spec-validator
Skill100 starsChanged 7 months agoMITView on GitHub
Validate consistency and traceability across the specification chain (PRD → FRD → Gherkin). Detect gaps, orphans, contradictions, and missing coverage. Use at Phase 2 exit (before human gate), Phase 3 entry (before e2e generation), Phase 4 entry (before Gherkin generation), on resume (re-validate specs haven't drifted), or after human edits to any spec file (specs/prd.md, specs/frd-*.md, specs/features/*.feature).
Files
Spec Validator
Validate that every requirement traces from PRD → FRD → Gherkin with no gaps or orphans.
Steps
- Parse PRD — Extract all user stories and requirements from
specs/prd.md - Parse FRDs — For each
specs/frd-*.md, extract all functional requirements - Trace PRD → FRD — Verify every PRD requirement maps to at least one FRD
- Parse Gherkin — For each
specs/features/*.feature, extract all scenarios - Trace FRD → Gherkin — Verify every FRD requirement has at least one Gherkin scenario
- Detect orphans — Find Gherkin scenarios that don't trace back to any FRD requirement
- Detect contradictions — Flag requirements that conflict across FRDs
- Report — Generate a coverage summary
Output Format
Coverage: <percentage>% of requirements have Gherkin scenarios
Verdict: PASS | FAIL
Gaps (requirements without scenarios):
- <FRD file>: <requirement description>
Orphans (scenarios without requirements):
- <feature file>: <scenario name>
Contradictions:
- <FRD file A> vs <FRD file B>: <description>Other versions3 projects use a version of this.
Word for word · 1
- crgarcia12/Liliput★ 4100% same
Edited · 0
None found.
Wrote their own version · 2
- fernandopetry/keelson★ 5same name
- willianbs/skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository47 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .github/copilot-instructions.mdCopilot instructions
- adrSkill
- api-extractorSkill
- architecture-mapperSkill
- aspireSkill
- audit-logSkill
- azure-deploymentSkill
- bug-fixSkill
- build-checkSkill
- cloud-native-assessmentSkill
- cloud-native-plannerSkill
- codebase-scannerSkill
- commit-protocolSkill
- contract-generationSkill
- data-model-extractorSkill
- ddd-modelingSkill
- dependency-inventorySkill
- deploy-diagnosticsSkill
- e2e-generationSkill
- error-handlingSkill
- extension-plannerSkill
- find-skillsSkill
- frd-generatorSkill
- gherkin-generationSkill
- human-gateSkill
- implementationSkill
- modernization-assessmentSkill
- modernization-plannerSkill
- performance-assessmentSkill
- playwright-cliSkill
- prd-generatorSkill
- research-best-practicesSkill
- resumeSkill
- rewrite-assessmentSkill
- rewrite-plannerSkill
- security-assessmentSkill
- security-plannerSkill
- skill-creatorSkill
- skill-discoverySkill
- spec-refinementSkill
- state-managementSkill
- tech-stack-resolutionSkill
- test-discoverySkill
- test-generationSkill
- test-runnerSkill
- ui-ux-designSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.