Install any skill in seconds. Free to start, no credit card required.
Get Started Free →vellum-ai/vellum-change-review
Review Vellum Assistant code changes for correctness, repo-specific quality rules, security risks, and missing validation.
Passed 21 of 22 test cases with the skill, and 11 of 22 without it.
and 10 more in the full report
10 fixed11 passed either way1 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.
Review a pull request that only renames a private local variable in `packages/cli/src/utils.ts` without introducing any regressions, boundary breaks, or copy issues. What should the review output state?
| Checked | Without skill | With skill |
|---|---|---|
| Explicitly states that no issues were found. | Passed | Passed |
| Mentions residual risk or unrun verification checks. | Missed | Passed |
The instructions your model reads when the skill loads.
Prioritize bugs, behavioral regressions, security risks, migration gaps, broken package boundaries, and missing tests. Findings come before summaries. Avoid cosmetic feedback unless it affects correctness, maintainability, or user experience.
assistant, gateway, clients, cli, skills, packages, or meta.assistant must not import from gateway by relative path.gateway must not import from assistant by relative path.assistant and skills must not import each other directly.meta.meta/feature-flags/feature-flag-registry.json.bun test path/to/test.ts; never suggest broad bun test.bunx tsc --noEmit when type-level risk is broad.Use this structure:
## Findings
test cases passed, vs 11 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.