Install any skill in seconds. Free to start, no credit card required.
Get Started Free →florianbruniaux/plan-pipeline-validate
2-layer plan validation: instant structural checks + trigger-based specialist agents. Auto-fixes issues using ADRs and first principles. Every issue must be resolved before execution.
Passed 11 of 16 test cases with the skill, and 7 of 16 without it.
and 9 more in the full report
9 fixed6 passed either way4 still failing3 broke
Tokens, turns and time describe resource use, not a dollar price.
This benchmark measured an earlier version of the skill.
A newer attempt on gemini-3.6-flash on 10/14/2026 did not produce a publishable comparison (not comparable). The snapshot above is the previously measured run.
One of 9 test cases the skill fixed. Same model, same prompt, with and without the skill.
An update plan introduces three new GraphQL resolvers and adds an external npm package dependency for data caching. Which agent handles this review and under what model tier?
| Checked | Without skill | With skill |
|---|---|---|
| The response assigns performance-reviewer to inspect the query and dependency changes. | Missed | Passed |
| The response specifies Sonnet as the model tier for the performance reviewer. | Missed | Passed |
The instructions your model reads when the skill loads.
Independently validate the plan produced by /plan-pipeline:start. No code is written. Run /clear after this command before running /plan-pipeline:execute.
Validation is separate from planning by design: validators that didn't write the plan are not anchored to its assumptions.
A committed plan file must exist at docs/plans/plan-{name}.md. If multiple plans exist, list them and ask the user which to validate.
Run immediately, no agents required. Check the plan document for:
Format & Completeness
Dependency Chain
File Existence
ADR Consistency
/plan-pipeline:startdocs/adr/CLAUDE.md Compliance
Test Coverage
test cases passed, vs 7 / 16 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.