yao-meta-skill

Category: Tools & Productivity | Uploader: yaojingang | Downloads: 0 | Version: v1.0（Latest）

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.

Changelog: Source: GitHub https://github.com/yaojingang/yao-meta-skill

Directory Structure

Current level: tree/main/

📁 .github/
- 📁 workflows/
  - 📄 test.yml 291 B
📁 agents/
- 📄 interface.yaml 707 B
📁 docs/
- 📄 README.fr-FR.md 9.9 KB
- 📄 README.ja-JP.md 9.8 KB
- 📄 README.ru-RU.md 12.8 KB
- 📄 README.zh-CN.md 7.9 KB
📁 evals/
- 📁 adversarial/
  - 📄 trigger_cases.json 1.2 KB
- 📁 blind_holdout/
  - 📄 trigger_cases.json 1.2 KB
- 📁 confusion/
  - 📄 route_cases.json 3.2 KB
- 📁 dev/
  - 📄 trigger_cases.json 3.8 KB
- 📁 history/
  - 📁 description_optimization/
    
    📄 2026-03-31-description-optimization-suite.json 1.4 KB
    
    📄 2026-04-01-adversarial-calibration-and-family-drift.json 11.8 KB
    
    📄 2026-04-01-blind-holdout-and-drift-history.json 3.0 KB
    
    📄 2026-04-01-judge-backed-blind-eval.json 14.8 KB
    
    📄 README.md 660 B
  - 📄 2026-03-31-context-first-pack.json 686 B
  - 📄 2026-03-31-family-suite-expansion.json 635 B
  - 📄 2026-03-31-governance-quality-gates.json 654 B
  - 📄 2026-03-31-governed-assets-and-history.json 699 B
  - 📄 2026-04-01-route-scorecard-foundation.json 769 B
  - 📄 README.md 440 B
- 📁 holdout/
  - 📄 trigger_cases.json 2.4 KB
- 📁 train/
  - 📄 trigger_cases.json 4.5 KB
- 📄 baseline_description.txt 33 B
- 📄 failure-cases.md 889 B
- 📄 improved_description.txt 261 B
- 📄 packaging_expectations.json 661 B
- 📄 promotion_policy.md 2.1 KB
- 📄 README.md 3.7 KB
- 📄 semantic_config.json 6.3 KB
- 📄 trigger_cases.json 10.2 KB
📁 examples/
- 📁 complex-release-orchestrator/
  - 📁 generated-skill/
    
    📁 agents/
    
    📄 interface.yaml 291 B
    
    📁 evals/
    
    📄 trigger_cases.json 632 B
    
    📁 input/
    
    📄 release_input_example.json 1.2 KB
    
    📁 outputs/
    
    📄 release_packet_example.md 1.0 KB
    
    📁 references/
    
    📄 migration-template.md 372 B
    
    📄 release-checklist.md 705 B
    
    📄 risk-matrix.md 619 B
    
    📄 stakeholder-comms.md 526 B
    
    📁 reports/
    
    📄 context_budget.json 416 B
    
    📁 scripts/
    
    📄 build_release_packet.py 1.4 KB
    
    📄 manifest.json 453 B
    
    📄 SKILL.md 2.8 KB
  - 📄 design-summary.md 757 B
  - 📄 raw-workflow.md 919 B
- 📁 evolution-frontend-review/
  - 📁 final/
    
    📄 SKILL.md 966 B
  - 📁 v0/
    
    📄 SKILL.md 149 B
  - 📁 v1/
    
    📄 SKILL.md 518 B
  - 📄 eval-delta.md 319 B
  - 📄 raw-workflow.md 220 B
  - 📄 README.md 291 B
- 📁 governed-incident-command/
  - 📁 generated-skill/
    
    📁 agents/
    
    📄 interface.yaml 411 B
    
    📁 evals/
    
    📄 trigger_cases.json 522 B
    
    📁 input/
    
    📄 incident_input_example.json 613 B
    
    📁 outputs/
    
    📄 incident_packet_example.md 815 B
    
    📁 references/
    
    📄 comms-policy.md 336 B
    
    📄 review-policy.md 397 B
    
    📄 severity-matrix.md 332 B
    
    📁 reports/
    
    📄 context_budget.json 416 B
    
    📄 governance_score.json 772 B
    
    📄 revision_history.md 163 B
    
    📁 scripts/
    
    📄 build_incident_packet.py 1.1 KB
    
    📄 manifest.json 539 B
    
    📄 SKILL.md 2.6 KB
  - 📁 optimization/
    
    📁 adversarial/
    
    📄 trigger_cases.json 1.2 KB
    
    📁 blind_holdout/
    
    📄 trigger_cases.json 1.0 KB
    
    📁 dev/
    
    📄 trigger_cases.json 1.2 KB
    
    📁 holdout/
    
    📄 trigger_cases.json 927 B
    
    📁 reports/
    
    📄 description_optimization.json 186.3 KB
    
    📄 description_optimization.md 2.1 KB
    
    📄 baseline_description.txt 376 B
    
    📄 semantic_config.json 3.1 KB
  - 📄 design-summary.md 917 B
  - 📄 raw-workflow.md 794 B
- 📁 simple-note-cleanup/
  - 📁 generated-skill/
    
    📁 agents/
    
    📄 interface.yaml 223 B
    
    📄 SKILL.md 488 B
  - 📄 design-summary.md 268 B
  - 📄 raw-workflow.md 336 B
- 📁 team-frontend-review/
  - 📁 generated-skill/
    
    📁 agents/
    
    📄 interface.yaml 203 B
    
    📁 references/
    
    📄 checklist.md 361 B
    
    📄 SKILL.md 1.0 KB
  - 📁 optimization/
    
    📁 adversarial/
    
    📄 trigger_cases.json 1.2 KB
    
    📁 blind_holdout/
    
    📄 trigger_cases.json 941 B
    
    📁 dev/
    
    📄 trigger_cases.json 1.5 KB
    
    📁 holdout/
    
    📄 trigger_cases.json 934 B
    
    📁 reports/
    
    📄 description_optimization.json 204.5 KB
    
    📄 description_optimization.md 2.2 KB
    
    📄 baseline_description.txt 210 B
    
    📄 semantic_config.json 3.2 KB
  - 📄 design-summary.md 350 B
  - 📄 raw-workflow.md 356 B
- 📄 README.md 1.6 KB
📁 failures/
- 📁 document-export-vs-agent-skill/
  - 📄 cases.json 664 B
  - 📄 README.md 721 B
- 📁 explain-not-package/
  - 📄 cases.json 595 B
  - 📄 README.md 718 B
- 📁 future-outline-vs-build/
  - 📄 cases.json 552 B
  - 📄 README.md 805 B
- 📁 one-off-vs-reusable/
  - 📄 cases.json 497 B
  - 📄 README.md 713 B
- 📄 README.md 493 B
📁 references/
- 📄 eval-playbook.md 1.3 KB
- 📄 gate-selection.md 1.7 KB
- 📄 governance.md 3.0 KB
- 📄 human-review-template.md 989 B
- 📄 non-skill-decision-tree.md 955 B
- 📄 operating-modes.md 2.0 KB
- 📄 packaging-contracts.md 1.0 KB
- 📄 platform-capability-matrix.md 1.4 KB
- 📄 qa-ladder.md 1.3 KB
- 📄 reference-scan.md 2.9 KB
- 📄 regression-cause-taxonomy.md 2.6 KB
- 📄 resource-boundaries.md 3.4 KB
- 📄 skill-archetypes.md 1.5 KB
- 📄 skill-engineering-method.md 3.5 KB
📁 reports/
- 📁 iteration_bundles/
  - 📁 governed-incident-command/
    
    📄 bundle.json 5.2 KB
    
    📄 bundle.md 2.2 KB
    
    📄 review.md 600 B
  - 📁 team-frontend-review/
    
    📄 bundle.json 5.2 KB
    
    📄 bundle.md 2.2 KB
    
    📄 review.md 670 B
  - 📁 yao-meta-skill/
    
    📄 bundle.json 5.4 KB
    
    📄 bundle.md 2.2 KB
    
    📄 review.md 762 B
- 📄 candidate_registry.json 29.0 KB
- 📄 candidate_registry.md 2.3 KB
- 📄 context_budget.json 421 B
- 📄 context_budget.md 600 B
- 📄 context_budget_summary.json 1.0 KB
- 📄 description_drift_history.md 4.9 KB
- 📄 description_optimization.json 321.1 KB
- 📄 description_optimization.md 2.3 KB
- 📄 description_optimization_suite.json 14.3 KB
- 📄 description_optimization_suite.md 1.1 KB
- 📄 eval_suite.json 126.3 KB
- 📄 family_summary.md 1.3 KB
- 📄 governance_score.json 701 B
- 📄 iteration_ledger.md 4.8 KB
- 📄 portability_score.json 641 B
- 📄 portability_score.md 554 B
- 📄 promotion_decisions.json 29.1 KB
- 📄 promotion_decisions.md 875 B
- 📄 regression_history.md 1.1 KB
- 📄 route_scorecard.json 16.6 KB
- 📄 route_scorecard.md 875 B
📁 scripts/
- 📄 build_confusion_matrix.py 10.2 KB
- 📄 context_sizer.py 4.1 KB
- 📄 create_iteration_snapshot.py 7.9 KB
- 📄 cross_packager.py 14.2 KB
- 📄 diff_eval.py 970 B
- 📄 governance_check.py 7.6 KB
- 📄 init_skill.py 4.2 KB
- 📄 judge_blind_eval.py 9.6 KB
- 📄 lint_skill.py 1.5 KB
- 📄 optimize_description.py 31.7 KB
- 📄 promotion_checker.py 18.1 KB
- 📄 render_context_reports.py 3.0 KB
- 📄 render_description_drift_history.py 4.7 KB
- 📄 render_eval_dashboard.py 4.5 KB
- 📄 render_iteration_ledger.py 5.2 KB
- 📄 render_portability_report.py 4.7 KB
- 📄 render_reference_scan.py 9.4 KB
- 📄 render_regression_history.py 1.9 KB
- 📄 render_skill_overview.py 15.0 KB
- 📄 resource_boundary_check.py 6.9 KB
- 📄 run_description_optimization_suite.py 18.4 KB
- 📄 run_eval_suite.py 3.6 KB
- 📄 trigger_eval.py 11.6 KB
- 📄 validate_skill.py 4.0 KB
- 📄 yao.py 19.8 KB
📁 templates/
- 📄 basic_skill.md.j2 544 B
- 📄 complex_skill.md.j2 1.0 KB
📁 tests/
- 📁 fixtures/
  - 📁 governance_invalid_manifest/
    
    📄 manifest.json 164 B
    
    📄 SKILL.md 177 B
  - 📁 package_invalid_yaml/
    
    📁 agents/
    
    📄 interface.yaml 219 B
    
    📄 SKILL.md 116 B
  - 📁 package_missing_interface_field/
    
    📁 agents/
    
    📄 interface.yaml 451 B
    
    📄 SKILL.md 101 B
- 📁 snapshots/
  - 📄 claude_adapter.json 350 B
  - 📄 generic_adapter.json 355 B
  - 📄 openai_adapter.json 359 B
- 📄 verify_adapter_snapshots.py 2.6 KB
- 📄 verify_description_optimization.py 7.6 KB
- 📄 verify_failure_regressions.py 1.8 KB
- 📄 verify_packager_failures.py 2.6 KB
- 📄 verify_portability_report.py 1.2 KB
- 📄 verify_promotion_checker.py 2.0 KB
- 📄 verify_quality_checks.py 4.2 KB
- 📄 verify_reference_scan.py 2.3 KB
- 📄 verify_route_confusion.py 890 B
- 📄 verify_skill_overview.py 1.9 KB
- 📄 verify_yao_cli.py 4.0 KB
📄 .gitignore 185 B
📄 LICENSE 1.0 KB
📄 Makefile 3.2 KB
📄 manifest.json 460 B
📄 README.md 23.3 KB
📄 SKILL.md 3.0 KB

SKILL.md

---
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.
metadata:
  author: Yao Team
  philosophy: "structured design, evaluation loop, template ergonomics, operational packaging"
---

# Yao Meta Skill

Build reusable skill packages, not long prompts.

## Router Rules

- Route by frontmatter `description` first.
- Keep `SKILL.md` to routing plus the minimal execution skeleton.
- Push long guidance to `references/`, deterministic logic to `scripts/`, and evidence to `reports/`.
- Use the lightest process that still makes the skill reliable.

## Modes

- `Scaffold`: exploratory or personal.
- `Production`: team reuse with focused gates.
- `Library`: shared infrastructure or meta skill.

Mode rules: [Operating Modes](references/operating-modes.md), [QA Ladder](references/qa-ladder.md), [Resource Boundary Spec](references/resource-boundaries.md), [Skill Engineering Method](references/skill-engineering-method.md).

## Compact Workflow

1. Decide whether the request should become a skill, then choose the lightest archetype.
2. Run a short reference scan with external benchmark objects first, then use local files only for fit, privacy, and compatibility calibration.
3. Capture the recurring job, outputs, trigger phrases, and exclusions.
4. Write the `description` early, then test route quality before expanding the package.
5. Add only the folders and gates that earn their keep: `trigger_eval.py`, `optimize_description.py`, `judge_blind_eval.py`, `resource_boundary_check.py`, `governance_check.py`, `cross_packager.py`.

Playbooks: [Skill Engineering Method](references/skill-engineering-method.md), [Reference Scan Strategy](references/reference-scan.md), [Skill Archetypes](references/skill-archetypes.md), [Gate Selection](references/gate-selection.md), [Non-Skill Decision Tree](references/non-skill-decision-tree.md), [Operating Modes](references/operating-modes.md), [Trigger And Eval Playbook](references/eval-playbook.md).

## Output Contract

Unless the user asks otherwise, produce:

1. a working skill directory
2. a trigger-aware `SKILL.md`
3. aligned `agents/interface.yaml`
4. optional `references/`, `scripts/`, `evals/`, `reports/`, and `manifest.json` only when justified
5. a short summary of boundary, exclusions, benchmark objects, gates, and next steps

## Reference Map

- [Skill Engineering Method](references/skill-engineering-method.md)
- [Reference Scan Strategy](references/reference-scan.md)
- [Skill Archetypes](references/skill-archetypes.md)
- [Gate Selection](references/gate-selection.md)
- [Non-Skill Decision Tree](references/non-skill-decision-tree.md)
- [Operating Modes](references/operating-modes.md)
- [Governance Model](references/governance.md)
- [Resource Boundary Spec](references/resource-boundaries.md)
- [Trigger And Eval Playbook](references/eval-playbook.md)

Comments 0

Latest | Hot

Please login before commenting.

Loading comments...

yao-meta-skill

Directory Structure

SKILL.md

Report

Notice