メニュー
Create a small verified artifact from a user workflow. Use when the user asks to capture a workflow as a reusable skill with evidence, tool checks, failure modes, retry limits, and final review.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
Create, improve, evaluate, harden, and package production-grade Codex/Claude skills and skill groups. Use when the user wants to turn a workflow into a reusable skill, upgrade an existing skill, create multiple coordinated skills, design orchestrator-worker systems, run skill evals or benchmarks, verify tool/MCP dependencies, harden dependency install policy, optimize a skill description for triggering, or produce an evidence-backed delivery report. Also use for lightweight "vibe" skill drafting when the user explicitly wants less process.
Demonstrate false positive lint behavior for failure retry evidence terms without linked production references.
Demonstrate missing reference validation for a skill with production gates and evidence requirements.
Help write better changelogs.
SOC 職業分類に基づく
| name | minimal-valid-skill |
| description | Create a small verified artifact from a user workflow. Use when the user asks to capture a workflow as a reusable skill with evidence, tool checks, failure modes, retry limits, and final review. |
Use this skill for a compact workflow.
Read references/production-skill-architecture.md and references/failure-modes.md.
Verify tools before relying on them with scripts/verify_tools.py. Run final review through references/final-review-gate.md.
Use the taxonomy in the linked reference.
Retry limits are finite and failures escalate.
Every success claim must cite a file, command output, or review artifact.
