メニュー
Analyze changes and create a commit with auto-generated message following the project's commit convention. Links to feature spec REQ numbers when a feature name is provided.
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
| name | commit |
| description | Analyze changes and create a commit with auto-generated message following the project's commit convention. Links to feature spec REQ numbers when a feature name is provided. |
| argument-hint | [feature-name] |
| context | fork |
$ARGUMENTS contains a feature name → spawn with sonnet (REQ linking requires reading spec.md and mapping changes to requirements)$ARGUMENTS is empty → spawn with haiku (simple diff analysis, no spec context needed)Spawn committer agent (model per above) with:
Create a commit for the following changes.
Feature context: $ARGUMENTS
Vercel AI SDK expert guidance. Use when building AI-powered features — chat interfaces, text generation, structured output, tool calling, agents, MCP integration, streaming, embeddings, reranking, image generation, or working with any LLM provider.
Turborepo monorepo build system guidance. Triggers on: turbo.json, task pipelines, dependsOn, caching, remote cache, the "turbo" CLI, --filter, --affected, CI optimization, environment variables, internal packages, monorepo structure/best practices, and boundaries. Use when user: configures tasks/workflows/pipelines, creates packages, sets up monorepo, shares code between apps, runs changed/affected packages, debugs cache, or has apps/packages directories.
Implement a feature. Supports resuming interrupted work and team mode (--team flag). Reads spec/feature/[name]/spec.md and design.md, generates PLAN.md inside the feature directory, waits for user confirmation, then implements and verifies the feature.
Generate or update MSW mock handlers and fixtures from feature spec API contracts. Use to set up mock infrastructure, generate feature-specific mocks, or check mock status.
AI-driven browser testing against feature specs. Default mode reads spec REQs and autonomously tests in a real browser via Playwright MCP. Also supports running existing Playwright test files, visual regression, and accessibility audits.
Check how well the current implementation matches the feature spec and evaluate code quality. Runs spec compliance review followed by code quality review. Optionally runs unit/integration test audit, logging audit, and security audit when strategy files exist. Does not modify code.