Ready to supercharge your AI agents?

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

Commit · vm0-ai | DecimalAI

code reviewby vm0-ai

Commit

vm0-ai/commit

Source vm0-ai/vm0 ↗License NOASSERTION

Complete pre-commit workflow - select and run applicable quality checks, then validate/create conventional commit messages

NewMaintained

Automatic

Coding pack

Last verified 9/9/2026

What it changes

Passed 6 of 13 test cases with the skill, and 7 of 13 without it.

Without skill54%

With skill46%

Checks it passed that the model alone missed

Execute only one Vitest process at a time.
Set CARGO_BUILD_JOBS=1 when retrying after an ENOMEM failure.
Skip running Cargo test suite for markdown documentation changes.

and 1 more in the full report

3 fixed8 passed either way8 still failing5 broke

Pass-rate lift: -8 pp
Tokens: -13%
Agent turns: 0%
Response time: -13%

Model gemini-3.6-flashMeasured 9/9/2026v211 of 24 cases passed with skill · 13 comparable

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/vm0-ai-commit/SKILL.md https://app.decimal.ai/s/vm0-ai-commit/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add vm0-ai-commit, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/vm0-ai-commit/ and pins it in .decimal/skills.lock

decimalai skills add vm0-ai-commit

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/vm0-ai-commit/SKILL.md https://app.decimal.ai/s/vm0-ai-commit/SKILL.md

Raw file: /s/vm0-ai-commit/SKILL.md ↗ · machine-readable summary at /s/vm0-ai-commit.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 3 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 3

Prompt

I just edited `docs/api-guide.md` to update endpoint examples. Please review, run our complete Cargo test suite and Vitest suite, and create a commit.

What was checked, without and with the skill
Checked	Without skill	With skill
Skip running Cargo test suite for markdown documentation changes.	Missed	Passed
Skip running Vitest test suite for markdown documentation changes.	Missed	Passed

case-10 · gemini-3.6-flash · 9/9/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md44 linessingle file

Commit

Use check to verify staged work, message to propose or validate its message, or both when a commit is requested.

Scope and Checks

Inspect git status --short, git diff, and git diff --cached. Stage only the requested change; preserve unrelated worktree and staged content.
Follow development and verification for the affected files, workspaces, generated outputs, and runtime consumers. Read the matching testing guide when behavior changes.
Run applicable formatting, lint/static analysis, type checks, and tests. Await each heavy check; run one Vitest or Cargo check at a time.
Fix actual failures. After checks pass, repeat them only if a new change, failure, or unresolved concern warrants it. Documentation does not require unrelated language suites.

lefthook.yml is the staged-file hook configuration. Hooks do not replace behavior verification. For local Rust ENOMEM failures, check for competing compiler/linker processes and retry once with CARGO_BUILD_JOBS=1; investigate actual compiler failures separately. Do not delete installed dependencies as a generic response to a slow hook.

Message

Use <type>[optional scope]: <description>. The authoritative rules and allowed types are in commitlint.config.mjs: lowercase type and subject, no final period, and at most 100 header characters. Use an imperative description of the actual change.

Examples:

feat: add agent sharing
fix(api): preserve webhook idempotency
docs: simplify testing guidance

Choose the type from the change, not from a desired version bump. See release behavior when release impact matters.

Track record

Benchmark

6 / 13

test cases passed, vs 7 / 13 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v5 — 9/9/2026

View 15 scanner checks

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

vm0-ai / vm0

.claude/skills/commit/SKILL.md

View on GitHub ↗

License NOASSERTIONImported 9/9/2026Version v2

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Commit

Scope and Checks

Message

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills