メニュー
Creates a new git commit for all uncommitted changes with an atomic, conventionally-tagged message. Use when work is complete and ready to be committed.
デフォルトでは、最初にソースを確認する Prompt が選択されています。直接コマンドに切り替えるか、ローカルコピーをダウンロードすることもできます。
インストールを決める前に、SKILL.md と SkillsMP に表示されている付属ファイルをお読みください。
SOC 職業分類に基づく
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。
直接コマンドでは確認用 Prompt が省略されます。実行前にソースを確認してください。
npx skills add https://github.com/coleam00/ai-native-starter-pack --skill commitコマンドは1行のまま表示されます。コピー前に横へスクロールして全体を確認してください。
ローカルで確認しますか？SkillsMP が現在取得できるファイルをダウンロードできます。
SKILL.md を表示中
Slice an epic or next-epic doc into PIV-sized tickets with a dependency graph. Turns a large strategic doc into the discrete units of work that the PIV loop consumes. Accepts a Confluence page id OR a local PRD/epic doc path; optionally cross-references a Jira epic key. Writes the breakdown to docs/specs/ and, when the input was a Confluence page, publishes it back as a child page of the PRD. When a Jira epic key is passed, it also creates the tickets as issues under that epic, skipping any that already exist.
Drive a real browser to validate web apps end-to-end. Use when you need to navigate to a URL, interact with UI elements, fill forms, click buttons, take screenshots, assert page state, or run a full end-to-end validation flow for a web feature. The primary tool for automated browser-based E2E testing in the AI Layer.
Derive the AI Layer's global rules (CLAUDE.md) and on-demand context modules FROM an existing codebase by analyzing its real structure, conventions, and patterns. Use on a brownfield codebase that has no CLAUDE.md yet (Brownfield Type A) to build the foundation of the AI Layer.
| name | commit |
| description | Creates a new git commit for all uncommitted changes with an atomic, conventionally-tagged message. Use when work is complete and ready to be committed. |
Create a new commit for all of our uncommitted changes.
git status && git diff HEAD && git status --porcelain to see what files are uncommitted.feat, fix, docs, refactor, test, chore, etc. that reflects our work.A single commit containing all uncommitted changes, with a conventional-commit-style message
(<tag>: <atomic description>) that accurately reflects the work done.
After the commit succeeds, print two clearly labelled summaries:
One short paragraph (3–6 sentences) describing the feature/fix/refactor that was committed — what problem it solves and what files were the key touch points. Write for a developer skimming the git log.
Only include this section if any files under .claude/ were modified or added (CLAUDE.md, .claude/references/, .claude/skills/, .claude/agents/, etc.).
List each changed AI-layer file with a one-line note on what evolved and why. If nothing in .claude/ changed, omit this section entirely.