メニュー
Generate a router-based skill across the host AI tools a project uses. Use when the user wants to create, scaffold, or refactor a skill, or turn a workflow into one. Not for other artifacts like rules, agents, commands, hooks.
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。
SOC 職業分類に基づく
Initialize or refresh the project memory bank. Use when the user wants to set up or regenerate the project's memory files. Not for updating one memory file after it exists or editing a single rule directly.
Guide a project's journey through AIDD, from first setup to shipping a feature. Use when the user says onboard me, where do I start, or what to do next. Not for listing every installed surface.
Design and validate a new SaaS's architecture into an INSTALL.md via Q&A and stack comparison. Use when the user starts a project, chooses a stack, or picks an architecture pattern. Not for editing an existing stack or scaffolding code.
Route a request to generate a context artifact (skill, rule, agent, command, or hook) to its generator when the kind is unnamed. A named kind triggers its generator directly. Not for listing existing artifacts.
Generate a coding rule that governs editor and agent behavior across the host AI tools. Use when the user wants to write, add, or refactor a rule, convention, or coding standard. Not for other artifacts like skills, agents, or hooks.
Generate an agent across the host AI tools a project uses. Use when the user wants to create, scaffold, or refactor an agent, subagent or specialized role. Not for other artifacts like skills, rules, commands, hooks.
| name | 04-skill-generate |
| description | Generate a router-based skill across the host AI tools a project uses. Use when the user wants to create, scaffold, or refactor a skill, or turn a workflow into one. Not for other artifacts like rules, agents, commands, hooks. |
| argument-hint | capture-intent | decompose-actions | draft-skill | write-actions | validate |
Builds one canonical skill from intent and renders it per confirmed host tool, or once as a plugin source.
| # | Action | Role | Input |
|---|---|---|---|
| 01 | capture-intent | Clarify intent + tools, inventory overlaps | user request |
| 02 | decompose-actions | Break the skill into atomic testable actions | what it produces |
| 03 | draft-skill | Write the SKILL.md router | intent + plan |
| 04 | write-actions | Write each action file from the template | the plan |
| 05 | validate | Run each action's Test, aggregate pass/fail | the skill path |
Run the actions in order, 01 → 05, and run each action's ## Test before the next. In modify mode the tool is fixed by the existing skill's location, so the resolution gate is skipped.
Before running an action, read its file in actions/, not only the table or assets.
references/skill-authoring.md: the contract (R1-R13, action anatomy, naming).references/tool-paths.md: per-tool skills path, frontmatter, resolution + write-safety gate.assets/skill-template.md: SKILL.md scaffold.assets/action-template.md: canonical action scaffold.