Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Create a minimal working CodeRabbit configuration and trigger your first AI review. Use when starting with CodeRabbit, testing your setup, or learning basic .coderabbit.yaml patterns. Trigger with phrases like "coderabbit hello world", "coderabbit example", "coderabbit quick start", "first coderabbit review".
.claude/skills/jeremylongshore-coderabbit-hello-world/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | 10% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 12% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 23% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 67% | 0% |
| case-12 | ✗→✓ | ▲ Improved | 22% | 0% |
Prove installation and review behavior with a synthetic reversible PR. Avoid production secrets, branch-rule changes, and timing promises.
references/official-docs.md and re-check any time-sensitive contract before execution.Treat Git-provider sessions, CodeRabbit web sessions, CLI credentials, and CodeRabbit API keys as separate credentials. Use only an already-approved session or secret-manager reference, never print a secret, and do not place credentials in .coderabbit.yaml, source files, logs, or deliverables.
Require owner approval before installation, a production-repository test PR, or merge. Keep analysis and drafts local until approval is explicit, and record who approved the action and its scope.
A receipt with repository, branch, PR, config hash, review surfaces, CI, and cleanup. Include source dates, unknowns, and the exact boundary between observed fact and recommendation.
| Condition | Response | |---|---| | Current contract is unclear or docs disagree | Stop mutation, cite both sources, and request owner resolution. | | Required access or approval is missing | Produce a draft and evidence plan only. | | Validation or pilot behavior differs from expectation | Restore the prior state and retain the failed evidence. | | Output contains secrets or private code | Stop, quarantine the artifact, redact it, and notify the data owner. |
Validate a private-repository installation with a docs-only PR.
Confirm a chill profile change is read before merge.
references/official-docs.md.| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | pass→pass | 10,570 | 5,386 | -49% | 1 | 1 | 0% | 2,065 | 2,180 | +6% | 0 | 0 | — |
case-02 | fail→pass | 12,108 | 7,232 | -40% | 1 | 1 | 0% | 2,099 | 2,304 | +10% | 0 | 0 | — |
case-03 | fail→pass | 13,322 | 11,335 | -15% | 1 | 1 | 0% | 2,777 | 3,113 | +12% | 0 | 0 | — |
case-04 | fail→fail | 10,203 | 10,633 | +4% | 1 | 1 | 0% | 1,785 | 2,927 | +64% | 0 | 0 | — |
case-05 | pass→pass | 11,253 | 6,955 | -38% | 1 | 1 | 0% | 2,065 | 2,282 | +11% | 0 | 0 | — |
case-10 | pass→pass | 3,687 | 2,212 | -40% | 1 | 1 | 0% | 620 | 1,421 | +129% | 0 | 0 | — |
case-06 | fail→pass | 15,192 | 12,148 | -20% | 1 | 1 | 0% | 2,626 | 3,224 | +23% | 0 | 0 | — |
case-07 | pass→pass | 6,101 | 1,661 | -73% | 1 | 1 | 0% | 902 | 1,285 | +42% | 0 | 0 | — |
case-08 | pass→pass | 2,786 | 2,148 | -23% | 1 | 1 | 0% | 486 | 1,332 | +174% | 0 | 0 | — |
case-09 | fail→pass | 4,743 | 2,750 | -42% | 1 | 1 | 0% | 909 | 1,516 | +67% | 0 | 0 | — |
case-11 | pass→pass | 3,639 | 2,590 | -29% | 1 | 1 | 0% | 707 | 1,547 | +119% | 0 | 0 | — |
case-12 | fail→pass | 6,805 | 3,079 | -55% | 1 | 1 | 0% | 1,269 | 1,552 | +22% | 0 | 0 | — |
case-13 | fail→pass | 4,122 | 1,977 | -52% | 1 | 1 | 0% | 697 | 1,317 | +89% | 0 | 0 | — |
case-14 | pass→pass | 8,389 | 3,536 | -58% | 1 | 1 | 0% | 1,450 | 1,633 | +13% | 0 | 0 | — |
case-15 | pass→pass | 7,141 | 4,156 | -42% | 1 | 1 | 0% | 1,231 | 1,791 | +45% | 0 | 0 | — |
case-16 | pass→pass | 7,690 | 2,282 | -70% | 1 | 1 | 0% | 1,345 | 1,315 | -2% | 0 | 0 | — |
case-17 | fail→pass | 18,788 | 2,647 | -86% | 1 | 1 | 0% | 929 | 1,466 | +58% | 0 | 0 | — |
case-18 | fail→pass | 7,795 | 2,015 | -74% | 1 | 1 | 0% | 1,229 | 1,377 | +12% | 0 | 0 | — |
case-19 | pass→pass | 2,533 | 1,149 | -55% | 1 | 1 | 0% | 410 | 1,226 | +199% | 0 | 0 | — |
case-20 | pass→pass | 8,118 | 3,230 | -60% | 1 | 1 | 0% | 1,401 | 1,507 | +8% | 0 | 0 | — |
case-21 | fail→pass | 3,311 | 1,623 | -51% | 1 | 1 | 0% | 581 | 1,285 | +121% | 0 | 0 | — |
case-22 | pass→pass | 10,070 | 5,681 | -44% | 1 | 1 | 0% | 1,694 | 1,951 | +15% | 0 | 0 | — |
case-23 | pass→pass | 7,972 | 3,552 | -55% | 1 | 1 | 0% | 1,391 | 1,671 | +20% | 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, and 22 counted toward the lift figure. The other 1 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +39 percentage points is the difference between those two pass rates over the 22 comparable cases.
The publisher has shipped newer versions since this run, so these numbers describe v1, not the version currently listed.
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.