yaojingang
1649 lines
64 KiB
JSON
1649 lines
64 KiB
JSON
{
|
|
"schema_version": "1.0",
|
|
"ok": true,
|
|
"generated_at": "2026-06-15",
|
|
"skill_dir": ".",
|
|
"summary": {
|
|
"check_count": 26,
|
|
"pass_count": 26,
|
|
"warn_count": 0,
|
|
"fail_count": 0,
|
|
"decision": "consistent"
|
|
},
|
|
"status_counts": {
|
|
"pass": 26,
|
|
"warn": 0,
|
|
"fail": 0
|
|
},
|
|
"checks": [
|
|
{
|
|
"key": "required-report-artifacts",
|
|
"label": "Required report artifacts are readable",
|
|
"status": "pass",
|
|
"expected": "all required JSON reports exist and parse",
|
|
"actual": "all readable",
|
|
"paths": [
|
|
"reports/benchmark_reproducibility.json",
|
|
"reports/skill-overview.json",
|
|
"reports/skill-interpretation.json",
|
|
"reports/adoption_drift_report.json",
|
|
"reports/world_class_evidence_ledger.json",
|
|
"reports/skill_os2_coverage.json",
|
|
"reports/review-studio.json"
|
|
],
|
|
"detail": "The consistency gate can only be trusted when every source report is present and valid JSON."
|
|
},
|
|
{
|
|
"key": "benchmark-release-lock-self-consistency",
|
|
"label": "Benchmark release lock matches git dirty state",
|
|
"status": "pass",
|
|
"expected": true,
|
|
"actual": true,
|
|
"paths": [
|
|
"reports/benchmark_reproducibility.json"
|
|
],
|
|
"detail": "The benchmark release lock must reflect the generation-time git dirty flag."
|
|
},
|
|
{
|
|
"key": "overview-benchmark-commit",
|
|
"label": "overview embeds the benchmark commit",
|
|
"status": "pass",
|
|
"expected": "27a5c120081fe8f2518de60c6a2278f41762e9b6",
|
|
"actual": "27a5c120081fe8f2518de60c6a2278f41762e9b6",
|
|
"paths": [
|
|
"reports/benchmark_reproducibility.json",
|
|
"reports/skill-overview.json"
|
|
],
|
|
"detail": "Human-facing reports must point to the same benchmark release-lock commit."
|
|
},
|
|
{
|
|
"key": "overview-benchmark-summary",
|
|
"label": "overview embeds benchmark summary fields",
|
|
"status": "pass",
|
|
"expected": {
|
|
"release_lock_ready": true,
|
|
"required_artifact_count": 24,
|
|
"missing_artifact_count": 0,
|
|
"source_contract_sha256": "4660a11db94947ab603dca42eddc447698785d08f0df2972bf2ca43454683306",
|
|
"archive_sha256": "6852cf91a74d232c32d732b7c159c971827abf23af50153987193b084ad3b5cc",
|
|
"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
|
|
},
|
|
"actual": {
|
|
"release_lock_ready": true,
|
|
"required_artifact_count": 24,
|
|
"missing_artifact_count": 0,
|
|
"source_contract_sha256": "4660a11db94947ab603dca42eddc447698785d08f0df2972bf2ca43454683306",
|
|
"archive_sha256": "6852cf91a74d232c32d732b7c159c971827abf23af50153987193b084ad3b5cc",
|
|
"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
|
|
},
|
|
"paths": [
|
|
"reports/benchmark_reproducibility.json",
|
|
"reports/skill-overview.json"
|
|
],
|
|
"detail": "Selected summary fields must match exactly across generated reports."
|
|
},
|
|
{
|
|
"key": "overview-adoption-summary",
|
|
"label": "overview embeds adoption drift summary fields",
|
|
"status": "pass",
|
|
"expected": {
|
|
"event_count": 1,
|
|
"adoption_sample_count": 0,
|
|
"activation_count": 0,
|
|
"accepted_count": 0,
|
|
"adoption_rate": 0,
|
|
"risk_band": "low",
|
|
"event_types": {
|
|
"review_event": 1
|
|
},
|
|
"source_types": {
|
|
"manual": 1
|
|
}
|
|
},
|
|
"actual": {
|
|
"event_count": 1,
|
|
"adoption_sample_count": 0,
|
|
"activation_count": 0,
|
|
"accepted_count": 0,
|
|
"adoption_rate": 0,
|
|
"risk_band": "low",
|
|
"event_types": {
|
|
"review_event": 1
|
|
},
|
|
"source_types": {
|
|
"manual": 1
|
|
}
|
|
},
|
|
"paths": [
|
|
"reports/adoption_drift_report.json",
|
|
"reports/skill-overview.json"
|
|
],
|
|
"detail": "Selected summary fields must match exactly across generated reports."
|
|
},
|
|
{
|
|
"key": "overview-world-class-ledger-summary",
|
|
"label": "overview embeds world-class ledger summary fields",
|
|
"status": "pass",
|
|
"expected": {
|
|
"ledger_entry_count": 4,
|
|
"accepted_count": 0,
|
|
"pending_count": 4,
|
|
"human_pending_count": 1,
|
|
"external_pending_count": 3,
|
|
"source_check_count": 13,
|
|
"source_pass_count": 6,
|
|
"source_blocked_count": 7,
|
|
"ready_to_claim_world_class": false,
|
|
"decision": "evidence-pending"
|
|
},
|
|
"actual": {
|
|
"ledger_entry_count": 4,
|
|
"accepted_count": 0,
|
|
"pending_count": 4,
|
|
"human_pending_count": 1,
|
|
"external_pending_count": 3,
|
|
"source_check_count": 13,
|
|
"source_pass_count": 6,
|
|
"source_blocked_count": 7,
|
|
"ready_to_claim_world_class": false,
|
|
"decision": "evidence-pending"
|
|
},
|
|
"paths": [
|
|
"reports/world_class_evidence_ledger.json",
|
|
"reports/skill-overview.json"
|
|
],
|
|
"detail": "Selected summary fields must match exactly across generated reports."
|
|
},
|
|
{
|
|
"key": "overview-world-class-readiness",
|
|
"label": "overview derives readiness from the ledger",
|
|
"status": "pass",
|
|
"expected": {
|
|
"ready": false,
|
|
"decision": "evidence-pending",
|
|
"pending_count": 4,
|
|
"accepted_count": 0,
|
|
"source_check_count": 13,
|
|
"source_pass_count": 6
|
|
},
|
|
"actual": {
|
|
"ready": false,
|
|
"decision": "evidence-pending",
|
|
"pending_count": 4,
|
|
"accepted_count": 0,
|
|
"source_check_count": 13,
|
|
"source_pass_count": 6
|
|
},
|
|
"paths": [
|
|
"reports/world_class_evidence_ledger.json",
|
|
"reports/skill-overview.json"
|
|
],
|
|
"detail": "Readiness summaries must be derived from the evidence ledger, not hand-maintained copy."
|
|
},
|
|
{
|
|
"key": "interpretation-benchmark-commit",
|
|
"label": "interpretation embeds the benchmark commit",
|
|
"status": "pass",
|
|
"expected": "27a5c120081fe8f2518de60c6a2278f41762e9b6",
|
|
"actual": "27a5c120081fe8f2518de60c6a2278f41762e9b6",
|
|
"paths": [
|
|
"reports/benchmark_reproducibility.json",
|
|
"reports/skill-interpretation.json"
|
|
],
|
|
"detail": "Human-facing reports must point to the same benchmark release-lock commit."
|
|
},
|
|
{
|
|
"key": "interpretation-benchmark-summary",
|
|
"label": "interpretation embeds benchmark summary fields",
|
|
"status": "pass",
|
|
"expected": {
|
|
"release_lock_ready": true,
|
|
"required_artifact_count": 24,
|
|
"missing_artifact_count": 0,
|
|
"source_contract_sha256": "4660a11db94947ab603dca42eddc447698785d08f0df2972bf2ca43454683306",
|
|
"archive_sha256": "6852cf91a74d232c32d732b7c159c971827abf23af50153987193b084ad3b5cc",
|
|
"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
|
|
},
|
|
"actual": {
|
|
"release_lock_ready": true,
|
|
"required_artifact_count": 24,
|
|
"missing_artifact_count": 0,
|
|
"source_contract_sha256": "4660a11db94947ab603dca42eddc447698785d08f0df2972bf2ca43454683306",
|
|
"archive_sha256": "6852cf91a74d232c32d732b7c159c971827abf23af50153987193b084ad3b5cc",
|
|
"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
|
|
},
|
|
"paths": [
|
|
"reports/benchmark_reproducibility.json",
|
|
"reports/skill-interpretation.json"
|
|
],
|
|
"detail": "Selected summary fields must match exactly across generated reports."
|
|
},
|
|
{
|
|
"key": "interpretation-adoption-summary",
|
|
"label": "interpretation embeds adoption drift summary fields",
|
|
"status": "pass",
|
|
"expected": {
|
|
"event_count": 1,
|
|
"adoption_sample_count": 0,
|
|
"activation_count": 0,
|
|
"accepted_count": 0,
|
|
"adoption_rate": 0,
|
|
"risk_band": "low",
|
|
"event_types": {
|
|
"review_event": 1
|
|
},
|
|
"source_types": {
|
|
"manual": 1
|
|
}
|
|
},
|
|
"actual": {
|
|
"event_count": 1,
|
|
"adoption_sample_count": 0,
|
|
"activation_count": 0,
|
|
"accepted_count": 0,
|
|
"adoption_rate": 0,
|
|
"risk_band": "low",
|
|
"event_types": {
|
|
"review_event": 1
|
|
},
|
|
"source_types": {
|
|
"manual": 1
|
|
}
|
|
},
|
|
"paths": [
|
|
"reports/adoption_drift_report.json",
|
|
"reports/skill-interpretation.json"
|
|
],
|
|
"detail": "Selected summary fields must match exactly across generated reports."
|
|
},
|
|
{
|
|
"key": "interpretation-world-class-ledger-summary",
|
|
"label": "interpretation embeds world-class ledger summary fields",
|
|
"status": "pass",
|
|
"expected": {
|
|
"ledger_entry_count": 4,
|
|
"accepted_count": 0,
|
|
"pending_count": 4,
|
|
"human_pending_count": 1,
|
|
"external_pending_count": 3,
|
|
"source_check_count": 13,
|
|
"source_pass_count": 6,
|
|
"source_blocked_count": 7,
|
|
"ready_to_claim_world_class": false,
|
|
"decision": "evidence-pending"
|
|
},
|
|
"actual": {
|
|
"ledger_entry_count": 4,
|
|
"accepted_count": 0,
|
|
"pending_count": 4,
|
|
"human_pending_count": 1,
|
|
"external_pending_count": 3,
|
|
"source_check_count": 13,
|
|
"source_pass_count": 6,
|
|
"source_blocked_count": 7,
|
|
"ready_to_claim_world_class": false,
|
|
"decision": "evidence-pending"
|
|
},
|
|
"paths": [
|
|
"reports/world_class_evidence_ledger.json",
|
|
"reports/skill-interpretation.json"
|
|
],
|
|
"detail": "Selected summary fields must match exactly across generated reports."
|
|
},
|
|
{
|
|
"key": "interpretation-world-class-readiness",
|
|
"label": "interpretation derives readiness from the ledger",
|
|
"status": "pass",
|
|
"expected": {
|
|
"ready": false,
|
|
"decision": "evidence-pending",
|
|
"pending_count": 4,
|
|
"accepted_count": 0,
|
|
"source_check_count": 13,
|
|
"source_pass_count": 6
|
|
},
|
|
"actual": {
|
|
"ready": false,
|
|
"decision": "evidence-pending",
|
|
"pending_count": 4,
|
|
"accepted_count": 0,
|
|
"source_check_count": 13,
|
|
"source_pass_count": 6
|
|
},
|
|
"paths": [
|
|
"reports/world_class_evidence_ledger.json",
|
|
"reports/skill-interpretation.json"
|
|
],
|
|
"detail": "Readiness summaries must be derived from the evidence ledger, not hand-maintained copy."
|
|
},
|
|
{
|
|
"key": "overview-interpretation-lockstep-scorecard",
|
|
"label": "Overview and interpretation share scorecard",
|
|
"status": "pass",
|
|
"expected": {
|
|
"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。"
|
|
]
|
|
}
|
|
},
|
|
"actual": {
|
|
"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。"
|
|
]
|
|
}
|
|
},
|
|
"paths": [
|
|
"reports/skill-overview.json",
|
|
"reports/skill-interpretation.json"
|
|
],
|
|
"detail": "The first-class interpretation report must stay in lockstep with the canonical overview model."
|
|
},
|
|
{
|
|
"key": "overview-interpretation-lockstep-capability-profile",
|
|
"label": "Overview and interpretation share capability_profile",
|
|
"status": "pass",
|
|
"expected": {
|
|
"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
|
|
}
|
|
},
|
|
"actual": {
|
|
"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
|
|
}
|
|
},
|
|
"paths": [
|
|
"reports/skill-overview.json",
|
|
"reports/skill-interpretation.json"
|
|
],
|
|
"detail": "The first-class interpretation report must stay in lockstep with the canonical overview model."
|
|
},
|
|
{
|
|
"key": "overview-interpretation-lockstep-principle-model",
|
|
"label": "Overview and interpretation share principle_model",
|
|
"status": "pass",
|
|
"expected": {
|
|
"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"
|
|
]
|
|
},
|
|
"actual": {
|
|
"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"
|
|
]
|
|
},
|
|
"paths": [
|
|
"reports/skill-overview.json",
|
|
"reports/skill-interpretation.json"
|
|
],
|
|
"detail": "The first-class interpretation report must stay in lockstep with the canonical overview model."
|
|
},
|
|
{
|
|
"key": "overview-interpretation-lockstep-contract-boundary",
|
|
"label": "Overview and interpretation share contract_boundary",
|
|
"status": "pass",
|
|
"expected": {
|
|
"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。"
|
|
}
|
|
]
|
|
},
|
|
"actual": {
|
|
"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。"
|
|
}
|
|
]
|
|
},
|
|
"paths": [
|
|
"reports/skill-overview.json",
|
|
"reports/skill-interpretation.json"
|
|
],
|
|
"detail": "The first-class interpretation report must stay in lockstep with the canonical overview model."
|
|
},
|
|
{
|
|
"key": "overview-interpretation-lockstep-quality-review",
|
|
"label": "Overview and interpretation share quality_review",
|
|
"status": "pass",
|
|
"expected": {
|
|
"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."
|
|
]
|
|
}
|
|
},
|
|
"actual": {
|
|
"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."
|
|
]
|
|
}
|
|
},
|
|
"paths": [
|
|
"reports/skill-overview.json",
|
|
"reports/skill-interpretation.json"
|
|
],
|
|
"detail": "The first-class interpretation report must stay in lockstep with the canonical overview model."
|
|
},
|
|
{
|
|
"key": "overview-interpretation-lockstep-risk-governance",
|
|
"label": "Overview and interpretation share risk_governance",
|
|
"status": "pass",
|
|
"expected": {
|
|
"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."
|
|
]
|
|
},
|
|
"actual": {
|
|
"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."
|
|
]
|
|
},
|
|
"paths": [
|
|
"reports/skill-overview.json",
|
|
"reports/skill-interpretation.json"
|
|
],
|
|
"detail": "The first-class interpretation report must stay in lockstep with the canonical overview model."
|
|
},
|
|
{
|
|
"key": "overview-interpretation-lockstep-world-class-readiness",
|
|
"label": "Overview and interpretation share world_class_readiness",
|
|
"status": "pass",
|
|
"expected": {
|
|
"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"
|
|
]
|
|
}
|
|
]
|
|
},
|
|
"actual": {
|
|
"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"
|
|
]
|
|
}
|
|
]
|
|
},
|
|
"paths": [
|
|
"reports/skill-overview.json",
|
|
"reports/skill-interpretation.json"
|
|
],
|
|
"detail": "The first-class interpretation report must stay in lockstep with the canonical overview model."
|
|
},
|
|
{
|
|
"key": "overview-interpretation-lockstep-package-assets",
|
|
"label": "Overview and interpretation share package_assets",
|
|
"status": "pass",
|
|
"expected": {
|
|
"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
|
|
}
|
|
]
|
|
},
|
|
"actual": {
|
|
"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
|
|
}
|
|
]
|
|
},
|
|
"paths": [
|
|
"reports/skill-overview.json",
|
|
"reports/skill-interpretation.json"
|
|
],
|
|
"detail": "The first-class interpretation report must stay in lockstep with the canonical overview model."
|
|
},
|
|
{
|
|
"key": "overview-interpretation-lockstep-iteration-roadmap",
|
|
"label": "Overview and interpretation share iteration_roadmap",
|
|
"status": "pass",
|
|
"expected": {
|
|
"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."
|
|
}
|
|
]
|
|
},
|
|
"actual": {
|
|
"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."
|
|
}
|
|
]
|
|
},
|
|
"paths": [
|
|
"reports/skill-overview.json",
|
|
"reports/skill-interpretation.json"
|
|
],
|
|
"detail": "The first-class interpretation report must stay in lockstep with the canonical overview model."
|
|
},
|
|
{
|
|
"key": "overview-html-contract",
|
|
"label": "overview has a stable HTML contract",
|
|
"status": "pass",
|
|
"expected": {
|
|
"schema_version": "2.0",
|
|
"default_language": "zh-CN",
|
|
"layout": "kami-white-audit-v2",
|
|
"html_report": "reports/skill-overview.html",
|
|
"html_exists": true
|
|
},
|
|
"actual": {
|
|
"schema_version": "2.0",
|
|
"default_language": "zh-CN",
|
|
"layout": "kami-white-audit-v2",
|
|
"html_report": "reports/skill-overview.html",
|
|
"html_exists": true
|
|
},
|
|
"paths": [
|
|
"reports/skill-overview.json",
|
|
"reports/skill-overview.html"
|
|
],
|
|
"detail": "Report output paths and language defaults are part of the user-facing contract."
|
|
},
|
|
{
|
|
"key": "interpretation-html-contract",
|
|
"label": "interpretation has a stable HTML contract",
|
|
"status": "pass",
|
|
"expected": {
|
|
"schema_version": "2.0",
|
|
"default_language": "zh-CN",
|
|
"layout": "kami-white-audit-v2",
|
|
"html_report": "reports/skill-interpretation.html",
|
|
"html_exists": true
|
|
},
|
|
"actual": {
|
|
"schema_version": "2.0",
|
|
"default_language": "zh-CN",
|
|
"layout": "kami-white-audit-v2",
|
|
"html_report": "reports/skill-interpretation.html",
|
|
"html_exists": true
|
|
},
|
|
"paths": [
|
|
"reports/skill-interpretation.json",
|
|
"reports/skill-interpretation.html"
|
|
],
|
|
"detail": "Report output paths and language defaults are part of the user-facing contract."
|
|
},
|
|
{
|
|
"key": "coverage-world-class-boundary",
|
|
"label": "Coverage report mirrors world-class evidence boundary",
|
|
"status": "pass",
|
|
"expected": {
|
|
"world_class_evidence_pending_count": 4,
|
|
"public_world_class_ready": false
|
|
},
|
|
"actual": {
|
|
"world_class_evidence_pending_count": 4,
|
|
"public_world_class_ready": false
|
|
},
|
|
"paths": [
|
|
"reports/world_class_evidence_ledger.json",
|
|
"reports/skill_os2_coverage.json"
|
|
],
|
|
"detail": "Blueprint coverage can be locally complete while public world-class evidence remains pending."
|
|
},
|
|
{
|
|
"key": "benchmark-world-class-boundary",
|
|
"label": "Benchmark report mirrors world-class evidence boundary",
|
|
"status": "pass",
|
|
"expected": {
|
|
"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
|
|
},
|
|
"actual": {
|
|
"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
|
|
},
|
|
"paths": [
|
|
"reports/world_class_evidence_ledger.json",
|
|
"reports/benchmark_reproducibility.json"
|
|
],
|
|
"detail": "Benchmark reproducibility must not overstate public claim readiness."
|
|
},
|
|
{
|
|
"key": "review-studio-no-overclaim",
|
|
"label": "Review Studio does not overclaim pending world-class evidence",
|
|
"status": "pass",
|
|
"expected": false,
|
|
"actual": false,
|
|
"paths": [
|
|
"reports/world_class_evidence_ledger.json",
|
|
"reports/review-studio.json"
|
|
],
|
|
"detail": "When world-class evidence is pending, Review Studio must stay in a review or warning posture."
|
|
}
|
|
],
|
|
"artifacts": {
|
|
"json": "reports/evidence_consistency.json",
|
|
"markdown": "reports/evidence_consistency.md"
|
|
}
|
|
}
|