Install
$ agentstack add skill-rikdc-ai-skills-commit ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Commit - Conventional Commit Messages
Creates commits with short conventional commit messages. Runs pre-commit checks and suggests splitting when the staged changes cover more than one concern.
Usage
/git-workflow:commit [--no-verify] [--help]
Workflow
- Pre-commit checks (unless
--no-verify): runmake checksif available. - Git analysis: inspect staged files and
git diffto identify the change. - Commit: write the message, then commit.
If nothing is staged, stage all modified files. If the diff covers distinct concerns, propose atomic commits before committing.
Message Rules
():
[body — only when required]
- No emoji. Not in the subject, not in the body.
- Subject: imperative mood, lower case, no trailing period, under 60 characters.
scopeis optional; include it only when it disambiguates.- Default to a subject line alone. Most commits need nothing more.
- Add a body only for information the diff cannot show: why the change was
made, a breaking change, or an issue reference. Cap it at two short sentences or three bullets.
- Never restate the diff, list touched files, summarise your process, or add
closing commentary.
Types
feat: new featurefix: bug fix, security fix, warning fixdocs: documentationstyle: formattingrefactor: restructuring without behaviour changeperf: performancetest: testschore: tooling, dependencies, configurationci: CI/CD
Splitting Criteria
Propose separate commits when the staged changes mix concerns, mix types (feature + fix + docs), or are large enough that one message cannot describe them accurately.
Examples
Good:
feat(auth): add session refresh endpointfix(render): release texture handles on unmountdocs: document the scanner exit codesrefactor: collapse duplicate error wrapping
With a body, where the reason is not visible in the diff:
fix(scanner): match patterns case-insensitively
Uppercase AWS keys were slipping through, reported in #212.
Too verbose — do not do this:
✨ feat(auth): add a new session refresh endpoint to the auth package
This commit adds a new endpoint. It modifies auth/handler.go to add the
handler, auth/routes.go to register the route, and auth/handler_test.go to
cover it. This improves the developer experience and makes the codebase
more maintainable going forward.
Options
--no-verify: skip pre-commit checks--help: show this reference
Notes
- Pre-commit failures: ask whether to fix or proceed.
- No staged files: auto-stage modified and new files.
- Large changes: suggest atomic commits with guided staging.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: rikdc
- Source: rikdc/ai-skills
- License: MPL-2.0
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.