Agent skill
ghm-gate-check
Validates gate criteria before PRD lifecycle advancement. Triggers before advancing from v0.X to v0.Y or explicit `/ghm-gate-check` invocation. Outputs pass/block summary with missing artifacts list.
Install this agent skill to your Project
npx add-skill https://github.com/mattgierhart/PRD-driven-context-engineering/tree/main/.claude/skills/ghm-gate-check
SKILL.md
Gate Check
Validate all gate criteria are met before advancing the PRD lifecycle version.
Workflow Overview
- Load Gate Criteria → Read target gate requirements from PRD.md
- Verify Evidence → Check required artifacts exist with valid IDs
- Assess Readiness → Evaluate handoff requirements
- Report → Pass/Block with specific gaps
Core Output Template
| Element | Definition | Evidence |
|---|---|---|
| Target Gate | Version being validated | v0.3 → v0.4 |
| Status | Pass or Block | Clear determination |
| Missing Artifacts | What's not complete | Specific list with IDs |
| Recommendation | Action to take | Proceed / Address gaps |
Gate Reference
| Gate | Focus | Key Artifacts |
|---|---|---|
| v0.1 → v0.2 | Problem validated | CFD-XXX evidence |
| v0.2 → v0.3 | Market defined | Segment definitions |
| v0.3 → v0.4 | Commercial viable | BR-XXX, pricing |
| v0.4 → v0.5 | Journeys mapped | UJ-XXX complete |
| v0.5 → v0.6 | Risks addressed | Risk register |
| v0.6 → v0.7 | Architecture set | API-XXX, schemas |
| v0.7 → v0.8 | Build complete | Tests passing |
| v0.8 → v0.9 | Deployed | Live environment |
| v0.9 → v1.0 | Launched | Metrics tracking |
Step 1: Load Gate Criteria
- Read PRD.md gate section for target version
- Extract all required criteria
- Identify artifact types needed (BR, UJ, API, CFD)
Checklist
- Target gate identified
- All criteria extracted
- Required artifact types listed
Step 2: Verify Evidence
For each required criterion:
- Check artifact exists in SoT/
- Verify artifact status is not "Draft"
- Confirm cross-references are valid
- Check for required CFD-XXX evidence
Evidence Matrix
| Criterion Type | Verification |
|---|---|
| Business Rule | BR-XXX exists, status Active |
| User Journey | UJ-XXX exists, all steps defined |
| API Contract | API-XXX exists, endpoints specified |
| Customer Evidence | CFD-XXX linked to BR-XXX |
Checklist
- All required BR-XXX verified
- All required UJ-XXX verified
- All required API-XXX verified
- Evidence chain (CFD → BR) validated
Step 3: Assess Handoff Readiness
Check downstream requirements:
- Next agent has context needed
- No open blockers in current EPIC
- Documentation is current
Checklist
- EPIC Session State section has no blockers
- README.md is synchronized
- Handoff documentation exists
Step 4: Generate Report
## Gate Check Report: v0.X → v0.Y
**Status**: [PASS / BLOCK]
**Date**: YYYY-MM-DD
### Criteria Assessment
| Criterion | Status | Evidence |
|-----------|--------|----------|
| [Criterion 1] | ✅/❌ | [ID or gap] |
| [Criterion 2] | ✅/❌ | [ID or gap] |
### Missing Artifacts
- [ ] [Specific gap with required action]
### Recommendation
[Proceed to v0.Y / Address [N] gaps before advancing]
Quality Gates
Pass Checklist
- All criteria evaluated (none skipped)
- Evidence is traceable to IDs
- Recommendation is actionable
Testability Check
- Report can be validated against PRD.md criteria
- Missing artifacts are specific and findable
Anti-Patterns
| Pattern | Example | Fix |
|---|---|---|
| Skipping criteria | "Probably fine" | → Verify each explicitly |
| Vague gaps | "Needs more work" | → Cite specific missing ID |
| Override blocks | Advancing despite fails | → Address gaps first |
Boundaries
DO:
- Validate against documented criteria
- Identify specific gaps
- Provide actionable recommendations
DON'T:
- Create missing artifacts (just report)
- Override gate blocks
- Make subjective quality judgments
Handoff
After gate check:
- If PASS: Advance PRD version, trigger
ghm-status-sync - If BLOCK: Return to current stage, address gaps
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
prd-v05-technical-stack-selection
Make technology decisions for every product capability by discovering existing assets, evaluating vendor-aligned options, and categorizing as Reuse/Extend/Build/Buy/Integrate/Research during PRD v0.5 Red Team Review. Handles both greenfield and brownfield contexts. Triggers on "tech stack", "build or buy?", "what technologies?", "technical decisions", "what do we reuse?", "existing stack", "vendor constraint", "IBM-first", "what tools do we need?", "evaluate solutions", "select tech stack". Consumes FEA- (features), SCR- (screens), RISK- (constraints). Outputs TECH- entries with decisions, rationale, and cross-references. Feeds v0.6 Architecture Design.
ghm-harvest
Extracts durable insights from temp/ files to SoT during EPIC Phase E. Triggers at EPIC completion or explicit `/ghm-harvest` invocation. Outputs new SoT entries and archive manifest.
ghm-status-sync
Synchronizes README.md Command Center with current project state. Triggers on gate changes, EPIC status changes, or explicit `/ghm-status-sync` invocation. Outputs updated README.md dashboard with current lifecycle stage, blockers, and metrics.
prd-v02-product-type-classification
Classify product approach into one of six types (Clone, Unbundle, Undercut, Slice, Wrapper, Innovation) based on competitive landscape. Triggers on PRD v0.2 work after competitive analysis, or when user asks "what type of product should we build?", "should we clone or innovate?", "is this a fast-follow opportunity?", "how should we position against competitors?", "clone vs undercut", "unbundle vs slice", or requests help choosing product strategy. Outputs BR- entries for product type classification and inherited GTM constraints.
prd-v03-outcome-definition
Define measurable success metrics (KPIs) tied to product type during PRD v0.3 Commercial Model. Triggers on requests to define success metrics, set KPI targets, determine what to measure, establish go/no-go thresholds, or when user asks "how do we measure success?", "what metrics matter?", "what's our target?", "how do we know if this works?", "define KPIs", "success criteria". Consumes Product Type Classification (BR-) from v0.2. Outputs KPI- entries with thresholds, evidence sources, and downstream gate linkages.
prd-v05-risk-discovery-interview
Surface risks through guided questioning, helping users consider pivots, constraints, and prioritization during PRD v0.5 Red Team Review. Triggers on requests to identify risks, stress-test the idea, perform red team review, or when user asks "what could go wrong?", "identify risks", "red team", "risk assessment", "challenge assumptions", "stress test the idea". Consumes all prior IDs (CFD-, BR-, FEA-, PER-, UJ-, SCR-) as interview context. Outputs RISK- entries with owner decisions and mitigations. Feeds v0.5 Technical Stack Selection.
Didn't find tool you were looking for?