メニュー
Scaffold a new skill in THIS repo — correct folder, valid frontmatter, README row, credits, and validation. (For the authoring craft, use the global skill-creator.)
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
Use before any creative/build work — adding features, building components, new functionality, or changing behavior. Turns a brief or vague idea into an approved design doc through one-question-at-a-time dialogue. Does NOT write code until the design is approved. Output is the design doc; the next step is owned by the caller.
Craft a clear /goal condition for Claude Code's autonomous mode from a rough task description.
Convene an independent cross-model judge — a model of a different family (e.g. Codex/GPT, Gemini, or a Cursor agent pinned to a non-Claude model), whichever CLI is installed — to cross-examine an artifact (a decision, a diff, a document, or a research answer) and adjudicate its findings disbelieve-it-back. This is the cross-model *mechanism*; the caller brings the artifact and its own in-family review. Use via `vet` (code), `research-council` (research), `plan` (a design decision), or directly when you want a second opinion from a model that doesn't share your blind spots. It reviews; it never edits.
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
Reference for writing and editing skills well — the vocabulary and principles that make a skill predictable.
Build and sharpen a project's domain model. Use when the user wants to pin down domain terminology or a ubiquitous language, record an architectural decision, or when another skill needs to maintain the domain model.
| name | add-skill |
| description | Scaffold a new skill in THIS repo — correct folder, valid frontmatter, README row, credits, and validation. (For the authoring craft, use the global skill-creator.) |
| disable-model-invocation | true |
Place a new skill so it satisfies the repo's invariants and installs cleanly. This handles placement and bookkeeping.
Choose the location (grouping below the domain is for humans; only the leaf matters):
<domain>/<group>/<name>/ (e.g. software-development/review/<name>/).workflows/<name>/.meta/<name>/.install.conf or it
won't install (default-deny).Pick a kebab-case leaf name unique across the entire repo (all domains, all depths) — the installer flattens leaves into one dir. The step-6 validator enforces this.
Create <location>/<name>/SKILL.md from docs/skill-template.md:
name: must equal the folder name exactly.description: is the trigger — lead with WHAT it does, then Use when … with concrete
cues.If adapted from another source: add a row to CREDITS.md, and if the
license requires attribution (MIT/BSD/Apache) keep a license: line in the frontmatter.
Add a one-line row to the area's README.md table (software-development/, workflows/,
or meta/). Keep it thin.
Validate, then preview the install:
./scripts/validate-skills.sh # must pass (0 errors)
./install.sh --dry-run # confirm the new leaf links with no collision