From rsturla-skills
Generate or improve git commit messages from staged changes using Claude on Vertex AI. Conventional Commits format, validates line lengths, retries on failure. Use when the user wants to write, generate, or improve a commit message, asks for help with git commits, or invokes /commit-message — even if they just say "commit this" or "what should the commit say."
How this skill is triggered — by the user, by Claude, or both
Slash command
/rsturla-skills:commit-messageThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Generate or improve commit messages from staged changes using Claude on Vertex AI.
Generate or improve commit messages from staged changes using Claude on Vertex AI.
git diff --cached --stat + git diff --cached (truncate to 8000 chars)feat: add database connection pool and migrations
- Add SQLite pool with WAL mode, auto-commit/rollback, and connection limits
- Add schema migrations for users and sessions tables
- Import DatabasePool in app entry point
feat/fix/refactor/docs/test/chore/ci/build/perf/style)Retry with error feedback on failure.
| Env Var | Default | Description |
|---|---|---|
CLAUDE_COMMIT_PROJECT | itpc-gcp-core-pe-eng-claude | GCP project |
CLAUDE_COMMIT_LOCATION | global | Vertex AI location (use global to avoid 10% regional premium) |
CLAUDE_COMMIT_MODEL | claude-haiku-4-5 | Model to use |
CLAUDE_COMMIT_RETRIES | 3 | Max retry attempts |
<commit> tag extraction as fallbackSee REFERENCE.md for Vertex AI call patterns, structured output schema, and git hook installation.
Guides collaborative design exploration before implementation: explores context, asks clarifying questions, proposes approaches, and writes a design doc for user approval.
Creates structured, bite-sized implementation plans from specs or requirements before writing code. Useful for breaking down multi-step tasks into testable steps with file structure and task boundaries.
Synthesizes the current conversation into a structured spec (PRD) and publishes it to the project issue tracker with a ready-for-agent label, without interviewing the user.
npx claudepluginhub rsturla/skills