Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

Conventional Commit — measured AI agent skill | DecimalAI

kunanonj/commit

SkillScore86Maintained

Generate a conventional commit message for staged changes

by kunanonj

Links this skill to your agents and keeps it current with the author’s updates.

On-demandOn-demand: invoked explicitly — never occupies your agent's context until called.

Coding pack

decimalai skills pull kunanonj-commit

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/kunanonj-commit/SKILL.md

Raw file: /s/kunanonj-commit/SKILL.md ↗ · machine-readable summary at /s/kunanonj-commit.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 3d ago

—-8% tokens0% turns86% of whole cases pass with skill (19/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-07	✗→✓	▲ Improved	-1%	0%
case-03	✓→✓	＝ Same ✓	-13%	0%
case-04	✓→✓	＝ Same ✓	43%	0%
case-05	✓→✓	＝ Same ✓	-14%	0%
case-06	✓→✓	＝ Same ✓	0%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/2/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

kunanonj / ai-skills-hub

skills/commit/SKILL.md

View on GitHub ↗

License MITImported 8/2/2026Version v1

Skill contents

SKILL.md

Conventional Commit

Generate a conventional commit message for staged changes.

Instructions

Run git diff --cached to see staged changes
Analyze the nature of changes
Generate a commit message following the format below

Commit Format

<type>(<scope>): <subject>

[optional body]

[optional footer]

Types

feat: New feature
fix: Bug fix
docs: Documentation only
style: Formatting, missing semicolons, etc.
refactor: Code change that neither fixes nor adds feature
perf: Performance improvement
test: Adding missing tests
chore: Maintenance tasks

Rules

Subject: imperative mood, no period, max 50 chars
Body: explain WHAT and WHY, not HOW
Footer: breaking changes, issue references

Examples

feat(auth): add password reset functionality

Implement password reset flow with email verification.
Users can now request a reset link and set new password.

Closes #123

fix(api): prevent race condition in order processing

Add mutex lock to ensure orders are processed sequentially.
This fixes duplicate charge issues reported by users.

Fixes #456

refactor(cart): extract pricing logic to separate module

No functional changes. Improves testability and
separates concerns for future discount feature.

Execution

After analyzing staged changes, suggest a commit message. Ask for confirmation before executing git commit -m "...".

$ARGUMENTS

Want to see if kunanonj/commit would activate on your phrasing? Try it before you install — no LLM call, no signup.

Other measured skills in the registry, with their headline benchmark lift.