|
"response": "先补证据和边界，再增加包体复杂度。"
|
|
},
|
|
{
|
|
"name": "输出漂移风险",
|
|
"impact": 2,
|
|
"probability": 1,
|
|
"signal": "已生成 20 / 20 类报告证据。",
|
|
"response": "先补证据和边界，再增加包体复杂度。"
|
|
},
|
|
{
|
|
"name": "证据不足风险",
|
|
"impact": 3,
|
|
"probability": 1,
|
|
"signal": "已生成 20 / 20 类报告证据。",
|
|
"response": "先补证据和边界，再增加包体复杂度。"
|
|
},
|
|
{
|
|
"name": "包体膨胀风险",
|
|
"impact": 2,
|
|
"probability": 1,
|
|
"signal": "SKILL.md 约 356 个词/字。",
|
|
"response": "先补证据和边界，再增加包体复杂度。"
|
|
},
|
|
{
|
|
"name": "跨平台迁移风险",
|
|
"impact": 3,
|
|
"probability": 1,
|
|
"signal": "agents/interface.yaml 已存在。",
|
|
"response": "先补证据和边界，再增加包体复杂度。"
|
|
}
|
|
],
|
|
"risk_families": [
|
|
{
|
|
"key": "markdown_readability",
|
|
"label": "Markdown readability",
|
|
"matched_keywords": [
|
|
"md",
|
|
"report",
|
|
"doc"
|
|
],
|
|
"score": 3,
|
|
"risks": [
|
|
"Tables can render as dense grids with weak hierarchy or poor mobile readability.",
|
|
"Long bullets can make the output look complete while hiding the actual decision logic.",
|
|
"Mixed heading levels can reduce scanability."
|
|
],
|
|
"constraints": [
|
|
"Use tables only when comparison is the main job; otherwise prefer compact cards or grouped bullets.",
|
|
"Keep table cells short and move explanations below the table.",
|
|
"Use heading levels consistently and keep each section anchored to a user-facing outcome."
|
|
],
|
|
"self_repair": [
|
|
"Preview whether each table still reads well when columns are narrow.",
|
|
"Convert any table with paragraph-length cells into bullets or cards."
|
|
]
|
|
},
|
|
{
|
|
"key": "citation_clutter",
|
|
"label": "Citation and footnote clutter",
|
|
"matched_keywords": [
|
|
"source",
|
|
"reference"
|
|
],
|
|
"score": 2,
|
|
"risks": [
|
|
"Footnote markers or dense citation notes can interrupt the reading flow.",
|
|
"Evidence can be over-attached to obvious statements and under-attached to risky claims.",
|
|
"Source notes may become more prominent than the tutorial itself."
|
|
],
|
|
"constraints": [
|
|
"Attach citations only to claims that need evidence, not to every sentence.",
|
|
"Group source notes at the end of a section when inline markers would hurt readability.",
|
|
"Keep the main sentence readable without requiring the reader to chase a footnote."
|
|
],
|
|
"self_repair": [
|
|
"Remove decorative citations that do not support a material claim.",
|
|
"Move repeated source explanations into one compact source note."
|
|
]
|
|
},
|
|
{
|
|
"key": "visual_capture",
|
|
"label": "Screenshot and visual capture",
|
|
"matched_keywords": [
|
|
"capture"
|
|
],
|
|
"score": 1,
|
|
"risks": [
|
|
"Screenshots can be captured from the wrong state, wrong viewport, or wrong crop.",
|
|
"Missing screenshots can cause the skill to invent visual references instead of declaring the gap.",
|
|
"Image descriptions can omit the action-relevant region."
|
|
],
|
|
"constraints": [
|
|
"Never invent a screenshot; state when visual evidence is missing.",
|
|
"Record the source, viewport, and crop intent for any screenshot-dependent output.",
|
|
"Describe what the reader should inspect in the image, not just that an image exists."
|
|
],
|
|
"self_repair": [
|
|
"Check that every screenshot reference points to a real provided or generated asset.",
|
|
"Reword any visual instruction that depends on an unseen screen state."
|
|
]
|
|
},
|
|
{
|
|
"key": "code_or_command_safety",
|
|
"label": "Code and command safety",
|
|
"matched_keywords": [
|
|
"script"
|
|
],
|
|
"score": 1,
|
|
"risks": [
|
|
"Commands can omit environment assumptions, working directory, or rollback notes.",
|
|
"Code snippets can look runnable while missing required inputs.",
|
|
"Error handling can be either absent or over-engineered."
|
|
],
|
|
"constraints": [
|
|
"Name the working directory, required inputs, and expected output for each command.",
|
|
"Mark destructive or external side-effect operations explicitly.",
|
|
"Prefer the smallest runnable snippet over broad framework code."
|
|
],
|
|
"self_repair": [
|
|
"Scan each command for cwd, input, output, and side-effect assumptions.",
|
|
"Remove speculative error handling that is not tied to a real failure mode."
|
|
]
|
|
},
|
|
{
|
|
"key": "tone_and_specificity",
|
|
"label": "Tone and specificity",
|
|
"matched_keywords": [
|
|
"summary"
|
|
],
|
|
"score": 1,
|
|
"risks": [
|
|
"Headings and summaries can drift into generic, interchangeable language.",
|
|
"The output can sound polished but lose the user's actual taste, audience, or scenario.",
|
|
"Strong claims can appear without examples or constraints."
|
|
],
|
|
"constraints": [
|
|
"Anchor titles and summaries in the user's audience, object, and concrete outcome.",
|
|
"Avoid placeholder phrases such as comprehensive guide, ultimate solution, or key insights unless the source demands them.",
|
|
"Preserve one distinctive phrase, constraint, or standard from the user's input."
|
|
],
|
|
"self_repair": [
|
|
"Replace generic title candidates with scenario-specific alternatives.",
|
|
"Delete any polished sentence that could fit almost any project unchanged."
|
|
]
|
|
}
|
|
],
|
|
"human_judgment_boundary": [
|
|
"Ask one focused clarification when the real job, output, or exclusion boundary is unclear.",
|
|
"Escalate visible tradeoffs when benchmark patterns conflict with local privacy, naming, or governance constraints.",
|
|
"Do not silently broaden the skill into adjacent jobs just because the examples are nearby."
|
|
]
|
|
},
|
|
"world_class_readiness": {
|
|
"ready": false,
|
|
"decision": "evidence-pending",
|
|
"entry_count": 4,
|
|
"pending_count": 4,
|
|
"accepted_count": 0,
|
|
"external_pending_count": 3,
|
|
"human_pending_count": 1,
|
|
"source_check_count": 13,
|
|
"source_pass_count": 6,
|
|
"conclusion_zh": "世界级证据尚未完成：4 项待补，0 项已接受。",
|
|
"conclusion_en": "World-class evidence is not complete: 4 pending, 0 accepted.",
|
|
"entries": [
|
|
{
|
|
"key": "provider-holdout",
|
|
"label_zh": "提供商留出",
|
|
"label_en": "Provider Holdout",
|
|
"category": "external",
|
|
"category_zh": "外部证据",
|
|
"category_en": "External evidence",
|
|
"status": "pending",
|
|
"summary_zh": "缺少真实 provider 模型运行和 token metadata。",
|
|
"summary_en": "Missing a real provider model run and token metadata.",
|
|
"blocked_checks": [
|
|
"Provider model run",
|
|
"Token usage observed"
|
|
]
|
|
},
|
|
{
|
|
"key": "human-adjudication",
|
|
"label_zh": "人工盲评",
|
|
"label_en": "Human Adjudication",
|
|
"category": "human",
|
|
"category_zh": "人工证据",
|
|
"category_en": "Human evidence",
|
|
"status": "pending",
|
|
"summary_zh": "盲评 pair 仍待真实 reviewer 决策。",
|
|
"summary_en": "Blind-review pairs still need real reviewer decisions.",
|
|
"blocked_checks": [
|
|
"No pending decisions",
|
|
"Judgments complete"
|
|
]
|
|
},
|
|
{
|
|
"key": "native-permission-enforcement",
|
|
"label_zh": "原生权限",
|
|
"label_en": "Native Permission",
|
|
"category": "external",
|
|
"category_zh": "外部证据",
|
|
"category_en": "External evidence",
|
|
"status": "pending",
|
|
"summary_zh": "原生 runtime enforcement 仍待目标客户端或外部安装器证明。",
|
|
"summary_en": "Native runtime enforcement still needs target-client or external-installer proof.",
|
|
"blocked_checks": [
|
|
"Native enforcement"
|
|
]
|
|
},
|
|
{
|
|
"key": "native-client-telemetry",
|
|
"label_zh": "原生遥测",
|
|
"label_en": "Native Telemetry",
|
|
"category": "external",
|
|
"category_zh": "外部证据",
|
|
"category_en": "External evidence",
|
|
"status": "pending",
|
|
"summary_zh": "真实外部客户端 metadata-only 事件仍未导入。",
|
|
"summary_en": "Real external-client metadata-only events have not been imported yet.",
|
|
"blocked_checks": [
|
|
"External events",
|
|
"Adoption sample"
|
|
]
|
|
}
|
|
]
|
|
},
|
|
"package_assets": {
|
|
"entries": [
|
|
{
|
|
"path": "SKILL.md",
|
|
"label": "Skill entrypoint",
|
|
"kind": "file",
|
|
"file_count": 1
|
|
},
|
|
{
|
|
"path": "README.md",
|
|
"label": "Human-readable usage guide",
|
|
"kind": "file",
|
|
"file_count": 1
|
|
},
|
|
{
|
|
"path": "agents/interface.yaml",
|
|
"label": "Neutral interface metadata",
|
|
"kind": "file",
|
|
"file_count": 1
|
|
},
|
|
{
|
|
"path": "manifest.json",
|
|
"label": "Lifecycle and portability metadata",
|
|
"kind": "file",
|
|
"file_count": 1
|
|
},
|
|
{
|
|
"path": "references",
|
|
"label": "Extended guidance and reusable notes",
|
|
"kind": "folder",
|
|
"file_count": 34
|
|
},
|
|
{
|
|
"path": "scripts",
|
|
"label": "Deterministic helpers or local tooling",
|
|
"kind": "folder",
|
|
"file_count": 107
|
|
},
|
|
{
|
|
"path": "evals",
|
|
"label": "Trigger and quality checks",
|
|
"kind": "folder",
|
|
"file_count": 29
|
|
},
|
|
{
|
|
"path": "reports",
|
|
"label": "Generated evidence and overview artifacts",
|
|
"kind": "folder",
|
|
"file_count": 215
|
|
}
|
|
],
|
|
"file_count": 389,
|
|
"folder_count": 4,
|
|
"distribution": [
|
|
{
|
|
"label": "SKILL.md",
|
|
"value": 1
|
|
},
|
|
{
|
|
"label": "README.md",
|
|
"value": 1
|
|
},
|
|
{
|
|
"label": "agents/interface.yaml",
|
|
"value": 1
|
|
},
|
|
{
|
|
"label": "manifest.json",
|
|
"value": 1
|
|
},
|
|
{
|
|
"label": "references",
|
|
"value": 34
|
|
},
|
|
{
|
|
"label": "scripts",
|
|
"value": 107
|
|
},
|
|
{
|
|
"label": "evals",
|
|
"value": 29
|
|
},
|
|
{
|
|
"label": "reports",
|
|
"value": 215
|
|
}
|
|
]
|
|
},
|
|
"iteration_roadmap": {
|
|
"items": [
|
|
{
|
|
"title": "补齐世界证据",
|
|
"why": "世界级证据仍有 4 项待补；公开完成态 claim 必须继续保持阻塞。",
|
|
"actions": [
|
|
"补齐提供商留出证据：缺少真实 provider 模型运行和 token metadata。",
|
|
"补齐人工盲评证据：盲评 pair 仍待真实 reviewer 决策。",
|
|
"继续补齐剩余 2 项外部/人工证据，并保持 claim guard 为 pending 状态。"
|
|
],
|
|
"unlocks": "全部外部/人工证据被 ledger 接受后，才能进入公开 world-class claim 复核。",
|
|
"source": "world_class_evidence_ledger"
|
|
},
|
|
{
|
|
"title": "Borrow one proven pattern on purpose",
|
|
"why": "You already have public benchmark objects. The next gain is to choose one pattern intentionally instead of absorbing everything loosely.",
|
|
"actions": [
|
|
"Read the strongest pattern from obra/superpowers.",
|
|
"Decide whether to borrow method, structure, execution, or portability, but only one of them first.",
|
|
"Record what you will not borrow so the package stays light."
|
|
],
|
|
"unlocks": "A cleaner package shape with less accidental over-design."
|
|
},
|
|
{
|
|
"title": "Harden portability semantics",
|
|
"why": "The skill already signals reuse across environments, so contract clarity matters early.",
|
|
"actions": [
|
|
"Confirm activation mode, execution context, and trust assumptions.",
|
|
"Add or review degradation strategy for non-native targets.",
|
|
"Package the skill once to verify adapter expectations."
|
|
],
|
|
"unlocks": "Safer cross-environment reuse with less target drift."
|
|
}
|
|
]
|
|
},
|
|
"report_contract": {
|
|
"schema_version": "2.0",
|
|
"html_report": "reports/skill-interpretation.html",
|
|
"language": "zh-CN",
|
|
"default_language": "zh-CN",
|
|
"languages": [
|
|
"zh-CN",
|
|
"en"
|
|
],
|
|
"layout": "kami-white-audit-v2",
|
|
"nav_labels": [
|
|
"技能概述",
|
|
"总览指标",
|
|
"能力画像",
|
|
"原理结构",
|
|
"契约边界",
|
|
"质量评估",
|
|
"风险治理",
|
|
"包体资产",
|
|
"迭代路线"
|
|
],
|
|
"nav_labels_en": [
|
|
"Overview",
|
|
"Metrics",
|
|
"Profile",
|
|
"Principle",
|
|
"Contract",
|
|
"Quality",
|
|
"Risk",
|
|
"Assets",
|
|
"Roadmap"
|
|
],
|
|
"report_kind": "skill-interpretation",
|
|
"canonical_overview_report": "reports/skill-overview.html",
|
|
"json_report": "reports/skill-interpretation.json",
|
|
"purpose": "Explain the generated skill's role, principles, usage scenarios, trigger contract, inputs, outputs, quality evidence, risks, assets, highlights, and next upgrade directions."
|
|
},
|
|
"name": "yao-meta-skill",
|
|
"title": "Yao Meta Skill",
|
|
"display_name": "Yao Meta Skill",
|
|
"description": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use when asked to create a skill, turn a repeated process into a reusable skill, improve an existing skill, add evals, or package a skill for team reuse.",
|
|
"logic_steps": [
|
|
"Decide whether the request should become a skill and choose the lightest fit.",
|
|
"Capture job, output, exclusions, constraints, and standards.",
|
|
"Run reference scan: external benchmarks first, user references second, local fit third; surface only uncertainty or conflict.",
|
|
"Write the `description` early and test route quality before expanding the package.",
|
|
"Add output-risk, artifact-design, prompt-quality, and system-model reports only when they matter."
|
|
],
|
|
"usage_steps": [
|
|
"Use $yao-meta-skill to turn my workflow or notes into a reusable skill with lean structure, clear triggering, and the right evals.",
|
|
"Use this skill when the request matches: Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use when asked to create a skill, turn a repeated process into a reusable skill, improve an existing skill, add evals, or package a skill for team reuse."
|
|
],
|
|
"package_map": [
|
|
{
|
|
"path": "SKILL.md",
|
|
"label": "Skill entrypoint",
|
|
"kind": "file",
|
|
"file_count": 1
|
|
},
|
|
{
|
|
"path": "README.md",
|
|
"label": "Human-readable usage guide",
|
|
"kind": "file",
|
|
"file_count": 1
|
|
},
|
|
{
|
|
"path": "agents/interface.yaml",
|
|
"label": "Neutral interface metadata",
|
|
"kind": "file",
|
|
"file_count": 1
|
|
},
|
|
{
|
|
"path": "manifest.json",
|
|
"label": "Lifecycle and portability metadata",
|
|
"kind": "file",
|
|
"file_count": 1
|
|
},
|
|
{
|
|
"path": "references",
|
|
"label": "Extended guidance and reusable notes",
|
|
"kind": "folder",
|
|
"file_count": 34
|
|
},
|
|
{
|
|
"path": "scripts",
|
|
"label": "Deterministic helpers or local tooling",
|
|
"kind": "folder",
|
|
"file_count": 107
|
|
},
|
|
{
|
|
"path": "evals",
|
|
"label": "Trigger and quality checks",
|
|
"kind": "folder",
|
|
"file_count": 29
|
|
},
|
|
{
|
|
"path": "reports",
|
|
"label": "Generated evidence and overview artifacts",
|
|
"kind": "folder",
|
|
"file_count": 215
|
|
}
|
|
],
|
|
"strengths": [
|
|
"触发面保持精简，并锚定在 frontmatter description。",
|
|
"已生成 Skill IR，核心语义可先于平台打包被审查和迁移。",
|
|
"已生成目标编译报告，可审查 IR 到 OpenAI、Claude、generic 等目标契约的映射。",
|
|
"已生成 Output Eval Lab scorecard，可比较 with-skill 与 baseline 输出质量。",
|
|
"已生成 Output Execution Runs，可区分记录样本、命令执行和模型执行证据。",
|
|
"已生成 Output Review Adjudication，可记录盲评决策、一致率和待评审项。"
|
|
],
|
|
"scenarios": [
|
|
"把重复流程沉淀为可复用的 agent skill。",
|
|
"把分散提示词、对话记录或操作规范整理为稳定能力。",
|
|
"团队复用前，需要明确触发边界、质量证据和维护责任。",
|
|
"用户说出类似需求时：Use $yao-meta-skill to turn my workflow or notes into a reusable skill with lean structure, clear triggering, and the right evals."
|
|
],
|
|
"trigger_contract": {
|
|
"description": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use when asked to create a skill, turn a repeated process into a reusable skill, improve an existing skill, add evals, or package a skill for team reuse.",
|
|
"activation": "manual",
|
|
"execution": "inline",
|
|
"shell": "bash"
|
|
},
|
|
"io_contract": {
|
|
"inputs": [
|
|
"rough workflow notes, SOPs, runbooks, prompts, transcripts, documents, or repeated task descriptions",
|
|
"an existing skill directory that needs refactor, evaluation, packaging, or governance hardening",
|
|
"target platform requirements such as OpenAI, Claude, generic Agent Skills, or team distribution",
|
|
"benchmark references, local constraints, desired maturity tier, and review standards"
|
|
],
|
|
"outputs": [
|
|
"A working skill package with lean SKILL.md, aligned agents/interface.yaml, justified references, scripts only when useful, eval evidence, reports, packaging metadata, and clear next iteration recommendations.",
|
|
"结构化 Skill 目录，共 8 类关键资产。"
|
|
]
|
|
},
|
|
"principles": [
|
|
{
|
|
"title": "意图澄清",
|
|
"body": "Turn repeated workflows, prompts, transcripts, runbooks, documents, or existing skill packages into routeable, evaluable, packageable, and governable agent skills for personal, team, library, or governed reuse."
|
|
},
|
|
{
|
|
"title": "边界路由",
|
|
"body": "用 frontmatter description 决定是否触发，并写明相邻非目标。"
|
|
},
|
|
{
|
|
"title": "资产分层",
|
|
"body": "把入口、参考、脚本、评估和报告拆到各自目录，避免 SKILL.md 膨胀。"
|
|
},
|
|
{
|
|
"title": "证据回路",
|
|
"body": "Ask only the highest-leverage clarification before adding package weight."
|
|
},
|
|
{
|
|
"title": "漂移观察",
|
|
"body": "Add near-neighbor exclusions and route evals before expanding workflow steps."
|
|
},
|
|
{
|
|
"title": "杠杆升级",
|
|
"body": "Name the recurring job, expected input, output, and strongest non-goal in compact language."
|
|
}
|
|
],
|
|
"roadmap": [
|
|
{
|
|
"title": "补齐世界证据",
|
|
"why": "世界级证据仍有 4 项待补；公开完成态 claim 必须继续保持阻塞。",
|
|
"actions": [
|
|
"补齐提供商留出证据：缺少真实 provider 模型运行和 token metadata。",
|
|
"补齐人工盲评证据：盲评 pair 仍待真实 reviewer 决策。",
|
|
"继续补齐剩余 2 项外部/人工证据，并保持 claim guard 为 pending 状态。"
|
|
],
|
|
"unlocks": "全部外部/人工证据被 ledger 接受后，才能进入公开 world-class claim 复核。",
|
|
"source": "world_class_evidence_ledger"
|
|
},
|
|
{
|
|
"title": "Borrow one proven pattern on purpose",
|
|
"why": "You already have public benchmark objects. The next gain is to choose one pattern intentionally instead of absorbing everything loosely.",
|
|
"actions": [
|
|
"Read the strongest pattern from obra/superpowers.",
|
|
"Decide whether to borrow method, structure, execution, or portability, but only one of them first.",
|
|
"Record what you will not borrow so the package stays light."
|
|
],
|
|
"unlocks": "A cleaner package shape with less accidental over-design."
|
|
},
|
|
{
|
|
"title": "Harden portability semantics",
|
|
"why": "The skill already signals reuse across environments, so contract clarity matters early.",
|
|
"actions": [
|
|
"Confirm activation mode, execution context, and trust assumptions.",
|
|
"Add or review degradation strategy for non-native targets.",
|
|
"Package the skill once to verify adapter expectations."
|
|
],
|
|
"unlocks": "Safer cross-environment reuse with less target drift."
|
|
}
|
|
],
|
|
"cards": [],
|
|
"introduction": [
|
|
"这份报告用于快速理解新生成 Skill 的定位、原理、触发边界和交付内容。",
|
|
"先确认重复任务、真实输入形态和可交付输出，再决定是否继续加 references、scripts 或 evals。",
|
|
"如果需求仍然模糊，优先回到 intent dialogue 收紧边界，再扩展包体结构。"
|
|
],
|
|
"benchmark_highlights": [],
|
|
"skill_ir": {
|
|
"schema_version": "2.0.0",
|
|
"target_count": 5,
|
|
"trigger_samples": 8,
|
|
"output_eval_cases": 3
|
|
},
|
|
"compiled_targets": {
|
|
"ok": true,
|
|
"schema_version": "1.0",
|
|
"summary": {
|
|
"target_count": 5,
|
|
"pass_count": 5,
|
|
"warn_count": 0,
|
|
"block_count": 0,
|
|
"failure_count": 0,
|
|
"warning_count": 0
|
|
},
|
|
"targets": [
|
|
{
|
|
"target": "openai",
|
|
"status": "pass",
|
|
"adapter_mode": "metadata-adapter",
|
|
"degradation_strategy": "metadata-adapter",
|
|
"native_surface": "OpenAI-style interface metadata plus neutral Agent Skills source",
|
|
"permission_enforcement": "metadata-only",
|
|
"generated_files": [
|
|
"targets/openai/adapter.json",
|
|
"targets/openai/agents/openai.yaml"
|
|
],
|
|
"unsupported_features": [
|
|
"client-native script permission prompts are represented as permission contract metadata"
|
|
],
|
|
"warnings": []
|
|
},
|
|
{
|
|
"target": "claude",
|
|
"status": "pass",
|
|
"adapter_mode": "neutral-source-plus-adapter",
|
|
"degradation_strategy": "neutral-source-plus-adapter",
|
|
"native_surface": "Claude-compatible neutral source folder with adapter notes",
|
|
"permission_enforcement": "metadata-fallback",
|
|
"generated_files": [
|
|
"targets/claude/adapter.json",
|
|
"targets/claude/README.md"
|
|
],
|
|
"unsupported_features": [
|
|
"vendor-native metadata fields are carried as adapter JSON and README notes"
|
|
],
|
|
"warnings": []
|
|
},
|
|
{
|
|
"target": "generic",
|
|
"status": "pass",
|
|
"adapter_mode": "agent-skills-compatible",
|
|
"degradation_strategy": "neutral-source",
|
|
"native_surface": "Agent Skills compatible neutral package",
|
|
"permission_enforcement": "consumer-enforced-or-metadata-only",
|
|
"generated_files": [
|
|
"targets/generic/adapter.json"
|
|
],
|
|
"unsupported_features": [],
|
|
"warnings": []
|
|
},
|
|
{
|
|
"target": "agent-skills-compatible",
|
|
"status": "pass",
|
|
"adapter_mode": "neutral-agent-skills-source",
|
|
"degradation_strategy": "neutral-source",
|
|
"native_surface": "Agent Skills standard source tree",
|
|
"permission_enforcement": "consumer-enforced-or-metadata-only",
|
|
"generated_files": [
|
|
"SKILL.md",
|
|
"agents/interface.yaml"
|
|
],
|
|
"unsupported_features": [],
|
|
"warnings": []
|
|
},
|
|
{
|
|
"target": "vscode",
|
|
"status": "pass",
|
|
"adapter_mode": "vscode-agent-skills-adapter",
|
|
"degradation_strategy": "agent-skills-source-with-vscode-notes",
|
|
"native_surface": "VS Code/Copilot Agent Skills project or user scope",
|
|
"permission_enforcement": "client-or-workspace-trust",
|
|
"generated_files": [
|
|
"targets/vscode/adapter.json",
|
|
"targets/vscode/README.md"
|
|
],
|
|
"unsupported_features": [
|
|
"VS Code installation scope is documented but not installed by this compiler"
|
|
],
|
|
"warnings": []
|
|
}
|
|
],
|
|
"failures": [],
|
|
"warnings": []
|
|
},
|
|
"output_quality": {
|
|
"case_count": 5,
|
|
"file_backed_case_count": 1,
|
|
"near_neighbor_case_count": 1,
|
|
"boundary_case_count": 1,
|
|
"baseline_pass_rate": 0.0,
|
|
"with_skill_pass_rate": 100.0,
|
|
"delta": 100.0,
|
|
"regression_count": 0,
|
|
"gate_pass": true,
|
|
"failure_taxonomy": [],
|
|
"blind_pair_count": 5
|
|
},
|
|
"output_execution": {
|
|
"ok": true,
|
|
"summary": {
|
|
"case_count": 5,
|
|
"variant_run_count": 10,
|
|
"command_executed_count": 10,
|
|
"model_executed_count": 0,
|
|
"recorded_fixture_count": 0,
|
|
"timing_observed_count": 10,
|
|
"token_observed_count": 0,
|
|
"token_estimated_count": 10,
|
|
"baseline_pass_rate": 0.0,
|
|
"with_skill_pass_rate": 100.0,
|
|
"delta": 100.0,
|
|
"regression_count": 0,
|
|
"failure_count": 0,
|
|
"gate_pass": true
|
|
},
|
|
"runner": {
|
|
"mode": "command",
|
|
"command": [
|
|
"python3",
|
|
"scripts/local_output_eval_runner.py"
|
|
],
|
|
"timeout_seconds": 30.0
|
|
},
|
|
"failures": []
|
|
},
|
|
"output_blind_review": {
|
|
"summary": {
|
|
"pair_count": 5,
|
|
"answer_key_separate": true,
|
|
"with_skill_hidden_count": 5
|
|
},
|
|
"seed": "yao-output-eval-blind-v1",
|
|
"pair_count": 5,
|
|
"answer_key_separate": true
|
|
},
|
|
"output_review_kit": {
|
|
"ok": true,
|
|
"summary": {
|
|
"case_count": 5,
|
|
"ready_for_adjudication_count": 0,
|
|
"pending_decision_count": 5,
|
|
"invalid_decision_count": 0,
|
|
"reviewer_metadata_present": false,
|
|
"answer_key_hidden": true,
|
|
"answer_key_path_exposed": false,
|
|
"ready_to_run_adjudication": false,
|
|
"failure_count": 0
|
|
},
|
|
"artifacts": {
|
|
"reviewer_kit_json": "reports/output_review_kit.json",
|
|
"reviewer_kit_markdown": "reports/output_review_kit.md",
|
|
"reviewer_kit_html": "reports/output_review_kit.html",
|
|
"blind_pack_json": "reports/output_blind_review_pack.json",
|
|
"blind_pack_markdown": "reports/output_blind_review_pack.md",
|
|
"decisions": "reports/output_review_decisions.json",
|
|
"adjudication_json": "reports/output_review_adjudication.json",
|
|
"adjudication_markdown": "reports/output_review_adjudication.md"
|
|
},
|
|
"failures": []
|
|
},
|
|
"output_review_adjudication": {
|
|
"ok": true,
|
|
"summary": {
|
|
"pair_count": 5,
|
|
"judgment_count": 0,
|
|
"pending_count": 5,
|
|
"agreement_count": 0,
|
|
"disagreement_count": 0,
|
|
"invalid_decision_count": 0,
|
|
"answer_revealed_count": 0,
|
|
"pending_answer_hidden_count": 5,
|
|
"agreement_rate": null,
|
|
"needs_review": true,
|
|
"failure_count": 0,
|
|
"reviewer_checklist_count": 5,
|
|
"reviewer_checklist_pending_count": 5,
|
|
"reviewer_checklist_invalid_count": 0,
|
|
"reviewer_checklist_ready_count": 0
|
|
},
|
|
"reviewer": "",
|
|
"reviewed_at": "",
|
|
"failures": []
|
|
},
|
|
"benchmark_reproducibility": {
|
|
"ok": true,
|
|
"summary": {
|
|
"reproducibility_ready": true,
|
|
"release_lock_ready": true,
|
|
"methodology_complete": true,
|
|
"required_artifact_count": 24,
|
|
"missing_artifact_count": 0,
|
|
"evidence_bundle_sha256": "0d1c762a722d1bbc83339a0365efcfcdf027849fc83c7079da92a524b905f5ab",
|
|
"source_contract_sha256": "4660a11db94947ab603dca42eddc447698785d08f0df2972bf2ca43454683306",
|
|
"archive_sha256": "6852cf91a74d232c32d732b7c159c971827abf23af50153987193b084ad3b5cc",
|
|
"output_case_count": 5,
|
|
"failure_disclosure_count": 3,
|
|
"command_count": 22,
|
|
"command_executed_count": 10,
|
|
"timing_observed_count": 10,
|
|
"model_executed_count": 0,
|
|
"token_observed_count": 0,
|
|
"human_review_complete": false,
|
|
"provider_evidence_complete": false,
|
|
"world_class_ready": false,
|
|
"world_class_open_gap_count": 4,
|
|
"world_class_task_count": 4,
|
|
"world_class_ledger_pending_count": 4,
|
|
"world_class_source_check_count": 13,
|
|
"world_class_source_pass_count": 6,
|
|
"world_class_source_blocked_count": 7,
|
|
"public_claim_ready": false,
|
|
"public_claim_blocker_count": 4,
|
|
"working_tree_dirty": false,
|
|
"changed_file_count": 0
|
|
},
|
|
"commit": "27a5c120081fe8f2518de60c6a2278f41762e9b6",
|
|
"missing_artifacts": [],
|
|
"limitations": [
|
|
"The git commit and dirty flag are generation-time context; the evidence bundle hash is the durable artifact anchor inside a committed report.",
|
|
"Local command-runner evidence is reproducible but does not replace provider-backed model holdout evidence.",
|
|
"Pending blind-review decisions are visible but do not count as human adjudication.",
|
|
"World-class readiness remains false until external and human evidence gaps close."
|
|
]
|
|
},
|
|
"runtime_conformance": {
|
|
"target_count": 5,
|
|
"pass_count": 5,
|
|
"fail_count": 0
|
|
},
|
|
"runtime_permissions": {
|
|
"ok": true,
|
|
"summary": {
|
|
"target_count": 4,
|
|
"pass_count": 4,
|
|
"fail_count": 0,
|
|
"native_enforcement_count": 0,
|
|
"metadata_fallback_count": 4,
|
|
"residual_risk_count": 4,
|
|
"required_capability_count": 3,
|
|
"failure_count": 0,
|
|
"installer_enforcement_source_status": "present",
|
|
"installer_enforcement_target_count": 4,
|
|
"installer_enforcement_pass_count": 4,
|
|
"installer_permission_enforced_count": 12,
|
|
"installer_permission_failure_count": 0,
|
|
"installer_permission_capability_count": 3,
|
|
"world_class_native_evidence_ready": false,
|
|
"installer_enforcement_ready": true
|
|
},
|
|
"expected_capabilities": [
|
|
"file_write",
|
|
"network",
|
|
"subprocess"
|
|
],
|
|
"targets": [
|
|
{
|
|
"target": "openai",
|
|
"status": "pass",
|
|
"assurance": "metadata-fallback-explicit",
|
|
"native_enforcement": false,
|
|
"metadata_fallback_explicit": true,
|
|
"residual_risks": [
|
|
"Client-native permission enforcement is not provided by this target; installer or operator must honor metadata."
|
|
]
|
|
},
|
|
{
|
|
"target": "claude",
|
|
"status": "pass",
|
|
"assurance": "metadata-fallback-explicit",
|
|
"native_enforcement": false,
|
|
"metadata_fallback_explicit": true,
|
|
"residual_risks": [
|
|
"Client-native permission enforcement is not provided by this target; installer or operator must honor metadata."
|
|
]
|
|
},
|
|
{
|
|
"target": "generic",
|
|
"status": "pass",
|
|
"assurance": "metadata-fallback-explicit",
|
|
"native_enforcement": false,
|
|
"metadata_fallback_explicit": true,
|
|
"residual_risks": [
|
|
"Client-native permission enforcement is not provided by this target; installer or operator must honor metadata."
|
|
]
|
|
},
|
|
{
|
|
"target": "vscode",
|
|
"status": "pass",
|
|
"assurance": "metadata-fallback-explicit",
|
|
"native_enforcement": false,
|
|
"metadata_fallback_explicit": true,
|
|
"residual_risks": [
|
|
"Client-native permission enforcement is not provided by this target; installer or operator must honor metadata."
|
|
]
|
|
}
|
|
],
|
|
"failures": []
|
|
},
|
|
"trust_security": {
|
|
"scanned_files": 194,
|
|
"script_count": 107,
|
|
"internal_module_count": 26,
|
|
"secret_findings": 0,
|
|
"dependency_files": [
|
|
"requirements-ci.txt"
|
|
],
|
|
"network_script_count": 3,
|
|
"network_policy_covered_count": 3,
|
|
"network_policy_missing_count": 0,
|
|
"file_write_script_count": 68,
|
|
"permission_required_count": 3,
|
|
"permission_approved_count": 3,
|
|
"permission_missing_count": 0,
|
|
"permission_invalid_count": 0,
|
|
"permission_expired_count": 0,
|
|
"help_smoke_checked_count": 81,
|
|
"help_smoke_failed_count": 0,
|
|
"interactive_script_count": 0,
|
|
"package_hash_scope": "source-contract-without-generated-reports",
|
|
"package_hash_file_count": 194,
|
|
"package_sha256": "4660a11db94947ab603dca42eddc447698785d08f0df2972bf2ca43454683306"
|
|
},
|
|
"skill_atlas": {
|
|
"skill_count": 12,
|
|
"actionable_skill_count": 1,
|
|
"route_collision_count": 5,
|
|
"actionable_route_collision_count": 0,
|
|
"owner_gap_count": 9,
|
|
"actionable_owner_gap_count": 0,
|
|
"stale_count": 10,
|
|
"actionable_stale_count": 0,
|
|
"shared_resource_count": 0,
|
|
"no_route_opportunity_count": 0,
|
|
"telemetry_report_count": 1,
|
|
"drift_signal_count": 0,
|
|
"actionable_drift_signal_count": 0,
|
|
"non_actionable_issue_count": 24
|
|
},
|
|
"registry_distribution": {
|
|
"ok": true,
|
|
"package": {
|
|
"schema_version": "2.0",
|
|
"name": "yao-meta-skill",
|
|
"version": "1.1.0",
|
|
"description": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use when asked to create a skill, turn a repeated process into a reusable skill, improve an existing skill, add evals, or package a skill for team reuse.",
|
|
"targets": [
|
|
"openai",
|
|
"claude",
|
|
"generic",
|
|
"agent-skills-compatible",
|
|
"vscode"
|
|
],
|
|
"maturity": "governed",
|
|
"owner": "Yao Team",
|
|
"review_cadence": "quarterly",
|
|
"trust_level": "local",
|
|
"license": "MIT",
|
|
"checksums": {
|
|
"package_sha256": "4660a11db94947ab603dca42eddc447698785d08f0df2972bf2ca43454683306",
|
|
"archive_sha256": "6852cf91a74d232c32d732b7c159c971827abf23af50153987193b084ad3b5cc"
|
|
},
|
|
"compatibility": {
|
|
"openai": "pass",
|
|
"claude": "pass",
|
|
"agent-skills": "pass",
|
|
"vscode": "pass",
|
|
"generic": "pass",
|
|
"agent-skills-compatible": "pass"
|
|
},
|
|
"source": {
|
|
"skill_dir": ".",
|
|
"skill_ir": "skill-ir/examples/yao-meta-skill.json",
|
|
"ir_schema_version": "2.0.0",
|
|
"canonical_metadata": "agents/interface.yaml"
|
|
},
|
|
"artifacts": {
|
|
"overview_html": "reports/skill-overview.html",
|
|
"review_studio_html": "reports/review-studio.html",
|
|
"trust_report": "reports/security_trust_report.md",
|
|
"conformance_matrix": "reports/conformance_matrix.md",
|
|
"compiled_targets": "reports/compiled_targets.md",
|
|
"package_verification": "reports/package_verification.md",
|
|
"install_simulation": "reports/install_simulation.md",
|
|
"adoption_drift": "reports/adoption_drift_report.md",
|
|
"review_waivers": "reports/review_waivers.md",
|
|
"review_annotations": "reports/review_annotations.md",
|
|
"package_metadata": "registry/packages/yao-meta-skill.json"
|
|
},
|
|
"distribution": {
|
|
"archive_verified": true,
|
|
"archive_sha256": "6852cf91a74d232c32d732b7c159c971827abf23af50153987193b084ad3b5cc",
|
|
"package_verification": "reports/package_verification.json",
|
|
"install_simulated": true,
|
|
"install_simulation": "reports/install_simulation.json"
|
|
},
|
|
"generated_at": "2026-06-13"
|
|
},
|
|
"failures": [],
|
|
"warnings": []
|
|
},
|
|
"package_verification": {
|
|
"ok": true,
|
|
"summary": {
|
|
"target_count": 4,
|
|
"adapter_count": 4,
|
|
"archive_present": true,
|
|
"archive_sha256": "6852cf91a74d232c32d732b7c159c971827abf23af50153987193b084ad3b5cc",
|
|
"archive_entry_count": 586,
|
|
"failure_count": 0,
|
|
"warning_count": 0
|
|
},
|
|
"failures": [],
|
|
"warnings": []
|
|
},
|
|
"install_simulation": {
|
|
"ok": true,
|
|
"summary": {
|
|
"archive_present": true,
|
|
"archive_entry_count": 607,
|
|
"archive_extracted": true,
|
|
"entrypoint_loaded": true,
|
|
"manifest_loaded": true,
|
|
"interface_loaded": true,
|
|
"adapter_count": 4,
|
|
"installer_permission_enforced_count": 12,
|
|
"installer_permission_failure_count": 0,
|
|
"permission_target_count": 4,
|
|
"permission_capability_count": 3,
|
|
"install_root_is_temp": false,
|
|
"failure_count": 0,
|
|
"warning_count": 0
|
|
},
|
|
"failures": [],
|
|
"warnings": []
|
|
},
|
|
"upgrade_check": {
|
|
"ok": true,
|
|
"summary": {
|
|
"declared_bump": "minor",
|
|
"recommended_bump": "minor",
|
|
"breaking_change_count": 0,
|
|
"added_target_count": 2,
|
|
"metadata_change_count": 1,
|
|
"checksum_change_count": 2,
|
|
"failure_count": 0,
|
|
"warning_count": 0
|
|
},
|
|
"upgrade_diff": {
|
|
"name_changed": false,
|
|
"added_targets": [
|
|
"agent-skills-compatible",
|
|
"vscode"
|
|
],
|
|
"removed_targets": [],
|
|
"compatibility_changes": [
|
|
{
|
|
"target": "agent-skills",
|
|
"from": "missing",
|
|
"to": "pass",
|
|
"direction": "improved"
|
|
},
|
|
{
|
|
"target": "agent-skills-compatible",
|
|
"from": "missing",
|
|
"to": "pass",
|
|
"direction": "improved"
|
|
},
|
|
{
|
|
"target": "vscode",
|
|
"from": "missing",
|
|
"to": "pass",
|
|
"direction": "improved"
|
|
}
|
|
],
|
|
"metadata_changes": [
|
|
{
|
|
"field": "description",
|
|
"from": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes.",
|
|
"to": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use when asked to create a skill, turn a repeated process into a reusable skill, improve an existing skill, add evals, or package a skill for team reuse."
|
|
}
|
|
],
|
|
"checksum_changes": [
|
|
{
|
|
"field": "archive_sha256",
|
|
"from": "",
|
|
"to": "6852cf91a74d232c32d732b7c159c971827abf23af50153987193b084ad3b5cc"
|
|
},
|
|
{
|
|
"field": "package_sha256",
|
|
"from": "0000000000000000000000000000000000000000000000000000000000000000",
|
|
"to": "4660a11db94947ab603dca42eddc447698785d08f0df2972bf2ca43454683306"
|
|
}
|
|
]
|
|
},
|
|
"release_notes": [
|
|
"Recommended version bump: minor.",
|
|
"Added targets: agent-skills-compatible, vscode.",
|
|
"Package or archive checksum changed; reviewers should verify package artifacts before release.",
|
|
"Package verification evidence: reports/package_verification.md."
|
|
],
|
|
"failures": [],
|
|
"warnings": []
|
|
},
|
|
"adoption_drift": {
|
|
"ok": true,
|
|
"summary": {
|
|
"event_count": 1,
|
|
"adoption_sample_count": 0,
|
|
"activation_count": 0,
|
|
"accepted_count": 0,
|
|
"edited_count": 0,
|
|
"rejected_count": 0,
|
|
"missed_count": 0,
|
|
"failed_count": 0,
|
|
"adoption_rate": 0,
|
|
"missed_trigger_count": 0,
|
|
"wrong_trigger_count": 0,
|
|
"bad_output_count": 0,
|
|
"script_error_count": 0,
|
|
"missing_resource_count": 0,
|
|
"review_overdue_count": 0,
|
|
"risk_band": "low",
|
|
"event_types": {
|
|
"review_event": 1
|
|
},
|
|
"failure_types": {},
|
|
"source_types": {
|
|
"manual": 1
|
|
},
|
|
"command_counts": {}
|
|
},
|
|
"next_iteration_candidates": [],
|
|
"privacy_contract": {
|
|
"storage": "local-first",
|
|
"event_scope": "metadata-only",
|
|
"raw_content_allowed": false,
|
|
"raw_event_log_packaged": false,
|
|
"blocked_fields": [
|
|
"content",
|
|
"input",
|
|
"inputs",
|
|
"message",
|
|
"messages",
|
|
"note",
|
|
"output",
|
|
"outputs",
|
|
"prompt",
|
|
"raw",
|
|
"text",
|
|
"transcript"
|
|
]
|
|
},
|
|
"failures": []
|
|
},
|
|
"review_waivers": {
|
|
"ok": true,
|
|
"summary": {
|
|
"waiver_count": 0,
|
|
"active_count": 0,
|
|
"expired_count": 0,
|
|
"invalid_count": 0,
|
|
"covered_gate_count": 0,
|
|
"covered_gate_keys": [],
|
|
"waiver_candidate_count": 2,
|
|
"waiverable_open_count": 1,
|
|
"non_waivable_count": 1
|
|
},
|
|
"policy": {
|
|
"blocker_waivers_allowed": false,
|
|
"minimum_reason_chars": 20,
|
|
"expires_required": true,
|
|
"known_gate_keys": [
|
|
"context-budget",
|
|
"intent-canvas",
|
|
"operations-loop",
|
|
"output-lab",
|
|
"permission-gates",
|
|
"permission-runtime",
|
|
"registry-audit",
|
|
"release-notes",
|
|
"runtime-matrix",
|
|
"skill-atlas",
|
|
"trigger-lab",
|
|
"trust-report"
|
|
]
|
|
},
|
|
"failures": [],
|
|
"warnings": []
|
|
},
|
|
"review_annotations": {
|
|
"ok": true,
|
|
"summary": {
|
|
"annotation_count": 0,
|
|
"open_count": 0,
|
|
"resolved_count": 0,
|
|
"deferred_count": 0,
|
|
"open_blocker_count": 0,
|
|
"open_warning_count": 0,
|
|
"linked_gate_count": 0,
|
|
"target_missing_count": 0,
|
|
"failure_count": 0
|
|
},
|
|
"annotations": [],
|
|
"failures": []
|
|
},
|
|
"world_class_evidence_plan": {
|
|
"ok": true,
|
|
"summary": {
|
|
"audit_decision": "continue-iteration",
|
|
"world_class_ready": false,
|
|
"audit_world_class_ready": false,
|
|
"ready_to_claim_world_class": false,
|
|
"ledger_completion_required": true,
|
|
"evidence_requirement_count": 4,
|
|
"task_count": 4,
|
|
"human_task_count": 1,
|
|
"external_task_count": 3,
|
|
"review_task_count": 0,
|
|
"decision": "collect-external-evidence"
|
|
},
|
|
"tasks": [
|
|
{
|
|
"key": "provider-holdout",
|
|
"label": "Provider Holdout",
|
|
"status": "external_required",
|
|
"category": "external",
|
|
"owner": "operator with provider credentials",
|
|
"current": "model-executed 0; token-observed 0",
|
|
"objective": "Collect at least one provider-backed output-eval holdout run with model, timing, and token metadata.",
|
|
"runbook": [
|
|
"YAO_OUTPUT_EVAL_MODEL=gpt-4.1-mini OPENAI_API_KEY=<redacted> python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60",
|
|
"python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>",
|
|
"Copy evidence/world_class/templates/provider-holdout.intake.json to evidence/world_class/submissions/provider-holdout.json and fill only real evidence fields.",
|
|
"python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions"
|
|
],
|
|
"success_checks": [
|
|
"reports/output_execution_runs.json summary.model_executed_count > 0",
|
|
"reports/output_execution_runs.json summary.timing_observed_count > 0",
|
|
"reports/output_execution_runs.json summary.token_observed_count > 0",
|
|
"reports/skill_os2_audit.json item provider-holdout status becomes pass"
|
|
],
|
|
"evidence_artifacts": [
|
|
"reports/output_execution_runs.json",
|
|
"reports/output_execution_runs.md",
|
|
"reports/skill_os2_audit.json",
|
|
"evidence/world_class/intake.schema.json",
|
|
"evidence/world_class/templates/provider-holdout.intake.json",
|
|
"reports/world_class_evidence_intake.json",
|
|
"reports/world_class_evidence_intake.md"
|
|
],
|
|
"privacy_contract": [
|
|
"Do not commit provider credentials or environment dumps.",
|
|
"The output execution report records output hashes and aggregate run metadata, not raw provider prompts."
|
|
],
|
|
"audit_next_action": "Run provider-backed holdout cases with real credentials and commit only aggregate evidence."
|
|
},
|
|
{
|
|
"key": "human-adjudication",
|
|
"label": "Human Adjudication",
|
|
"status": "human_required",
|
|
"category": "human",
|
|
"owner": "human reviewer",
|
|
"current": "0/5 decisions; pending 5",
|
|
"objective": "Record real blind A/B reviewer decisions before claiming human output review completion.",
|
|
"runbook": [
|
|
"python3 scripts/yao.py output-review-kit --write-template",
|
|
"Open reports/output_review_kit.md and choose A or B for each pair without opening the answer key.",
|
|
"python3 scripts/adjudicate_output_review.py --write-template",
|
|
"Edit reports/output_review_decisions.json with winner_variant values and reviewer metadata.",
|
|
"python3 scripts/yao.py output-review",
|
|
"python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>",
|
|
"Copy evidence/world_class/templates/human-adjudication.intake.json to evidence/world_class/submissions/human-adjudication.json and fill only real evidence fields.",
|
|
"python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions"
|
|
],
|
|
"success_checks": [
|
|
"reports/output_review_adjudication.json summary.pending_count == 0",
|
|
"reports/output_review_adjudication.json summary.judgment_count == summary.pair_count",
|
|
"reports/output_review_adjudication.json summary.invalid_decision_count == 0",
|
|
"reports/skill_os2_audit.json item human-adjudication status becomes pass"
|
|
],
|
|
"evidence_artifacts": [
|
|
"reports/output_blind_review_pack.md",
|
|
"reports/output_review_kit.md",
|
|
"reports/output_review_decisions.json",
|
|
"reports/output_review_adjudication.json",
|
|
"reports/output_review_adjudication.md",
|
|
"evidence/world_class/intake.schema.json",
|
|
"evidence/world_class/templates/human-adjudication.intake.json",
|
|
"reports/world_class_evidence_intake.json",
|
|
"reports/world_class_evidence_intake.md"
|
|
],
|
|
"privacy_contract": [
|
|
"Reviewer decisions should not include raw user data or private customer detail.",
|
|
"Keep the answer key separate until after decisions are recorded."
|
|
],
|
|
"audit_next_action": "Record real A/B choices in the decision template, then regenerate adjudication."
|
|
},
|
|
{
|
|
"key": "native-permission-enforcement",
|
|
"label": "Native Permission Enforcement",
|
|
"status": "external_required",
|
|
"category": "external",
|
|
"owner": "target client or installer integrator",
|
|
"current": "native-enforced targets 0; installer-enforced targets 4",
|
|
"objective": "Prove at least one real target client or external installer runtime guard enforces approved high-permission capabilities.",
|
|
"runbook": [
|
|
"Implement or connect a real target client or external installer runtime guard that blocks undeclared network, file_write, or subprocess capabilities.",
|
|
"Update the generated target adapter only when the guard is actually enforced by that target.",
|
|
"python3 scripts/yao.py package . --platform openai --platform claude --platform generic --platform vscode --output-dir dist --zip",
|
|
"python3 scripts/yao.py install-simulate . --package-dir dist --install-root dist/install-simulation",
|
|
"python3 scripts/yao.py runtime-permissions . --package-dir dist",
|
|
"python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>",
|
|
"Copy evidence/world_class/templates/native-permission-enforcement.intake.json to evidence/world_class/submissions/native-permission-enforcement.json and fill only real evidence fields.",
|
|
"python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions"
|
|
],
|
|
"success_checks": [
|
|
"reports/runtime_permission_probes.json summary.native_enforcement_count > 0",
|
|
"reports/runtime_permission_probes.json summary.failure_count == 0",
|
|
"reports/runtime_permission_probes.json summary.installer_enforcement_pass_count records local installer enforcement but does not replace native evidence",
|
|
"reports/skill_os2_audit.json item native-permission-enforcement status becomes pass"
|
|
],
|
|
"evidence_artifacts": [
|
|
"dist/targets/*/adapter.json",
|
|
"reports/runtime_permission_probes.json",
|
|
"reports/runtime_permission_probes.md",
|
|
"reports/install_simulation.json",
|
|
"reports/install_simulation.md",
|
|
"security/permission_policy.json",
|
|
"evidence/world_class/intake.schema.json",
|
|
"evidence/world_class/templates/native-permission-enforcement.intake.json",
|
|
"reports/world_class_evidence_intake.json",
|
|
"reports/world_class_evidence_intake.md"
|
|
],
|
|
"privacy_contract": [
|
|
"Do not mark native_enforcement true for metadata-only fallbacks.",
|
|
"Keep residual risks visible for targets that still rely on operator enforcement."
|
|
],
|
|
"audit_next_action": "Integrate a real target-client or external installer runtime guard before claiming native permission enforcement."
|
|
},
|
|
{
|
|
"key": "native-client-telemetry",
|
|
"label": "Native Client Telemetry",
|
|
"status": "external_required",
|
|
"category": "external",
|
|
"owner": "Browser/Chrome/IDE/provider client integrator",
|
|
"current": "external source events 0; adoption samples 0",
|
|
"objective": "Import production metadata-only events from a real external client into the local drift loop.",
|
|
"runbook": [
|
|
"python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension://<extension-id>/",
|
|
"Install the generated native messaging manifest for the real client and send at least one accepted skill_activation or skill_output event.",
|
|
"python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl",
|
|
"python3 scripts/yao.py skill-atlas --workspace-root .",
|
|
"python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>",
|
|
"Copy evidence/world_class/templates/native-client-telemetry.intake.json to evidence/world_class/submissions/native-client-telemetry.json and fill only real evidence fields.",
|
|
"python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions"
|
|
],
|
|
"success_checks": [
|
|
"reports/adoption_drift_report.json summary.source_types.external > 0",
|
|
"reports/adoption_drift_report.json summary.adoption_sample_count > 0",
|
|
"reports/skill_os2_audit.json item native-client-telemetry status becomes pass"
|
|
],
|
|
"evidence_artifacts": [
|
|
"reports/adoption_drift_report.json",
|
|
"reports/adoption_drift_report.md",
|
|
"reports/telemetry_hook_recipes.json",
|
|
"scripts/telemetry_native_host.py",
|
|
"evidence/world_class/intake.schema.json",
|
|
"evidence/world_class/templates/native-client-telemetry.intake.json",
|
|
"reports/world_class_evidence_intake.json",
|
|
"reports/world_class_evidence_intake.md"
|
|
],
|
|
"privacy_contract": [
|
|
"Telemetry must remain metadata-only and local-first.",
|
|
"Do not package reports/telemetry_events.jsonl or any raw prompt, output, transcript, note, or message field."
|
|
],
|
|
"audit_next_action": "Install a real client against the native host and import production metadata-only events."
|
|
}
|
|
],
|
|
"source_audit": {
|
|
"json": "reports/skill_os2_audit.json",
|
|
"markdown": "reports/skill_os2_audit.md",
|
|
"open_gap_count": 4
|
|
}
|
|
},
|
|
"world_class_evidence_ledger": {
|
|
"ok": true,
|
|
"summary": {
|
|
"ledger_entry_count": 4,
|
|
"source_accepted_count": 0,
|
|
"accepted_count": 0,
|
|
"pending_count": 4,
|
|
"human_pending_count": 1,
|
|
"external_pending_count": 3,
|
|
"submitted_entry_count": 0,
|
|
"missing_submission_count": 4,
|
|
"invalid_submission_count": 0,
|
|
"source_check_count": 13,
|
|
"source_pass_count": 6,
|
|
"source_blocked_count": 7,
|
|
"submitted_but_pending_count": 0,
|
|
"source_accepted_without_valid_submission_count": 0,
|
|
"overclaim_guard_active": true,
|
|
"ready_to_claim_world_class": false,
|
|
"decision": "evidence-pending"
|
|
},
|
|
"entries": [
|
|
{
|
|
"key": "provider-holdout",
|
|
"label": "Provider Holdout",
|
|
"category": "external",
|
|
"owner": "operator with provider credentials",
|
|
"status": "pending",
|
|
"source_status": "external_required",
|
|
"source_accepted": false,
|
|
"current": "model-executed 0; token-observed 0",
|
|
"objective": "Collect at least one provider-backed output-eval holdout run with model, timing, and token metadata.",
|
|
"runbook": [
|
|
"YAO_OUTPUT_EVAL_MODEL=gpt-4.1-mini OPENAI_API_KEY=<redacted> python3 scripts/yao.py output-exec --provider-runner openai --timeout-seconds 60",
|
|
"python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>",
|
|
"Copy evidence/world_class/templates/provider-holdout.intake.json to evidence/world_class/submissions/provider-holdout.json and fill only real evidence fields.",
|
|
"python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions"
|
|
],
|
|
"provenance_requirements": [
|
|
"provider-backed model run",
|
|
"observed timing",
|
|
"observed token metadata"
|
|
],
|
|
"success_checks": [
|
|
"reports/output_execution_runs.json summary.model_executed_count > 0",
|
|
"reports/output_execution_runs.json summary.timing_observed_count > 0",
|
|
"reports/output_execution_runs.json summary.token_observed_count > 0",
|
|
"reports/skill_os2_audit.json item provider-holdout status becomes pass"
|
|
],
|
|
"evidence_artifacts": [
|
|
"reports/output_execution_runs.json",
|
|
"reports/output_execution_runs.md",
|
|
"reports/skill_os2_audit.json",
|
|
"evidence/world_class/intake.schema.json",
|
|
"evidence/world_class/templates/provider-holdout.intake.json",
|
|
"reports/world_class_evidence_intake.json",
|
|
"reports/world_class_evidence_intake.md"
|
|
],
|
|
"privacy_contract": [
|
|
"Do not commit provider credentials or environment dumps.",
|
|
"The output execution report records output hashes and aggregate run metadata, not raw provider prompts."
|
|
],
|
|
"observed_state": {
|
|
"model_executed_count": 0,
|
|
"timing_observed_count": 10,
|
|
"token_observed_count": 0,
|
|
"accepted": false
|
|
},
|
|
"source_checklist": [
|
|
{
|
|
"evidence_key": "provider-holdout",
|
|
"label": "Provider model run",
|
|
"field": "model_executed_count",
|
|
"expected": ">0",
|
|
"actual": 0,
|
|
"status": "blocked",
|
|
"source_accepted": false,
|
|
"next_action": "Run provider-backed output-exec with real credentials."
|
|
},
|
|
{
|
|
"evidence_key": "provider-holdout",
|
|
"label": "Timing observed",
|
|
"field": "timing_observed_count",
|
|
"expected": ">0",
|
|
"actual": 10,
|
|
"status": "pass",
|
|
"source_accepted": false,
|
|
"next_action": "Provider execution should record timing metadata."
|
|
},
|
|
{
|
|
"evidence_key": "provider-holdout",
|
|
"label": "Token usage observed",
|
|
"field": "token_observed_count",
|
|
"expected": ">0",
|
|
"actual": 0,
|
|
"status": "blocked",
|
|
"source_accepted": false,
|
|
"next_action": "Provider execution should return non-estimated token usage."
|
|
}
|
|
],
|
|
"source_check_count": 3,
|
|
"source_pass_count": 1,
|
|
"source_blocked_count": 2,
|
|
"submission_state": {
|
|
"status": "missing",
|
|
"path": "evidence/world_class/submissions/provider-holdout.json",
|
|
"artifact_ref_count": 0,
|
|
"attested_real_evidence": false,
|
|
"privacy_contract_satisfied": false,
|
|
"ledger_counts_as_completion": false
|
|
},
|
|
"anti_overclaim": {
|
|
"planned_work_counts_as_evidence": false,
|
|
"metadata_fallback_counts_as_native_enforcement": false,
|
|
"pending_review_counts_as_human_decision": false,
|
|
"local_command_runner_counts_as_provider_model": false
|
|
},
|
|
"next_action": "Run provider-backed holdout cases with real credentials and commit only aggregate evidence."
|
|
},
|
|
{
|
|
"key": "human-adjudication",
|
|
"label": "Human Adjudication",
|
|
"category": "human",
|
|
"owner": "human reviewer",
|
|
"status": "pending",
|
|
"source_status": "human_required",
|
|
"source_accepted": false,
|
|
"current": "0/5 decisions; pending 5",
|
|
"objective": "Record real blind A/B reviewer decisions before claiming human output review completion.",
|
|
"runbook": [
|
|
"python3 scripts/yao.py output-review-kit --write-template",
|
|
"Open reports/output_review_kit.md and choose A or B for each pair without opening the answer key.",
|
|
"python3 scripts/adjudicate_output_review.py --write-template",
|
|
"Edit reports/output_review_decisions.json with winner_variant values and reviewer metadata.",
|
|
"python3 scripts/yao.py output-review",
|
|
"python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>",
|
|
"Copy evidence/world_class/templates/human-adjudication.intake.json to evidence/world_class/submissions/human-adjudication.json and fill only real evidence fields.",
|
|
"python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions"
|
|
],
|
|
"provenance_requirements": [
|
|
"real reviewer identity",
|
|
"blind A/B decisions",
|
|
"answer key unopened until decisions exist"
|
|
],
|
|
"success_checks": [
|
|
"reports/output_review_adjudication.json summary.pending_count == 0",
|
|
"reports/output_review_adjudication.json summary.judgment_count == summary.pair_count",
|
|
"reports/output_review_adjudication.json summary.invalid_decision_count == 0",
|
|
"reports/skill_os2_audit.json item human-adjudication status becomes pass"
|
|
],
|
|
"evidence_artifacts": [
|
|
"reports/output_blind_review_pack.md",
|
|
"reports/output_review_kit.md",
|
|
"reports/output_review_decisions.json",
|
|
"reports/output_review_adjudication.json",
|
|
"reports/output_review_adjudication.md",
|
|
"evidence/world_class/intake.schema.json",
|
|
"evidence/world_class/templates/human-adjudication.intake.json",
|
|
"reports/world_class_evidence_intake.json",
|
|
"reports/world_class_evidence_intake.md"
|
|
],
|
|
"privacy_contract": [
|
|
"Reviewer decisions should not include raw user data or private customer detail.",
|
|
"Keep the answer key separate until after decisions are recorded."
|
|
],
|
|
"observed_state": {
|
|
"pair_count": 5,
|
|
"judgment_count": 0,
|
|
"pending_count": 5,
|
|
"invalid_decision_count": 0,
|
|
"answer_revealed_count": 0,
|
|
"accepted": false
|
|
},
|
|
"source_checklist": [
|
|
{
|
|
"evidence_key": "human-adjudication",
|
|
"label": "Review pairs exist",
|
|
"field": "pair_count",
|
|
"expected": ">0",
|
|
"actual": 5,
|
|
"status": "pass",
|
|
"source_accepted": false,
|
|
"next_action": "Generate the blind A/B review pack."
|
|
},
|
|
{
|
|
"evidence_key": "human-adjudication",
|
|
"label": "No pending decisions",
|
|
"field": "pending_count",
|
|
"expected": "==0",
|
|
"actual": 5,
|
|
"status": "blocked",
|
|
"source_accepted": false,
|
|
"next_action": "Record a reviewer choice for every pair."
|
|
},
|
|
{
|
|
"evidence_key": "human-adjudication",
|
|
"label": "Judgments complete",
|
|
"field": "judgment_count",
|
|
"expected": "==pair_count",
|
|
"actual": 0,
|
|
"status": "blocked",
|
|
"source_accepted": false,
|
|
"next_action": "Every pair needs one valid human judgment."
|
|
},
|
|
{
|
|
"evidence_key": "human-adjudication",
|
|
"label": "No invalid decisions",
|
|
"field": "invalid_decision_count",
|
|
"expected": "==0",
|
|
"actual": 0,
|
|
"status": "pass",
|
|
"source_accepted": false,
|
|
"next_action": "Fix malformed winner/confidence entries."
|
|
}
|
|
],
|
|
"source_check_count": 4,
|
|
"source_pass_count": 2,
|
|
"source_blocked_count": 2,
|
|
"submission_state": {
|
|
"status": "missing",
|
|
"path": "evidence/world_class/submissions/human-adjudication.json",
|
|
"artifact_ref_count": 0,
|
|
"attested_real_evidence": false,
|
|
"privacy_contract_satisfied": false,
|
|
"ledger_counts_as_completion": false
|
|
},
|
|
"anti_overclaim": {
|
|
"planned_work_counts_as_evidence": false,
|
|
"metadata_fallback_counts_as_native_enforcement": false,
|
|
"pending_review_counts_as_human_decision": false,
|
|
"local_command_runner_counts_as_provider_model": false
|
|
},
|
|
"next_action": "Record real A/B choices in the decision template, then regenerate adjudication."
|
|
},
|
|
{
|
|
"key": "native-permission-enforcement",
|
|
"label": "Native Permission Enforcement",
|
|
"category": "external",
|
|
"owner": "target client or installer integrator",
|
|
"status": "pending",
|
|
"source_status": "external_required",
|
|
"source_accepted": false,
|
|
"current": "native-enforced targets 0; installer-enforced targets 4",
|
|
"objective": "Prove at least one real target client or external installer runtime guard enforces approved high-permission capabilities.",
|
|
"runbook": [
|
|
"Implement or connect a real target client or external installer runtime guard that blocks undeclared network, file_write, or subprocess capabilities.",
|
|
"Update the generated target adapter only when the guard is actually enforced by that target.",
|
|
"python3 scripts/yao.py package . --platform openai --platform claude --platform generic --platform vscode --output-dir dist --zip",
|
|
"python3 scripts/yao.py install-simulate . --package-dir dist --install-root dist/install-simulation",
|
|
"python3 scripts/yao.py runtime-permissions . --package-dir dist",
|
|
"python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>",
|
|
"Copy evidence/world_class/templates/native-permission-enforcement.intake.json to evidence/world_class/submissions/native-permission-enforcement.json and fill only real evidence fields.",
|
|
"python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions"
|
|
],
|
|
"provenance_requirements": [
|
|
"real target client or external installer runtime guard",
|
|
"native enforcement flag or externally accepted guard proof",
|
|
"residual risk retained for fallback targets"
|
|
],
|
|
"success_checks": [
|
|
"reports/runtime_permission_probes.json summary.native_enforcement_count > 0",
|
|
"reports/runtime_permission_probes.json summary.failure_count == 0",
|
|
"reports/runtime_permission_probes.json summary.installer_enforcement_pass_count records local installer enforcement but does not replace native evidence",
|
|
"reports/skill_os2_audit.json item native-permission-enforcement status becomes pass"
|
|
],
|
|
"evidence_artifacts": [
|
|
"dist/targets/*/adapter.json",
|
|
"reports/runtime_permission_probes.json",
|
|
"reports/runtime_permission_probes.md",
|
|
"reports/install_simulation.json",
|
|
"reports/install_simulation.md",
|
|
"security/permission_policy.json",
|
|
"evidence/world_class/intake.schema.json",
|
|
"evidence/world_class/templates/native-permission-enforcement.intake.json",
|
|
"reports/world_class_evidence_intake.json",
|
|
"reports/world_class_evidence_intake.md"
|
|
],
|
|
"privacy_contract": [
|
|
"Do not mark native_enforcement true for metadata-only fallbacks.",
|
|
"Keep residual risks visible for targets that still rely on operator enforcement."
|
|
],
|
|
"observed_state": {
|
|
"native_enforcement_count": 0,
|
|
"metadata_fallback_count": 4,
|
|
"installer_enforcement_pass_count": 4,
|
|
"installer_permission_failure_count": 0,
|
|
"installer_enforcement_ready": true,
|
|
"residual_risk_count": 4,
|
|
"failure_count": 0,
|
|
"accepted": false
|
|
},
|
|
"source_checklist": [
|
|
{
|
|
"evidence_key": "native-permission-enforcement",
|
|
"label": "Native enforcement",
|
|
"field": "native_enforcement_count",
|
|
"expected": ">0",
|
|
"actual": 0,
|
|
"status": "blocked",
|
|
"source_accepted": false,
|
|
"next_action": "Collect real target-client or external runtime guard proof."
|
|
},
|
|
{
|
|
"evidence_key": "native-permission-enforcement",
|
|
"label": "Probe failures",
|
|
"field": "failure_count",
|
|
"expected": "==0",
|
|
"actual": 0,
|
|
"status": "pass",
|
|
"source_accepted": false,
|
|
"next_action": "Runtime permission probes must stay clean."
|
|
},
|
|
{
|
|
"evidence_key": "native-permission-enforcement",
|
|
"label": "Installer support",
|
|
"field": "installer_enforcement_ready",
|
|
"expected": "true",
|
|
"actual": true,
|
|
"status": "pass",
|
|
"source_accepted": false,
|
|
"next_action": "Installer enforcement is supporting evidence, not native proof."
|
|
}
|
|
],
|
|
"source_check_count": 3,
|
|
"source_pass_count": 2,
|
|
"source_blocked_count": 1,
|
|
"submission_state": {
|
|
"status": "missing",
|
|
"path": "evidence/world_class/submissions/native-permission-enforcement.json",
|
|
"artifact_ref_count": 0,
|
|
"attested_real_evidence": false,
|
|
"privacy_contract_satisfied": false,
|
|
"ledger_counts_as_completion": false
|
|
},
|
|
"anti_overclaim": {
|
|
"planned_work_counts_as_evidence": false,
|
|
"metadata_fallback_counts_as_native_enforcement": false,
|
|
"pending_review_counts_as_human_decision": false,
|
|
"local_command_runner_counts_as_provider_model": false
|
|
},
|
|
"next_action": "Integrate a real target-client or external installer runtime guard before claiming native permission enforcement."
|
|
},
|
|
{
|
|
"key": "native-client-telemetry",
|
|
"label": "Native Client Telemetry",
|
|
"category": "external",
|
|
"owner": "Browser/Chrome/IDE/provider client integrator",
|
|
"status": "pending",
|
|
"source_status": "external_required",
|
|
"source_accepted": false,
|
|
"current": "external source events 0; adoption samples 0",
|
|
"objective": "Import production metadata-only events from a real external client into the local drift loop.",
|
|
"runbook": [
|
|
"python3 scripts/telemetry_native_host.py . --write-launcher /tmp/yao-telemetry-host.sh --write-manifest /tmp/yao-telemetry-host.json --allowed-origin chrome-extension://<extension-id>/",
|
|
"Install the generated native messaging manifest for the real client and send at least one accepted skill_activation or skill_output event.",
|
|
"python3 scripts/yao.py telemetry-import . --input-jsonl .yao/telemetry_spool/external_events.jsonl",
|
|
"python3 scripts/yao.py skill-atlas --workspace-root .",
|
|
"python3 scripts/yao.py skill-os2-audit . --generated-at <YYYY-MM-DD>",
|
|
"Copy evidence/world_class/templates/native-client-telemetry.intake.json to evidence/world_class/submissions/native-client-telemetry.json and fill only real evidence fields.",
|
|
"python3 scripts/yao.py world-class-intake . --submissions-dir evidence/world_class/submissions"
|
|
],
|
|
"provenance_requirements": [
|
|
"real external client source",
|
|
"metadata-only event",
|
|
"local-first import path"
|
|
],
|
|
"success_checks": [
|
|
"reports/adoption_drift_report.json summary.source_types.external > 0",
|
|
"reports/adoption_drift_report.json summary.adoption_sample_count > 0",
|
|
"reports/skill_os2_audit.json item native-client-telemetry status becomes pass"
|
|
],
|
|
"evidence_artifacts": [
|
|
"reports/adoption_drift_report.json",
|
|
"reports/adoption_drift_report.md",
|
|
"reports/telemetry_hook_recipes.json",
|
|
"scripts/telemetry_native_host.py",
|
|
"evidence/world_class/intake.schema.json",
|
|
"evidence/world_class/templates/native-client-telemetry.intake.json",
|
|
"reports/world_class_evidence_intake.json",
|
|
"reports/world_class_evidence_intake.md"
|
|
],
|
|
"privacy_contract": [
|
|
"Telemetry must remain metadata-only and local-first.",
|
|
"Do not package reports/telemetry_events.jsonl or any raw prompt, output, transcript, note, or message field."
|
|
],
|
|
"observed_state": {
|
|
"external_source_events": 0,
|
|
"adoption_sample_count": 0,
|
|
"raw_content_allowed": false,
|
|
"risk_band": "low",
|
|
"accepted": false
|
|
},
|
|
"source_checklist": [
|
|
{
|
|
"evidence_key": "native-client-telemetry",
|
|
"label": "External events",
|
|
"field": "external_source_events",
|
|
"expected": ">0",
|
|
"actual": 0,
|
|
"status": "blocked",
|
|
"source_accepted": false,
|
|
"next_action": "Import at least one metadata-only event from a real client."
|
|
},
|
|
{
|
|
"evidence_key": "native-client-telemetry",
|
|
"label": "Adoption sample",
|
|
"field": "adoption_sample_count",
|
|
"expected": ">0",
|
|
"actual": 0,
|
|
"status": "blocked",
|
|
"source_accepted": false,
|
|
"next_action": "Telemetry must include adoption outcome evidence."
|
|
},
|
|
{
|
|
"evidence_key": "native-client-telemetry",
|
|
"label": "Raw content blocked",
|
|
"field": "raw_content_allowed",
|
|
"expected": "false",
|
|
"actual": false,
|
|
"status": "pass",
|
|
"source_accepted": false,
|
|
"next_action": "Telemetry must stay metadata-only."
|
|
}
|
|
],
|
|
"source_check_count": 3,
|
|
"source_pass_count": 1,
|
|
"source_blocked_count": 2,
|
|
"submission_state": {
|
|
"status": "missing",
|
|
"path": "evidence/world_class/submissions/native-client-telemetry.json",
|
|
"artifact_ref_count": 0,
|
|
"attested_real_evidence": false,
|
|
"privacy_contract_satisfied": false,
|
|
"ledger_counts_as_completion": false
|
|
},
|
|
"anti_overclaim": {
|
|
"planned_work_counts_as_evidence": false,
|
|
"metadata_fallback_counts_as_native_enforcement": false,
|
|
"pending_review_counts_as_human_decision": false,
|
|
"local_command_runner_counts_as_provider_model": false
|
|
},
|
|
"next_action": "Install a real client against the native host and import production metadata-only events."
|
|
}
|
|
],
|
|
"source_plan": {
|
|
"json": "reports/world_class_evidence_plan.json",
|
|
"markdown": "reports/world_class_evidence_plan.md",
|
|
"task_count": 4,
|
|
"evidence_requirement_count": 4
|
|
}
|
|
},
|
|
"synthesis_highlights": [
|
|
"Borrow progressive disclosure: keep the entrypoint lean and move depth into references or scripts.",
|
|
"Borrow a review checkpoint wherever trust matters more than raw speed.",
|
|
"Borrow the discipline of defining what the skill should not own before growing the package."
|
|
],
|
|
"artifact_design": {
|
|
"design_system": "metric editorial",
|
|
"highlights": [
|
|
"Execution-focused technical artifact with environment assumptions, copyable commands, expected outputs, and side effects made explicit.",
|
|
"Name the working directory and required inputs for commands.",
|
|
"Mark destructive, networked, or external side-effect operations.",
|
|
"Prefer the smallest runnable snippet over broad framework scaffolding."
|
|
]
|
|
},
|
|
"prompt_quality": {
|
|
"overall_quality_score": 89.0,
|
|
"highlights": [
|
|
"Primary prompt task family: Execution operation.",
|
|
"Complexity: expert — multiple task families plus governance, evaluation, or expert-level constraints",
|
|
"Completeness: 100/100.",
|
|
"Clarity: 85/100."
|
|
]
|
|
},
|
|
"system_model": {
|
|
"stability": {
|
|
"score": 100,
|
|
"band": "system-ready"
|
|
},
|
|
"highlights": [
|
|
"Stability: system-ready (100/100).",
|
|
"Owned job: Turn repeated workflows, prompts, transcripts, runbooks, documents, or existing skill packages into routeable, evaluable, packageable, and governable agent skills for personal, team, library, or governed reuse.",
|
|
"Leverage: Tune the frontmatter description — Name the recurring job, expected input, output, and strongest non-goal in compact language.",
|
|
"Leverage: Install output self-repair checks — Add only the checks that prevent recurring output mistakes."
|
|
]
|
|
},
|
|
"metadata": {
|
|
"canonical_format": "agent-skills",
|
|
"targets": [
|
|
"openai",
|
|
"claude",
|
|
"generic",
|
|
"vscode"
|
|
],
|
|
"maturity_tier": "governed",
|
|
"skill_archetype": "governed",
|
|
"updated_at": "2026-03-31"
|
|
},
|
|
"interpretation_contract": {
|
|
"schema_version": "2.0",
|
|
"source_model": "skill-overview-v2",
|
|
"source_model_reused": true,
|
|
"overview_report": "reports/skill-overview.html",
|
|
"html_report": "reports/skill-interpretation.html",
|
|
"json_report": "reports/skill-interpretation.json",
|
|
"default_language": "zh-CN",
|
|
"languages": [
|
|
"zh-CN",
|
|
"en"
|
|
],
|
|
"includes": [
|
|
"skill role",
|
|
"principles",
|
|
"usage scenarios",
|
|
"trigger contract",
|
|
"inputs and outputs",
|
|
"quality evidence",
|
|
"risk governance",
|
|
"package assets",
|
|
"highlights",
|
|
"upgrade roadmap"
|
|
]
|
|
}
|
|
} |