ghm-harvest_skill
- Python
17
GitHub Stars
1
Bundled Files
2 months ago
Catalog Refreshed
4 months ago
First Indexed
Readme & install
Copy the install command, review bundled files from the catalogue, and read any extended description pulled from the listing source.
Installation
Preview and clipboard use veilstrat where the catalogue uses aiagentskills.
npx veilstrat add skill mattgierhart/prd-driven-context-engineering --skill ghm-harvest- SKILL.md4.4 KB
Overview
This skill extracts durable insights from temporary EPIC files and promotes them into the Source of Truth (SoT) during EPIC Phase E. It runs automatically at EPIC completion or on explicit /ghm-harvest invocation. The skill outputs new SoT entries, moves processed temps into a dated archive, and produces an archive manifest for traceability.
How this skill works
The skill enumerates all files in the temp/ directory and matches them to the current EPIC by name or date. It evaluates each file against a decision matrix to Extract, Archive, or Discard, then formats extracts with generated IDs and inserts them into the appropriate SoT documents. Finally, it moves processed files to archive/YYYY-MM/, writes an archive manifest showing extracted, archived-only, and discarded items, and updates the EPIC Phase E checklist.
When to use it
- At EPIC Phase E (Finish) to lock down lasting knowledge
- When closing an EPIC and you need a complete SoT update
- After a review session with temp notes that may contain durable insights
- When you want an auditable archive manifest of temporary files
- On-demand via /ghm-harvest to capture new discoveries immediately
Best practices
- Run harvest only after review—do not auto-promote unvetted notes
- Use the decision matrix to avoid over- or under-extraction
- Generate IDs with the ghm-id-register to ensure consistent cross-references
- Keep SoT templates current so formatted entries are uniform
- Always produce an archive manifest and verify the temp directory is clean
Example use cases
- Convert finalized API designs discovered in temp/ into SoT.API_CONTRACTS.md with API-XXX IDs
- Extract business rules from meeting notes into SoT.BUSINESS_RULES.md as BR-XXX entries
- Move session notes and contextual files to archive/YYYY-MM/ with a manifest entry for audit
- Discard scratch work after review while documenting reasons in the manifest to maintain traceability
- Trigger on-demand harvest to capture urgent customer feedback found in temp/ into SoT.CUSTOMER_FEEDBACK.md
FAQ
Business rules, user journeys, finalized API designs, and customer evidence are candidates for extraction per the decision matrix.
How are new IDs generated and tracked?
The skill uses ghm-id-register to create consistent IDs (e.g., BR-XXX, UJ-XXX) and inserts them into SoT entries and the archive manifest.
What happens to files that are not extracted?
Useful context files are archived under archive/YYYY-MM/ and scratch work is discarded after review; both actions are recorded in the manifest.
