Collect Commit Info
Productivitycollect-commit-infoCollect Commit Info is an Agent Skill for productivity published in the majiayu000/claude-skill-registry repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.
Analyze staged files, group by category, and generate conventional commit specs as JSON.
How to use this skill
Bring this guide into your coding agent with a prompt tailored to the tool you use.
- Open your project in Codex.
- Copy and paste the prompt below.
- Review files and risks before approving any action.
Inspect the Agent Skill at https://github.com/majiayu000/claude-skill-registry/blob/HEAD/skills/data/collect-commit-info/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/collect-commit-info, but wait for my approval before writing files or running scripts.
Copying this prompt does not install or run the skill. Review third-party files before use.
This skill analyzes staged git files and returns commit specifications as JSON. It:
- Collects staged file metadata via script
- Reads diff content to understand changes
- Groups files by category (deps, ci, config, source, test, docs)
- Generates conventional commit messages for each group
- Returns JSON specs for the caller to execute
Arguments
| Arg | Default | Description |
|---|---|---|
--lang | context | Message language (conversation context → system locale → en) |
Output Contract
This skill ALWAYS returns JSON. The caller executes git commands based on this output.
Success:
{
"commits": [
{"message": "type(scope): subject\n\nBody", "files": ["file1", "file2"]}
],
"summary": {"total_commits": 1, "total_files": 2}
}
Error:
{"error": "description", "error_code": "CODE"}
Workflow
Step 1: Collect file info
${CLAUDE_PLUGIN_ROOT}/skills/collect-commit-info/scripts/collect-info.sh --lang <code>
Script returns JSON with temp_dir, files array (with categories), and paths.diff_content.
On error JSON → return it immediately and stop.
Step 2: Read diff content
Read the file at paths.diff_content to understand what changed.
Step 3: Group files by category
Group files from the files array. Commit order:
deps- Dependencies (package.json, lock files)ci- CI/CD (.github/*)config- Configuration (*.yml, *.toml, rc files)source- Source codetest- Tests (_test., .test., .spec.)docs- Documentation (.md, docs/)
Step 4: Generate commit messages
For each group, create a conventional commit message:
type(scope): imperative subject (max 50 chars)
Optional body explaining what and why.
Type by category:
| Category | Type |
|---|---|
| deps | chore |
| ci | ci |
| config | chore |
| source | feat/fix/refactor (analyze diff) |
| test | test |
| docs | docs |
For source files, analyze diff to determine type:
- New functionality →
feat - Bug fixes, error handling →
fix - Restructuring, cleanup →
refactor
Scope: Derive from paths (e.g., src/auth/* → auth)
Language: Use lang.effective from script output. If conversation context indicates a preferred language, use that instead.
Step 5: Cleanup and return
${CLAUDE_PLUGIN_ROOT}/skills/collect-commit-info/scripts/cleanup.sh <temp_dir>
Return the JSON commit specs.