Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Create commit messages following Sentry conventions. Use when committing code changes, writing commit messages, or formatting git history. Follows conventional commits with Sentry-specific issue references.
.claude/skills/davila7-commit/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 39% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 47% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 53% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 55% | 0% |
| case-12 | ✗→✓ | ▲ Improved | 88% | 0% |
Follow these conventions when creating commits for Sentry projects.
<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 closingfix(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-5678feat(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-05 | pass→pass | 5,648 | 5,686 | +1% | 1 | 1 | 0% | 928 | 1,430 | +54% | 0 | 0 | — |
case-01 | fail→pass | 5,984 | 3,664 | -39% | 1 | 1 | 0% | 939 | 1,308 | +39% | 0 | 0 | — |
case-02 | fail→fail | 6,391 | 5,335 | -17% | 1 | 1 | 0% | 1,176 | 1,487 | +26% | 0 | 0 | — |
case-03 | pass→pass | 5,699 | 4,381 | -23% | 1 | 1 | 0% | 857 | 1,487 | +74% | 0 | 0 | — |
case-04 | fail→pass | 5,222 | 3,365 | -36% | 1 | 1 | 0% | 820 | 1,204 | +47% | 0 | 0 | — |
case-06 | fail→pass | 5,293 | 3,703 | -30% | 1 | 1 | 0% | 820 | 1,252 | +53% | 0 | 0 | — |
case-07 | fail→pass | 6,075 | 4,254 | -30% | 1 | 1 | 0% | 919 | 1,426 | +55% | 0 | 0 | — |
case-08 | pass→pass | 5,510 | 5,234 | -5% | 1 | 1 | 0% | 908 | 1,343 | +48% | 0 | 0 | — |
case-09 | pass→fail | 3,621 | 3,952 | +9% | 1 | 1 | 0% | 554 | 1,302 | +135% | 0 | 0 | — |
case-15 | pass→pass | 5,857 | 3,708 | -37% | 1 | 1 | 0% | 957 | 1,295 | +35% | 0 | 0 | — |
case-10 | pass→pass | 5,888 | 4,020 | -32% | 1 | 1 | 0% | 887 | 1,268 | +43% | 0 | 0 | — |
case-11 | pass→pass | 5,234 | 5,275 | +1% | 1 | 1 | 0% | 821 | 1,529 | +86% | 0 | 0 | — |
case-12 | fail→pass | 5,415 | 5,620 | +4% | 1 | 1 | 0% | 881 | 1,656 | +88% | 0 | 0 | — |
case-13 | pass→pass | 7,574 | 5,307 | -30% | 1 | 1 | 0% | 1,246 | 1,552 | +25% | 0 | 0 | — |
case-14 | pass→pass | 3,555 | 2,742 | -23% | 1 | 1 | 0% | 552 | 1,174 | +113% | 0 | 0 | — |
case-16 | pass→pass | 3,990 | 4,228 | +6% | 1 | 1 | 0% | 646 | 1,356 | +110% | 0 | 0 | — |
case-17 | fail→pass | 4,961 | 2,529 | -49% | 1 | 1 | 0% | 754 | 1,002 | +33% | 0 | 0 | — |
case-18 | fail→pass | 3,378 | 4,660 | +38% | 1 | 1 | 0% | 527 | 1,376 | +161% | 0 | 0 | — |
case-19 | pass→pass | 3,244 | 4,034 | +24% | 1 | 1 | 0% | 478 | 1,268 | +165% | 0 | 0 | — |
case-20 | pass→pass | 5,962 | 7,084 | +19% | 1 | 1 | 0% | 880 | 1,891 | +115% | 0 | 0 | — |
case-21 | pass→pass | 7,598 | 7,420 | -2% | 1 | 1 | 0% | 1,248 | 1,900 | +52% | 0 | 0 | — |
case-22 | pass→pass | 8,791 | 6,279 | -29% | 1 | 1 | 0% | 1,401 | 1,716 | +22% | 0 | 0 | — |
case-23 | pass→pass | 6,335 | 3,552 | -44% | 1 | 1 | 0% | 1,154 | 1,280 | +11% | 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. 23 cases were attempted. The headline lift of +26 percentage points is the difference between those two pass rates over the 23 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
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.
Other measured skills in the registry, with their headline benchmark lift.