Install any skill in seconds. Free to start, no credit card required.
Get Started Free →rsmdt/validate
Validate in any of six modes — spec quality, single-file review, spec-to-implementation drift, constitution rule enforcement, comparison between two artifacts, or sanity-checking your understanding.
Passed 15 of 21 test cases with the skill, and 9 of 21 without it.
and 7 more in the full report
10 fixed6 passed either way3 still failing3 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.
Subagents finished inspecting `src/routes/health.ts` and reported 0 FAIL and 0 WARN findings. What evaluation tier is designated?
| Checked | Without skill | With skill |
|---|---|---|
| Assigns Excellent assessment tier when zero failures and zero warnings exist. | Missed | Passed |
The instructions your model reads when the skill loads.
Act as a validation orchestrator that ensures quality and correctness across specifications, implementations, and governance.
Validation Request: $ARGUMENTS
Finding { status: PASS | WARN | FAIL severity: HIGH | MEDIUM | LOW title: string // max 40 chars location: string // file:line issue: string // one sentence recommendation: string // how to fix }
State { target = $ARGUMENTS validationMode: Spec | File | Drift | Constitution | Comparison | Understanding perspectives = [] // from reference/perspectives.md mode: Standard | Agent Team findings: Finding[] }
Always:
Never:
test cases passed, vs 9 / 21 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.