.agents/skills/create-commit/SKILL.md
Stages changes safely, generates a conventional-commit message from the diff, and blocks secrets or debug artifacts from being committed. TRIGGER when: user asks to commit, save changes, stage files, write a commit message, run git commit, check in my changes, or commit my work. DO NOT TRIGGER when: user asks to push, open a PR, or create a branch.
npx skillsauth add geemus/hax-yax create-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.
Guides agents through safe, well-formed git commits. Stages files automatically (skipping secrets and artifacts), generates a conventional-commit message from the diff, and confirms before committing.
Side effects: stages files (git add), creates a git commit object. Does not push or open a PR.
git status
git diff
If git status shows no changes (clean working tree), stop and tell the user: "Nothing to commit — the working tree is clean."
Identify:
dist/, *.pyc, node_modules/, *.min.js), lock files unless they changed intentionallyIf the untracked file set is ambiguous (many files, files that look auto-generated, or files outside the project's normal structure), list them and ask the user which to include before proceeding.
Before staging anything, scan all modified, added, and untracked files identified in step 1 for secret patterns. Read references/secret-patterns.md for the full pattern list.
If any match is found:
.gitignore)Stage all safe files (those that passed step 2 and are not excluded artifacts) using individual git add <file> calls — never git add . or git add -A.
Report a brief summary:
If nothing is staged after exclusions, stop and tell the user what was skipped and why.
Read the staged diff:
git diff --cached
Derive the message following Conventional Commits:
<type>[optional scope]: <subject>
[optional body]
Type — pick the best fit:
feat: new feature or capabilityfix: bug fixdocs: documentation onlyrefactor: restructuring without behaviour changetest: adding or updating testschore: maintenance, tooling, dependenciesScope — optional; use the skill name, component, or directory most affected (e.g. feat(plan):, fix(skills):).
Subject — lowercase imperative mood, no trailing period, ≤72 characters.
Body — include when the change is non-obvious: explain why, not what. Wrap at 72 characters.
Display the proposed commit message to the user, then immediately commit using a HEREDOC to avoid shell quoting issues:
git commit -m "$(cat <<'EOF'
<type>[scope]: <subject>
<body if any>
EOF
)"
Invocation:
/commit
Feature addition:
User has edited
.agents/skills/plan/SKILL.mdto add update mode.
feat(plan): add update mode for existing issues
Allows /plan to be invoked with an issue number or URL to edit an
existing issue in place rather than always creating a new one.
Bug fix:
User fixed a typo and a broken link in
AGENTS.md.
fix: correct typo and broken link in AGENTS.md
Secret detected — partial commit:
User runs
/commit; one file contains a hardcoded database password.
Staged: src/api/client.py, README.md
Skipped:
- config/local.env [BLOCKED: explicit secret assignment on line 4]
Fix: remove DB_PASSWORD value; reference $DB_PASSWORD instead,
or add config/local.env to .gitignore
Commit message:
feat(api): add client module
development
Produces a complete health report on a skill library: per-skill structural validation followed by cross-skill analysis covering trigger conflicts, redundancy, workflow coverage gaps, and composition chains. Auto-fixes unambiguous minor structural issues (whitespace, missing optional metadata) and formats all other findings with format-review-comments. TRIGGER when: user asks to audit skills, check skill coverage, validate all skills, find gaps in skills, check for trigger conflicts, or health-check the skill library. DO NOT TRIGGER when: user asks to create, update, rename, or delete a skill (use upsert-skill instead); or to evaluate a single skill for quality (use review-skill instead).
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.