Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Review Vellum Assistant code changes for correctness, repo-specific quality rules, security risks, and missing validation. Use when reviewing diffs, preparing a PR, finishing implementation work, or when the user asks for a code review, quality pass, or pre-merge check in this repository.
| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | -19% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -37% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -29% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -9% | 0% |
| case-09 | ✗→✓ | ▲ Improved | -30% | 0% |
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:
markdown## Findings - [severity] `path`: issue, impact, and concrete fix. ## Open Questions - Any uncertainty that affects correctness or review confidence. ## Verification Gaps - Tests or checks that still need to run.
If no issues are found, say that clearly and still mention residual risk or unrun checks.
Other measured skills in the registry, with their headline benchmark lift.