Agent skill
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.
Install this agent skill to your Project
npx add-skill https://github.com/mattgierhart/PRD-driven-context-engineering/tree/main/.claude/skills/ghm-harvest
SKILL.md
Harvest
Extract durable insights from temporary files to Source of Truth during EPIC Phase E (Finish).
Workflow Overview
- Enumerate Temps → List all temp/ files from current EPIC
- Identify SoT-worthy → Determine what should persist
- Format Entries → Convert to proper SoT templates
- Archive → Move temps to archive, update manifest
Core Output Template
| Element | Definition | Evidence |
|---|---|---|
| Temp Files | Files processed | List with paths |
| New SoT Entries | IDs created | BR-XXX, UJ-XXX, etc. |
| Archive Manifest | What was archived | Paths and dates |
| Discarded | What was not kept | Reason for each |
Harvest Decision Matrix
| Content Type | Action | Destination |
|---|---|---|
| Business rule discovered | Extract | SoT/SoT.BUSINESS_RULES.md |
| User flow documented | Extract | SoT/SoT.USER_JOURNEYS.md |
| API design finalized | Extract | SoT/SoT.API_CONTRACTS.md |
| Customer feedback captured | Extract | SoT/SoT.customer_feedback.md |
| Session notes | Archive only | archive/YYYY-MM/ |
| Scratch work | Discard | Delete after review |
Step 1: Enumerate Temp Files
- Read EPIC Execution Plan for temp file references
- List all files in
temp/directory - Match temps to EPIC (by date or naming)
Checklist
- All EPIC-referenced temps identified
- Temp directory scanned
- Files categorized by content type
Step 2: Identify SoT-Worthy Content
For each temp file, evaluate:
| Question | If Yes | If No |
|---|---|---|
| Is this a business rule? | Extract as BR-XXX | Continue |
| Is this a user flow? | Extract as UJ-XXX | Continue |
| Is this an API design? | Extract as API-XXX | Continue |
| Is this customer evidence? | Extract as CFD-XXX | Continue |
| Is this useful context? | Archive | Continue |
| Is this scratch work? | Discard | - |
Checklist
- Each temp file evaluated
- Extract/Archive/Discard decision made
- Decisions documented
Step 3: Format SoT Entries
For each extracted item:
- Generate appropriate ID using
ghm-id-register - Format per SoT template
- Add cross-references
- Insert into correct SoT file
Entry Template
### [ID]: [Title]
**Status**: Active
**Created**: YYYY-MM-DD
**Source**: temp/[filename].md (EPIC-XX)
**Cross-References**: [Related IDs]
[Extracted content, properly formatted]
Checklist
- All extracts have valid IDs
- Formatting matches SoT templates
- Cross-references verified
Step 4: Archive and Cleanup
- Create archive directory:
archive/YYYY-MM/ - Move processed temps to archive
- Generate manifest
- Update EPIC Phase E checklist
Archive Manifest Template
## Archive Manifest: EPIC-XX
**Date**: YYYY-MM-DD
**Archived To**: archive/YYYY-MM/
### Extracted to SoT
| Temp File | New ID | SoT File |
|-----------|--------|----------|
| temp/file.md | BR-XXX | SoT.BUSINESS_RULES.md |
### Archived Only
| Temp File | Reason |
|-----------|--------|
| temp/notes.md | Session context |
### Discarded
| Temp File | Reason |
|-----------|--------|
| temp/scratch.md | No durable value |
Quality Gates
Pass Checklist
- All temps processed (none orphaned)
- Extracted content has valid IDs
- Archive manifest is complete
- EPIC Phase E checklist updated
Testability Check
- SoT entries are findable by ID
- Archive manifest matches actual files
- Temp directory is clean
Anti-Patterns
| Pattern | Example | Fix |
|---|---|---|
| Orphan temps | Temps not in manifest | → Process all files |
| Lost context | Archive without manifest | → Always create manifest |
| Over-extraction | Everything becomes SoT | → Apply decision matrix |
| Under-extraction | Valuable insights lost | → Review before discard |
Boundaries
DO:
- Extract durable insights
- Format per templates
- Create complete manifests
- Clean up temps
DON'T:
- Create new analysis
- Modify conclusions
- Skip the manifest
- Delete without review
Handoff
After harvest completes:
- SoT files updated with new entries
- Temps archived with manifest
- EPIC Phase E marked complete
- Ready to close EPIC
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-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.
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.
Didn't find tool you were looking for?