Agent skill
commit
Commit workflow for ai-standards repo. Formats all markdown files and previews changes before committing.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/commit-guillempuche-ai-standards
SKILL.md
Commit Workflow
Standard commit workflow for the ai-standards repository.
Before Every Commit
1. Run Markdown Formatter
Format project markdown files using mdformat (excludes opensrc/ which contains external source):
nix develop -c mdformat skills/ .claude/ agents/ templates/ *.md
2. Preview Changes
Show files involved and diff preview:
git status
git diff --stat
git diff
3. Analyze and Group Changes
Review the changes and determine:
- Single commit: All changes are related to one feature/fix
- Multiple commits: Changes are unrelated and should be separate
Examples:
- Docs update + new skill → 2 commits
- Rename agent + update references → 1 commit
- Bug fix + unrelated refactor → 2 commits
4. Stage and Commit
For single commit:
git add -A
git commit -m "commit message"
For multiple commits, stage selectively:
git add <related-files>
git commit -m "first commit message"
git add <other-files>
git commit -m "second commit message"
Commit Message Guidelines
- Start with uppercase, imperative mood
- Reference skill/agent names in brackets when applicable:
[powersync] Add sync pattern docs - If AI made the changes, include co-author:
Co-Authored-By: Claude <[email protected]>
Output Format
Always show proposed commits with their files:
**Commit 1:** `commit message here`
- file1.md
- file2.ts
**Commit 2:** `another commit message`
- file3.md
Then wait for user approval before executing.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?