A curated collection of reusable skills for AI coding agents, distilled from real-world development and engineering workflows.
A skill is a reusable prompt playbook stored as SKILL.md that an agent executes on demand. Skills follow the agentskills.io open standard and are compatible with Claude Code and OpenAI Codex CLI.
Invoke with a slash command: /commit, /debug my-file.go, /pr-review 42
| Skill | Trigger | Description |
|---|---|---|
| commit | /commit |
Stage changes and write a Conventional Commit message |
| create-pr | /create-pr |
Create a PR with title, description, and test plan |
| pr-review | /pr-review [PR] |
Review a PR for correctness, security, tests, and style |
| security-review | /security-review |
Audit code for OWASP Top 10, secret leaks, and insecure patterns |
| debug | /debug |
Systematically diagnose a bug and fix the root cause |
| refactor | /refactor [file] |
Improve code clarity without changing behavior |
| simplify | /simplify [file] |
Remove unnecessary complexity — dead code, over-abstraction, YAGNI |
| test-gen | /test-gen [file] |
Generate unit tests covering happy path, edges, and errors |
| docstring | /docstring [file] |
Add or improve docstrings and inline comments |
| changelog | /changelog [tag] |
Generate a Keep a Changelog entry from recent commits |
| migrate | /migrate [path] |
Audit database migrations for lock risks, data loss, and zero-downtime safety |
| dep-update | /dep-update |
Analyze outdated dependencies and produce a prioritized batch upgrade plan |
| postmortem | /postmortem |
Generate a blameless incident postmortem with timeline, RCA, and action items |
| adr | /adr |
Create an Architecture Decision Record |
| spec | /spec |
Write a requirements specification with acceptance criteria |
| release-notes | /release-notes [ver] |
Generate user-facing release notes grouped by impact, with breaking-change prominence |
| hotfix | /hotfix |
Ship an urgent production fix safely — triage, minimal fix, verify, PR |
| revert | /revert [commit] |
Safely revert a commit or range — checks downstream dependencies before acting |
| sync-main | /sync-main |
Safely fast-forward the primary branch from its remote |
| post-merge-cleanup | /post-merge-cleanup [PR] |
Safely remove merged local and remote branches |
Copy only the skills you want to install.
# Project-level
mkdir -p .claude/skills
cp -R skills/commit .claude/skills/commit
# User-level
mkdir -p ~/.claude/skills
cp -R skills/commit ~/.claude/skills/commit# User-level
mkdir -p ~/.codex/skills
cp -R skills/commit ~/.codex/skills/commitFor project-level Codex installation, follow the discovery path documented by your installed Codex version. This repository does not assume an unverified project-level path.
Run the copy command again to update an installed copy:
cp -R skills/commit ~/.codex/skills/commitBefore removal, verify that the target is the exact installed skill directory. Then remove that copy:
rm -rf ~/.codex/skills/commitallowed-tools declares the maximum capability a skill may request. The
workflow rules inside each skill still determine whether an action is
appropriate in the current repository and when user confirmation is required.
| Level | Skills | Impact |
|---|---|---|
| Read-only | dep-update, migrate, postmortem, pr-review, security-review | Inspect files, repository state, dependencies, or GitHub metadata without writing project or remote state |
| Local files | adr, changelog, debug, docstring, refactor, release-notes, simplify, spec, test-gen | May edit files in the current worktree and run local checks |
| Local Git | commit, sync-main | May stage and commit local changes or fast-forward local refs without updating remote refs |
| Remote Git or GitHub | create-pr, hotfix, post-merge-cleanup, revert | May create or update remote Git/GitHub state as defined by the workflow |
Install the validation dependency, run the regression suite, and validate the real skill collection before submitting changes:
python3 -m pip install -r requirements-dev.txt
python3 -m unittest discover -s tests -p 'test_*.py' -v
python3 scripts/validate_skills.pyThis repository is available under the MIT License.
Follow these principles when adding or editing a skill:
- Process-driven, not prompt-driven. Each skill defines an explicit step-by-step workflow, not a vague "help me do X". Steps are ordered and checkable.
- Constraints first. Hard limits (what the skill must never do) belong in the skill itself, not in a separate global config. This makes skills portable.
- Minimal tool permissions.
allowed-toolsgrants only the specific commands the skill needs — not broadBash(*). - Triggerable by natural language. The
descriptionfield covers realistic phrasings a developer would actually use, so the agent can auto-invoke without a slash command. - Single responsibility. One skill, one workflow. If a skill is doing two separate things, split it.
- Language-agnostic where possible. Skills that work across multiple languages (debug, refactor, docstring) should detect the project's language rather than hardcode one.