Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Helps write conventional commit messages, create atomic commits, and follow git best practices. Use when the agent needs to help with git commits, commit message writing, or git workflow guidance.
.claude/skills/aiskillstore-commit/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | 27% | 0% |
| case-01 | ✗→✓ | ▲ Improved | 68% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 52% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 56% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -11% | 0% |
Follow these conventions when creating commits for Sentry projects.
Use this skill when:
Before committing, ensure you're working on a feature branch, not the main branch.
bash# Check current branch git branch --show-current
If you're on main or master, create a new branch first:
bash# Create and switch to a new branch git checkout -b <type>/<short-description>
Branch naming should follow the pattern: <type>/<short-description> where type matches the commit type (e.g., feat/add-user-auth, fix/null-pointer-error, ref/extract-validation).
<type>(<scope>): <subject>
<body>
<footer>The header is required. Scope is optional. All lines must stay under 100 characters.
| Type | Purpose | |------|---------| | feat | New feature | | fix | Bug fix | | ref | Refactoring (no behavior change) | | perf | Performance improvement | | docs | Documentation only | | test | Test additions or corrections | | build | Build system or dependencies | | ci | CI configuration | | chore | Maintenance tasks | | style | Code formatting (no logic change) | | meta | Repository metadata | | license | License changes |
Reference issues in the footer using these patterns:
Fixes GH-1234
Fixes #1234
Fixes SENTRY-1234
Refs LINEAR-ABC-123Fixes closes the issue when mergedRefs links without closingWhen changes were primarily generated by a coding agent (like Claude Code), include the Co-Authored-By attribution in the commit footer:
Co-Authored-By: Claude <noreply@anthropic.com>This is the only indicator of AI involvement that should appear in commits. Do not add phrases like "Generated by AI", "Written with Claude", or similar markers in the subject, body, or anywhere else in the commit message.
fix(api): Handle null response in user endpoint
The user API could return null for deleted accounts, causing a crash
in the dashboard. Add null check before accessing user properties.
Fixes SENTRY-5678
Co-Authored-By: Claude <noreply@anthropic.com>feat(alerts): Add Slack thread replies for alert updates
When an alert is updated or resolved, post a reply to the original
Slack thread instead of creating a new message. This keeps related
notifications grouped together.
Refs GH-1234ref: Extract common validation logic to shared module
Move duplicate validation code from three endpoints into a shared
validator class. No behavior change.feat(api)!: Remove deprecated v1 endpoints
Remove all v1 API endpoints that were deprecated in version 23.1.
Clients should migrate to v2 endpoints.
BREAKING CHANGE: v1 endpoints no longer available
Fixes SENTRY-9999revert: feat(api): Add new endpoint
This reverts commit abc123def456.
Reason: Caused performance regression in production.| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-04 | fail→pass | 7,854 | 4,789 | -39% | 1 | 1 | 0% | 1,559 | 1,973 | +27% | 0 | 0 | — |
case-01 | fail→pass | 8,240 | 5,727 | -30% | 1 | 1 | 0% | 1,261 | 2,120 | +68% | 0 | 0 | — |
case-02 | fail→pass | 6,596 | 4,582 | -31% | 1 | 1 | 0% | 1,284 | 1,946 | +52% | 0 | 0 | — |
case-03 | fail→pass | 6,460 | 4,460 | -31% | 1 | 1 | 0% | 1,282 | 2,003 | +56% | 0 | 0 | — |
case-05 | pass→pass | 6,248 | 4,658 | -25% | 1 | 1 | 0% | 1,191 | 1,871 | +57% | 0 | 0 | — |
case-06 | pass→pass | 6,796 | 4,339 | -36% | 1 | 1 | 0% | 1,274 | 1,843 | +45% | 0 | 0 | — |
case-07 | fail→pass | 23,149 | 4,571 | -80% | 1 | 1 | 0% | 1,963 | 1,754 | -11% | 0 | 0 | — |
case-08 | pass→pass | 6,901 | 2,702 | -61% | 1 | 1 | 0% | 1,206 | 1,471 | +22% | 0 | 0 | — |
case-09 | pass→pass | 5,927 | 2,642 | -55% | 1 | 1 | 0% | 1,135 | 1,475 | +30% | 0 | 0 | — |
case-10 | fail→pass | 7,993 | 3,414 | -57% | 1 | 1 | 0% | 1,416 | 1,702 | +20% | 0 | 0 | — |
case-11 | pass→pass | 8,002 | 2,580 | -68% | 1 | 1 | 0% | 1,491 | 1,562 | +5% | 0 | 0 | — |
case-12 | pass→pass | 9,770 | 4,747 | -51% | 1 | 1 | 0% | 1,824 | 1,929 | +6% | 0 | 0 | — |
case-13 | pass→pass | 5,502 | 3,363 | -39% | 1 | 1 | 0% | 1,032 | 1,663 | +61% | 0 | 0 | — |
case-23 | pass→pass | 8,647 | 6,908 | -20% | 1 | 1 | 0% | 1,485 | 2,105 | +42% | 0 | 0 | — |
case-14 | pass→pass | 12,900 | 4,475 | -65% | 1 | 1 | 0% | 2,043 | 1,759 | -14% | 0 | 0 | — |
case-15 | pass→pass | 7,993 | 3,968 | -50% | 1 | 1 | 0% | 1,345 | 1,813 | +35% | 0 | 0 | — |
case-16 | fail→pass | 7,762 | 3,267 | -58% | 1 | 1 | 0% | 1,378 | 1,598 | +16% | 0 | 0 | — |
case-17 | pass→pass | 6,103 | 3,300 | -46% | 1 | 1 | 0% | 1,102 | 1,585 | +44% | 0 | 0 | — |
case-18 | pass→pass | 5,802 | 1,768 | -70% | 1 | 1 | 0% | 952 | 1,277 | +34% | 0 | 0 | — |
case-19 | fail→pass | 7,069 | 3,285 | -54% | 1 | 1 | 0% | 1,330 | 1,602 | +20% | 0 | 0 | — |
case-20 | fail→pass | 7,919 | 2,399 | -70% | 1 | 1 | 0% | 1,319 | 1,405 | +7% | 0 | 0 | — |
case-21 | fail→pass | 7,122 | 3,214 | -55% | 1 | 1 | 0% | 1,172 | 1,524 | +30% | 0 | 0 | — |
case-22 | fail→pass | 5,808 | 2,349 | -60% | 1 | 1 | 0% | 950 | 1,350 | +42% | 0 | 0 | — |
case-24 | pass→pass | 10,478 | 7,650 | -27% | 1 | 1 | 0% | 1,661 | 2,409 | +45% | 0 | 0 | — |
case-25 | pass→pass | 4,402 | 3,988 | -9% | 1 | 1 | 0% | 862 | 1,709 | +98% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 25 cases were attempted. The headline lift of +44 percentage points is the difference between those two pass rates over the 25 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
| Model | Method | Date | Lift |
|---|---|---|---|
| gemini-3.6-flash | verified | 8/21/2026 | -9% |
Other measured skills in the registry, with their headline benchmark lift.