YAO
31ce04c655
Merge the beta-ready Yao Meta Skill architecture, report, evidence gate, and release-boundary updates.\n\nRelease boundary: beta/public testing is allowed; formal world-class, fully reviewed, or superiority claims remain blocked until the pending evidence gates are accepted.
386 lines
17 KiB
JSON
386 lines
17 KiB
JSON
{
|
|
"schema_version": "2.0.0",
|
|
"name": "yao-meta-skill",
|
|
"title": "Yao Meta Skill",
|
|
"job_to_be_done": "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.",
|
|
"trigger_surface": {
|
|
"description": "Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use for skill creation, reusable workflow packaging, skill improvement, evals, and team-ready distribution.",
|
|
"should_trigger": [
|
|
"Create a skill from this repeated workflow.",
|
|
"Turn this runbook into a reusable agent skill.",
|
|
"Convert this process note into a reusable skill package for the team.",
|
|
"Improve this skill description and add evals.",
|
|
"Refactor this prompt into a proper skill package.",
|
|
"Package this skill for team reuse.",
|
|
"Create a meta-skill for packaging internal workflows.",
|
|
"Standardize this recurring workflow as a shareable skill package with references."
|
|
],
|
|
"should_not_trigger": [
|
|
"Explain what a workflow is.",
|
|
"Just explain what a skill is.",
|
|
"Summarize this random note.",
|
|
"Translate this README into Japanese.",
|
|
"Write a product headline for this landing page.",
|
|
"Draft a blog title for this article.",
|
|
"Rewrite this paragraph more clearly, but do not package anything.",
|
|
"Explain the difference between a runbook and a workflow.",
|
|
"one-off writing, translation, explanation, or brainstorming requests that do not need a reusable skill",
|
|
"general code review or debugging unless the user is packaging that workflow as a skill"
|
|
],
|
|
"edge_cases": [
|
|
"Create a one-off prompt for this task.",
|
|
"Write a custom answer for this request without creating a skill package.",
|
|
"Help me brainstorm process ideas without building a skill.",
|
|
"Improve this README but do not turn it into a skill.",
|
|
"Make a checklist for this task, but not a reusable skill.",
|
|
"Create a reusable-looking checklist, but keep it as a plain note instead of a skill.",
|
|
"Review this process note and explain it, no packaging needed.",
|
|
"Turn this into a checklist and template, but stop short of making a full skill."
|
|
]
|
|
},
|
|
"workflow": {
|
|
"steps": [
|
|
"For one-off/no reusable process: `Do not create a skill`; `near-neighbor`; require `repeated use` + `reusable output contract`.",
|
|
"Capture job, output, exclusions, constraints, standards, and the lightest fit.",
|
|
"Scan references in order: external benchmark, user source, local fit; surface only uncertainty or conflict.",
|
|
"Write `description` early, test route quality, then add only earned folders and gates.",
|
|
"Add output-risk, artifact-design, prompt-quality, system-model, and next directions only when useful."
|
|
],
|
|
"decision_points": [
|
|
"Route by frontmatter `description`.",
|
|
"Keep `SKILL.md` lean; put guidance in `references/`, logic in `scripts/`, and evidence in `reports/`.",
|
|
"Use the lightest reliable process.",
|
|
"`Scaffold`: exploratory/personal. `Production`: team reuse. `Library`: shared infrastructure. `Governed`: high-trust, policy-sensitive, or release-critical.",
|
|
"Rules: [Method](references/skill-engineering-method.md), [Operating Modes](references/operating-modes.md), [Resource Boundaries](references/resource-boundaries.md).",
|
|
"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."
|
|
],
|
|
"failure_modes": [
|
|
"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.",
|
|
"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.",
|
|
"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.",
|
|
"Users start invoking the skill for adjacent one-off or explanation-only requests.",
|
|
"Outputs remain valid but become generic, cluttered, or weakly aligned with the user's domain.",
|
|
"Borrowed benchmark patterns no longer fit the local job or add ceremony without payoff.",
|
|
"Skill usage becomes team-critical while ownership, review cadence, or rollback evidence stays informal."
|
|
]
|
|
},
|
|
"resources": {
|
|
"references": [
|
|
"references/artifact-design-doctrine.md",
|
|
"references/authoring-discipline.md",
|
|
"references/autonomous-adaptation.md",
|
|
"references/distribution-registry-method.md",
|
|
"references/eval-playbook.md",
|
|
"references/gate-selection.md",
|
|
"references/governance.md",
|
|
"references/human-review-template.md",
|
|
"references/intent-dialogue.md",
|
|
"references/iteration-philosophy.md",
|
|
"references/non-skill-decision-tree.md",
|
|
"references/operating-modes.md",
|
|
"references/output-eval-method.md",
|
|
"references/output-quality-risk.md",
|
|
"references/output-visual-quality.md",
|
|
"references/packaging-contracts.md",
|
|
"references/pattern-extraction-doctrine.md",
|
|
"references/platform-capability-matrix.md",
|
|
"references/prompt-engineering-doctrine.md",
|
|
"references/qa-ladder.md",
|
|
"references/reference-scan.md",
|
|
"references/regression-cause-taxonomy.md",
|
|
"references/resource-boundaries.md",
|
|
"references/review-studio-method.md",
|
|
"references/review-waiver-method.md",
|
|
"references/runtime-conformance-method.md",
|
|
"references/skill-archetypes.md",
|
|
"references/skill-atlas-method.md",
|
|
"references/skill-engineering-method.md",
|
|
"references/skill-ir-method.md",
|
|
"references/skillops-decision-policy.md",
|
|
"references/systems-thinking-doctrine.md",
|
|
"references/telemetry-drift-method.md",
|
|
"references/trust-security-method.md",
|
|
"references/user-memory-policy.md"
|
|
],
|
|
"scripts": [
|
|
"scripts/adaptation_patch_safety.py",
|
|
"scripts/adaptation_report_contracts.py",
|
|
"scripts/adjudicate_output_review.py",
|
|
"scripts/apply_adaptation.py",
|
|
"scripts/benchmark_release_lock.py",
|
|
"scripts/build_confusion_matrix.py",
|
|
"scripts/build_skill_atlas.py",
|
|
"scripts/build_skill_atlas_layout.py",
|
|
"scripts/build_skill_atlas_opportunities.py",
|
|
"scripts/check_update.py",
|
|
"scripts/ci_test.py",
|
|
"scripts/collect_feedback.py",
|
|
"scripts/compile_skill.py",
|
|
"scripts/compile_skill_targets.py",
|
|
"scripts/context_sizer.py",
|
|
"scripts/create_iteration_snapshot.py",
|
|
"scripts/cross_packager.py",
|
|
"scripts/cross_packager_contracts.py",
|
|
"scripts/description_optimizer_reporting.py",
|
|
"scripts/diff_eval.py",
|
|
"scripts/emit_telemetry_event.py",
|
|
"scripts/evidence_consistency_artifact_roles.py",
|
|
"scripts/evidence_consistency_core.py",
|
|
"scripts/evidence_consistency_phase_queue.py",
|
|
"scripts/evidence_consistency_release.py",
|
|
"scripts/evidence_consistency_skill_os2_review.py",
|
|
"scripts/evidence_consistency_world_class.py",
|
|
"scripts/export_skill_ir.py",
|
|
"scripts/github_benchmark_scan.py",
|
|
"scripts/governance_check.py",
|
|
"scripts/html_rendering.py",
|
|
"scripts/import_output_review_decisions.py",
|
|
"scripts/import_telemetry_events.py",
|
|
"scripts/init_skill.py",
|
|
"scripts/judge_blind_eval.py",
|
|
"scripts/lint_skill.py",
|
|
"scripts/local_output_eval_runner.py",
|
|
"scripts/optimize_description.py",
|
|
"scripts/output_review_privacy.py",
|
|
"scripts/prepare_output_review_kit.py",
|
|
"scripts/prepare_world_class_submission_kit.py",
|
|
"scripts/probe_runtime_permissions.py",
|
|
"scripts/promotion_checker.py",
|
|
"scripts/propose_adaptation.py",
|
|
"scripts/provider_output_eval_runner.py",
|
|
"scripts/python_compat_check.py",
|
|
"scripts/reference_synthesis_markdown.py",
|
|
"scripts/registry_audit.py",
|
|
"scripts/render_adoption_drift_report.py",
|
|
"scripts/render_architecture_maintainability.py",
|
|
"scripts/render_artifact_design_profile.py",
|
|
"scripts/render_baseline_compare.py",
|
|
"scripts/render_benchmark_reproducibility.py",
|
|
"scripts/render_context_reports.py",
|
|
"scripts/render_daily_skillops_report.py",
|
|
"scripts/render_description_drift_history.py",
|
|
"scripts/render_eval_dashboard.py",
|
|
"scripts/render_evidence_consistency.py",
|
|
"scripts/render_intent_confidence.py",
|
|
"scripts/render_intent_dialogue.py",
|
|
"scripts/render_iteration_directions.py",
|
|
"scripts/render_iteration_ledger.py",
|
|
"scripts/render_output_risk_profile.py",
|
|
"scripts/render_portability_report.py",
|
|
"scripts/render_prompt_quality_profile.py",
|
|
"scripts/render_reference_scan.py",
|
|
"scripts/render_reference_synthesis.py",
|
|
"scripts/render_regression_history.py",
|
|
"scripts/render_review_annotations.py",
|
|
"scripts/render_review_studio.py",
|
|
"scripts/render_review_viewer.py",
|
|
"scripts/render_review_waivers.py",
|
|
"scripts/render_skill_interpretation.py",
|
|
"scripts/render_skill_os2_audit.py",
|
|
"scripts/render_skill_os2_coverage.py",
|
|
"scripts/render_skill_overview.py",
|
|
"scripts/render_social_preview.py",
|
|
"scripts/render_system_model.py",
|
|
"scripts/render_telemetry_hook_recipes.py",
|
|
"scripts/render_weekly_curator_report.py",
|
|
"scripts/render_world_class_claim_guard.py",
|
|
"scripts/render_world_class_evidence_intake.py",
|
|
"scripts/render_world_class_evidence_ledger.py",
|
|
"scripts/render_world_class_evidence_plan.py",
|
|
"scripts/render_world_class_operator_runbook.py",
|
|
"scripts/render_world_class_preflight.py",
|
|
"scripts/render_world_class_submission_review.py",
|
|
"scripts/resource_boundary_check.py",
|
|
"scripts/review_studio_action_evidence.py",
|
|
"scripts/review_studio_actions.py",
|
|
"scripts/review_studio_data.py",
|
|
"scripts/review_studio_formatting.py",
|
|
"scripts/review_studio_gate_contract.py",
|
|
"scripts/review_studio_gate_helpers.py",
|
|
"scripts/review_studio_gates.py",
|
|
"scripts/review_studio_layout.py",
|
|
"scripts/review_studio_output_review.py",
|
|
"scripts/review_studio_panels.py",
|
|
"scripts/review_studio_skillops.py",
|
|
"scripts/review_studio_waivers.py",
|
|
"scripts/review_studio_world_class.py",
|
|
"scripts/review_viewer_data.py",
|
|
"scripts/run_conformance_suite.py",
|
|
"scripts/run_description_optimization_suite.py",
|
|
"scripts/run_eval_suite.py",
|
|
"scripts/run_output_eval.py",
|
|
"scripts/run_output_execution.py",
|
|
"scripts/simulate_install.py",
|
|
"scripts/skill_ir_paths.py",
|
|
"scripts/skill_os2_coverage_markdown.py",
|
|
"scripts/skill_report_charts.py",
|
|
"scripts/skill_report_i18n.py",
|
|
"scripts/skill_report_layout.py",
|
|
"scripts/skill_report_metrics.py",
|
|
"scripts/skill_report_model.py",
|
|
"scripts/skill_report_sections.py",
|
|
"scripts/skill_report_sources.py",
|
|
"scripts/skill_report_world_class.py",
|
|
"scripts/skillops_opportunity.py",
|
|
"scripts/summarize_user_signals.py",
|
|
"scripts/sync_local_install.py",
|
|
"scripts/telemetry_native_host.py",
|
|
"scripts/trigger_eval.py",
|
|
"scripts/trust_check.py",
|
|
"scripts/trust_check_scripts.py",
|
|
"scripts/upgrade_check.py",
|
|
"scripts/validate_skill.py",
|
|
"scripts/verify_package.py",
|
|
"scripts/world_class_evidence_contract.py",
|
|
"scripts/world_class_human_evidence.py",
|
|
"scripts/world_class_native_permission_evidence.py",
|
|
"scripts/world_class_native_telemetry_evidence.py",
|
|
"scripts/world_class_operator_runbook_coordination.py",
|
|
"scripts/world_class_phase_queue.py",
|
|
"scripts/world_class_preflight_layout.py",
|
|
"scripts/world_class_preflight_markdown.py",
|
|
"scripts/world_class_provider_evidence.py",
|
|
"scripts/world_class_repair_checklist.py",
|
|
"scripts/world_class_source_checks.py",
|
|
"scripts/world_class_submission_kit_rendering.py",
|
|
"scripts/world_class_submission_matrix.py",
|
|
"scripts/yao.py",
|
|
"scripts/yao_cli_adaptation_commands.py",
|
|
"scripts/yao_cli_config.py",
|
|
"scripts/yao_cli_create_commands.py",
|
|
"scripts/yao_cli_distribution_commands.py",
|
|
"scripts/yao_cli_output_commands.py",
|
|
"scripts/yao_cli_parser.py",
|
|
"scripts/yao_cli_parser_evidence.py",
|
|
"scripts/yao_cli_parser_operations.py",
|
|
"scripts/yao_cli_report_commands.py",
|
|
"scripts/yao_cli_runtime.py",
|
|
"scripts/yao_cli_telemetry.py"
|
|
],
|
|
"assets": [
|
|
"assets/review-studio.css",
|
|
"assets/review-viewer.css",
|
|
"assets/skill-overview.css",
|
|
"assets/skill-overview.js",
|
|
"templates/basic_skill.md.j2",
|
|
"templates/complex_skill.md.j2"
|
|
],
|
|
"reports": [
|
|
"reports/benchmark_methodology.md",
|
|
"reports/intent-context.json",
|
|
"reports/intent-confidence.json",
|
|
"reports/intent-confidence.md",
|
|
"reports/reference-synthesis.json",
|
|
"reports/reference-synthesis.md",
|
|
"reports/output-risk-profile.json",
|
|
"reports/output-risk-profile.md",
|
|
"reports/artifact-design-profile.json",
|
|
"reports/artifact-design-profile.md",
|
|
"reports/prompt-quality-profile.json",
|
|
"reports/prompt-quality-profile.md",
|
|
"reports/system-model.json",
|
|
"reports/system-model.md",
|
|
"reports/iteration-directions.json",
|
|
"reports/iteration-directions.md",
|
|
"reports/skill-overview.json",
|
|
"reports/skill-overview.html",
|
|
"reports/output_quality_scorecard.json",
|
|
"reports/output_quality_scorecard.md",
|
|
"reports/output_execution_runs.json",
|
|
"reports/output_execution_runs.md",
|
|
"reports/output_blind_review_pack.json",
|
|
"reports/output_blind_review_pack.md",
|
|
"reports/output_blind_answer_key.json",
|
|
"reports/output_review_adjudication.json",
|
|
"reports/output_review_adjudication.md",
|
|
"reports/review_annotations.json",
|
|
"reports/review_annotations.md",
|
|
"reports/conformance_matrix.json",
|
|
"reports/conformance_matrix.md",
|
|
"reports/security_trust_report.json",
|
|
"reports/security_trust_report.md",
|
|
"reports/runtime_permission_probes.json",
|
|
"reports/runtime_permission_probes.md",
|
|
"reports/telemetry_hook_recipes.json",
|
|
"reports/telemetry_hook_recipes.md",
|
|
"reports/skill_atlas.json",
|
|
"reports/skill_atlas.html",
|
|
"reports/skill-os-2-review.md",
|
|
"reports/portability_score.json",
|
|
"reports/portability_score.md",
|
|
"reports/governance_score.json"
|
|
]
|
|
},
|
|
"eval_plan": {
|
|
"trigger": [
|
|
"evals/README.md",
|
|
"evals/adaptation/user_signals.example.jsonl",
|
|
"evals/adversarial/trigger_cases.json",
|
|
"evals/blind_holdout/trigger_cases.json",
|
|
"evals/confusion/route_cases.json",
|
|
"evals/dev/trigger_cases.json",
|
|
"evals/failure-cases.md",
|
|
"evals/history/2026-03-31-context-first-pack.json",
|
|
"evals/history/2026-03-31-family-suite-expansion.json",
|
|
"evals/history/2026-03-31-governance-quality-gates.json",
|
|
"evals/history/2026-03-31-governed-assets-and-history.json",
|
|
"evals/history/2026-04-01-route-scorecard-foundation.json",
|
|
"evals/history/README.md",
|
|
"evals/history/description_optimization/2026-03-31-description-optimization-suite.json",
|
|
"evals/history/description_optimization/2026-04-01-adversarial-calibration-and-family-drift.json",
|
|
"evals/history/description_optimization/2026-04-01-blind-holdout-and-drift-history.json",
|
|
"evals/history/description_optimization/2026-04-01-judge-backed-blind-eval.json",
|
|
"evals/history/description_optimization/README.md",
|
|
"evals/holdout/trigger_cases.json",
|
|
"evals/output/cases.jsonl",
|
|
"evals/output/fixtures/release-brief-source.md",
|
|
"evals/output/schema.json",
|
|
"evals/packaging_expectations.json",
|
|
"evals/promotion_policy.md",
|
|
"evals/semantic_config.json",
|
|
"evals/train/trigger_cases.json",
|
|
"evals/trigger_cases.json"
|
|
],
|
|
"output": [
|
|
"evals/output/cases.jsonl",
|
|
"evals/output/fixtures/release-brief-source.md",
|
|
"evals/output/schema.json"
|
|
],
|
|
"adversarial": [
|
|
"evals/adversarial/trigger_cases.json"
|
|
],
|
|
"baseline": "without_skill"
|
|
},
|
|
"risk": {
|
|
"output_risk": "high",
|
|
"execution_risk": "medium",
|
|
"trust_boundary": "external"
|
|
},
|
|
"governance": {
|
|
"owner": "Yao Team",
|
|
"maturity": "governed",
|
|
"review_cadence": "quarterly",
|
|
"review_due": ""
|
|
},
|
|
"targets": [
|
|
"openai",
|
|
"claude",
|
|
"generic",
|
|
"agent-skills-compatible",
|
|
"vscode"
|
|
],
|
|
"source_files": [
|
|
"SKILL.md",
|
|
"manifest.json",
|
|
"agents/interface.yaml",
|
|
"reports/intent-context.json",
|
|
"reports/output-risk-profile.json",
|
|
"reports/system-model.json"
|
|
]
|
|
}
|