メニュー
Execute a full feature workflow by chaining feature development, tests, feature summaries, selective cleanup, personal review artifacts, and review-feedback triage when external feedback is available.
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
Commit and publish local GitHub work with review requests. Use when the user wants Codex to commit staged changes, stage all changes only when nothing is staged, push the current branch, and open a GitHub pull request that tags @codex and @copilot for review.
Analyze staged and unstaged git changes and refactor for readability, maintainability, and conciseness while preserving behavior. Use when the user asks to refactor recent changes, clean up work in progress, improve code quality, or review a diff for safe structural improvements.
Generate implementation TASKS.md plans from one design document or from all feature documents in a directory.
Run a phased feature-development workflow: discovery, codebase exploration, clarifying questions, architecture options, implementation, quality review, and summary. Use when a user asks for end-to-end feature delivery with strong design rigor before coding.
Convert one planning document into PRD.md, USER_FLOW.md, BACKEND_ARCHITECTURE.md, FRONTEND_DESIGN.md, and TASKS.md in fixed deterministic order with a quality gate and traceability checks.
Remove AI-generated code slop from the current branch by auditing `git diff main...HEAD` and applying minimal cleanups. Use when a user asks to de-slop a PR/branch, make code look human-written, or remove over-defensive/verbose/generated patterns without changing behavior.
| name | full-feature-workflow |
| description | Execute a full feature workflow by chaining feature development, tests, feature summaries, selective cleanup, personal review artifacts, and review-feedback triage when external feedback is available. |
| disable-model-invocation | true |
Execute these steps in order:
feature-dev for the provided feature request.write-tests for the implemented feature.feature-summary with output path {git-root}/docs/feature-summary.md.code-review-personal (it will load context from docs/feature-summary.md) and implement high-value low-risk cleanups.feature-summary again with output path {git-root}/docs/feature-summary-2.md.code-review-personal using updated context from docs/feature-summary*.md and save review to {git-root}/docs/code-review-personal.md.review-feedback-orchestrator using {git-root}/docs/code-review-personal.md from Step 7 as the primary review source (append PR comments or pasted notes if available), then save output to {git-root}/docs/review-feedback-resolution.md.{git-root}/docs/code-review-personal.md from Step 7, then include any additional external reviewer feedback when available.