Ready to supercharge your AI agents?

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

Commit Message — measured AI agent skill | DecimalAI

contextosai/commit-message

SkillScore55Maintained

Write a clear, conventional git commit message from staged changes. Use when the user asks to commit, write a commit message, or describe what changed.

by contextosai

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

Automatic

Coding pack

decimalai skills pull contextosai-commit-message

Get this skill — curl · raw file

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

Raw file: /s/contextosai-commit-message/SKILL.md ↗ · machine-readable summary at /s/contextosai-commit-message.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 4d ago

—+12% tokens0% turns55% of whole cases pass with skill (12/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-05	✗→✓	▲ Improved	89%	0%
case-09	✗→✓	▲ Improved	30%	0%
case-13	✗→✓	▲ Improved	-8%	0%
case-22	✓→✗	▼ Worse	4%	0%
case-20	✓→✓	＝ Same ✓	-17%	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

contextosai / skills

skills/commit-message/SKILL.md

View on GitHub ↗

License MITImported 8/2/2026Version v1

Skill contents

SKILL.md

Commit Message

Generate a high-quality commit message that describes the staged changes.

Steps

Run git diff --staged to see what is actually being committed. If nothing

is staged, inspect git status and ask the user what to stage.

Identify the single primary intent of the change. If the diff does more than

one unrelated thing, suggest splitting it into multiple commits.

Write the message using the Conventional Commits format.

Format

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

<body — what changed and why, wrapped at ~72 cols>

type: one of feat, fix, refactor, docs, test, chore, perf,

build, ci.

subject: imperative mood, lowercase, no trailing period, ≤ 50 chars.
body: optional. Explain why, not just what. Omit for trivial changes.

Guidelines

Describe the effect of the change, not the mechanics of editing files.
Never invent a rationale that isn't supported by the diff.
One logical change per commit.

Examples

feat(auth): add refresh-token rotation

Tokens are now rotated on every refresh so a leaked token is valid for
at most one cycle.

fix(parser): handle empty input without panicking

Want to see if contextosai/commit-message 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.