.factory/skills/commit/SKILL.md
Commit staged changes with conventional commit message. Use when user wants to commit code changes.
npx skillsauth add sunshow/droidgear commitInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Check current status:
git status --porcelain
If no staged changes, stage all modified files:
git add -A
Review changes to be committed:
git diff --cached --stat
git diff --cached
Security check: Scan diff for sensitive data:
Analyze changes and determine commit type:
feat: - New feature or functionalityfix: - Bug fixchore: - Maintenance, dependencies, releasedocs: - Documentation onlystyle: - Code formatting, no logic changerefactor: - Code restructure without behavior changetest: - Adding or updating testsGenerate commit message:
<type>: <description>feat: openclaw support streaming settingsfix: openclaw profile apply policydocs: update changelog for v0.3.2style: format Rust codeExecute commit:
git commit -m "<type>: <description>"
If commit fails due to pre-commit hooks:
git status shows clean working tree after commitdocumentation
Generate changelog from commits since last tag and release new version. Use when user wants to release a new version or update changelog.
development
Maintainer-only workflow for handling GitHub Secret Scanning alerts on OpenClaw. Use when Codex needs to triage, redact, clean up, and resolve secret leakage found in issue comments, issue bodies, PR comments, or other GitHub content.
development
Maintainer workflow for OpenClaw releases, prereleases, changelog release notes, and publish validation. Use when Codex needs to prepare or verify stable or beta release steps, align version naming, assemble release notes, check release auth requirements, or validate publish-time commands and artifacts.
development
Run, watch, debug, and extend OpenClaw QA testing with qa-lab and qa-channel. Use when Codex needs to execute the repo-backed QA suite, inspect live QA artifacts, debug failing scenarios, add new QA scenarios, or explain the OpenClaw QA workflow. Prefer the live OpenAI lane with regular openai/gpt-5.4 in fast mode; do not use gpt-5.4-pro or gpt-5.4-mini unless the user explicitly overrides that policy.