Use when you have a written implementation plan to execute in a separate session with review checkpoints
npx skills add TaylorHuston/local-life-manager --skill "validate-spec"
Install specific skill from multi-skill repository
# Description
Validate spec completeness and implementation compliance. Use before approval (--pre) or before completion (--post).
# SKILL.md
name: validate-spec
description: "Validate spec completeness and implementation compliance. Use before approval (--pre) or before completion (--post)."
model: claude-opus-4-5-20251101
allowed-tools: Read, Glob, Grep
/validate-spec
Validate spec quality (pre-implementation) or implementation compliance (post-implementation).
Usage
/validate-spec SPEC-001 # Auto-detect mode based on status
/validate-spec SPEC-001 --pre # Pre-implementation validation
/validate-spec SPEC-001 --post # Post-implementation compliance
Mode Detection
| Spec Status | Default Mode | Purpose |
|---|---|---|
| draft, review | --pre | Validate before approval |
| approved | --pre | Final check before implementation |
| in_progress, complete | --post | Verify implementation matches |
Pre-Implementation Validation (--pre)
1. Structure Completeness
Required sections:
β Summary (present)
β Problem Statement (present)
β Acceptance Scenarios (3 found)
β Agent Context (present)
β Out of Scope (present)
β Dependencies (MISSING)
2. Acceptance Scenario Quality
Scenario 1: "User signs up"
β Has Given/When/Then clauses
β Specific, not vague
Scenario 2: "Invalid credentials"
β Then clause is vague: "shows error"
Suggest: "shows 'Invalid email or password' message"
Scenarios must be:
- Specific: Not "shows error" but "shows error X"
- Testable: Can become automated test
- Complete: Given/When/Then present
3. Agent Context Validation
Files referenced:
β src/lib/auth.ts exists
β src/middleware/session.ts NOT FOUND
4. Success Metrics Measurability
Metric 1: "Page load < 2s"
β Measurable, has threshold
Metric 2: "Good user experience"
β NOT MEASURABLE
Suggest: "User satisfaction > 4/5"
5. Conciseness Check
Word count: 847 words
Guideline: < 500 words
β Consider splitting into multiple specs
6. Open Questions Check
2 open questions found:
1. "Which OAuth providers?"
2. "Session timeout?"
β Resolve before 'approved' status
Pre-Validation Summary
Ready for approval: NO
Fix:
- Add missing Dependencies section
- Refine vague scenario
- Make metrics measurable
- Resolve open questions
Post-Implementation Validation (--post)
1. Acceptance Scenario Coverage
Scenario: "User signs up"
β Found: auth/signup.test.ts:15
Scenario: "Session expires"
β NO TEST FOUND
Coverage: 2/3 scenarios (67%)
2. Success Metrics Verification
Metric: "Page load < 2s"
Result: 1.4s average
β PASS
Metric: "95% coverage"
Result: 97.2%
β PASS
3. Out-of-Scope Violations
Out of scope: "Social login", "2FA"
Scanning...
β No oauth/social code found
β Found "password strength" - potential violation
4. Agent Constraints Compliance
Constraint: "No new dependencies"
β package.json unchanged
Constraint: "Files outside scope"
β src/utils/helpers.ts modified
5. Definition of Done
- [x] Acceptance scenarios tested
- [ ] No console errors β incomplete
Post-Validation Summary
Implementation compliance: PARTIAL
Issues to resolve:
1. Add test for "Session expires"
2. Review password complexity code
3. Fix console warnings
Interactive Fixes
When issues found:
AI: Let's refine Scenario 2...
What should the error message say?
User: "Invalid email or password"
AI: Updated. Now the metrics...
Remove "Good UX" or replace with measurable?
User: Remove it
AI: Done. Re-validating...
## Validation: PASS
Ready to move to 'review' status?
Integration
/spec β /validate-spec --pre β [approval] β /plan β /implement β /validate-spec --post β /complete
# Supported AI Coding Agents
This skill is compatible with the SKILL.md standard and works with all major AI coding agents:
Learn more about the SKILL.md standard and how to use these skills with your preferred AI coding agent.