Idea Refinement
addyosmani/agent-skills
Guides a conversation that takes a vague idea through divergent and convergent thinking and ends in a markdown one-pager covering scope and assumptions.
Extracts durable insights from temp/ files to SoT during EPIC Phase E.
Install Ghm Harvest
$ npx skills add mattgierhart/PRD-driven-context-engineering --skill ghm-harvest -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install mattgierhart/PRD-driven-context-engineering ghm-harvest --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/mattgierhart/PRD-driven-context-engineering.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/ghm-harvest .claude/skills/ghm-harvest && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "ghm-harvest" agent skill from https://github.com/mattgierhart/PRD-driven-context-engineering/tree/main/.claude/skills/ghm-harvest into .claude/skills/ghm-harvest/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ghm-harvest", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/mattgierhart/PRD-driven-context-engineering/tree/main/.claude/skills/ghm-harvestType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add mattgierhart/PRD-driven-context-engineering --skill ghm-harvest -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install mattgierhart/PRD-driven-context-engineering ghm-harvest --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mattgierhart/PRD-driven-context-engineering.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/ghm-harvest .agents/skills/ghm-harvest && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "ghm-harvest" agent skill from https://github.com/mattgierhart/PRD-driven-context-engineering/tree/main/.claude/skills/ghm-harvest into .agents/skills/ghm-harvest/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ghm-harvest", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add mattgierhart/PRD-driven-context-engineering --skill ghm-harvest -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install mattgierhart/PRD-driven-context-engineering ghm-harvest --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mattgierhart/PRD-driven-context-engineering.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/ghm-harvest .cursor/skills/ghm-harvest && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "ghm-harvest" agent skill from https://github.com/mattgierhart/PRD-driven-context-engineering/tree/main/.claude/skills/ghm-harvest into .cursor/skills/ghm-harvest/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ghm-harvest", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/mattgierhart/PRD-driven-context-engineering.git --path .claude/skills/ghm-harvest--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add mattgierhart/PRD-driven-context-engineering --skill ghm-harvest -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install mattgierhart/PRD-driven-context-engineering ghm-harvest --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mattgierhart/PRD-driven-context-engineering.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/ghm-harvest .gemini/skills/ghm-harvest && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "ghm-harvest" agent skill from https://github.com/mattgierhart/PRD-driven-context-engineering/tree/main/.claude/skills/ghm-harvest into .gemini/skills/ghm-harvest/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ghm-harvest", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install mattgierhart/PRD-driven-context-engineering ghm-harvestInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add mattgierhart/PRD-driven-context-engineering --skill ghm-harvest -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/mattgierhart/PRD-driven-context-engineering.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/ghm-harvest .github/skills/ghm-harvest && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "ghm-harvest" agent skill from https://github.com/mattgierhart/PRD-driven-context-engineering/tree/main/.claude/skills/ghm-harvest into .github/skills/ghm-harvest/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ghm-harvest", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add mattgierhart/PRD-driven-context-engineering --skill ghm-harvest -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install mattgierhart/PRD-driven-context-engineering ghm-harvest --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mattgierhart/PRD-driven-context-engineering.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/ghm-harvest .opencode/skills/ghm-harvest && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "ghm-harvest" agent skill from https://github.com/mattgierhart/PRD-driven-context-engineering/tree/main/.claude/skills/ghm-harvest into .opencode/skills/ghm-harvest/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ghm-harvest", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
ghm-harvest- GitHub stars
- 180
- Token cost
- ~1.1k tokens
- SKILL.md length
- 435 words
- Files
- 4 (incl. references, assets)
- Skills in repo
- 45
- Repo updated
- First seen
- Licence
- MIT
At a glance
Extracts durable insights from temp/ files to SoT during EPIC Phase E.
- Works in 4 steps: Enumerate Temp Files → Identify SoT-Worthy Content → Format SoT Entries → …
- At EPIC completion
- SKILL.md covers Workflow Overview, Core Output Template, Harvest Decision Matrix and Step 1: Enumerate Temp Files, plus 7 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Ghm Harvest is an agent skill from mattgierhart/PRD-driven-context-engineering. 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.
Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including reference files and assets (for example `assets/harvest-log-template.md`, `references/examples.md` and `references/harvest-patterns.md`).
It sits in Agent Workflows. The repository describes itself as: PRD-Led Context Engineering — Memory as Infrastructure. An ontology layer for product teams building products that solve real problems — with AI agents that remember. Gated PRD… The licence is MIT.
When your agent uses it
- At EPIC completion
- Explicit /ghm-harvest invocation
Example prompts
- “Use the ghm-harvest skill to extract durable insights from temp/ files to SoT during EPIC Phase E”
- “/ghm-harvest”
Requirements
- Pre-approved tools (allowed-tools): Read, Write, Edit, Glob, Grep
Workflow steps
4 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 30ed1b0. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves these tools, so the agent can use them without asking each time:
ReadWriteEditGlobGrep
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Ghm Harvest loads about 1.1k tokens when it runs, and up to ~4.4k if it reads all its reference files. Until then it costs about 49 tokens; SKILL.md has 435 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from mattgierhart/PRD-driven-context-engineering at commit 30ed1b0, republished under its MIT licence (© mattgierhart). 435 words, ~1,147 tokens.
Download SKILL.mdSave it as
.claude/skills/ghm-harvest/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.- name
- ghm-harvest
- description
- 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.
- allowed-tools
- Read, Write, Edit, Glob, Grep
- context
- fork
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
Show full SKILL.md (166 more words)Show less
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
© mattgierhart, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 3 other files (references, assets) in .claude/skills/ghm-harvest of mattgierhart/PRD-driven-context-engineering.
- SKILL.md
- assets/harvest-log-template.md
- references/examples.md
- references/harvest-patterns.md
Open the folder on GitHubat commit 30ed1b0
Compare with similar skills
Ghm Harvest next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Ghm Harvest this skillmattgierhart/PRD-driven-context-engineering | 180 | — | ~1.1k | Automated safety check: Pass | MIT | |
| Idea Refinementaddyosmani/agent-skills | 105k | 6 repos | ~2k | Automated safety check: Pass | MIT | |
| Coherence AuditorGoogleChrome/modern-web-guidance-src | 1.1k | — | ~864 | Automated safety check: Pass | Apache-2.0 | |
| Agent Development SpecificationSmartSunruiyang/Agent-development-specification | 150 | — | ~2.5k | Automated safety check: Pass | MIT | |
| Agent RelayAgentWorkforce/relay | 872 | — | ~1.7k | Automated safety check: Pass | Apache-2.0 | |
| CE BrainstormEveryInc/compound-engineering-plugin | 25k | — | ~1.9k | Automated safety check: Pass | MIT |
Similar skills
Coherence Auditor
GoogleChrome/modern-web-guidance-src
Run a document coherence, link integrity, and git repository status audit across repository markdown files using a dedicated subagent.
Agent Development Specification
SmartSunruiyang/Agent-development-specification
Bootstraps the Day-0 agent-governance + documentation scaffold for ANY project on ANY stack.
Agent Relay
AgentWorkforce/relay
A skill your agent uses when you need Codex to coordinate multiple agents through Agent Relay for peer-to-peer messaging, lead/worker handoffs, or shared status tracking across sub-agents and…
CE Brainstorm
EveryInc/compound-engineering-plugin
Turns a vague or ambitious feature idea into a requirements-only plan through dialogue with you, sized to the work, before any code is written.
Extracting Requirements
prime-radiant-inc/iterative-development
Reads human-written spec documents and produces per-epic requirement files with proof obligations plus behavior scenarios with stable IDs, using parallel chunked extraction.
More from mattgierhart/PRD-driven-context-engineering
All 45 skills in this repoGhm Gate Check
mattgierhart/PRD-driven-context-engineering
Validates gate criteria before PRD lifecycle advancement by delegating to the readiness scoring pipeline (scripts/readiness.py).
Ghm Id Register
mattgierhart/PRD-driven-context-engineering
Validates and registers new SoT IDs with cross-reference integrity.
Ghm Sot Builder
mattgierhart/PRD-driven-context-engineering
Creates new Source of Truth (SoT) files when existing templates don't fit your needs.
Prd V01 Problem Framing
mattgierhart/PRD-driven-context-engineering
Transform vague product ideas into evidence-anchored problem statements for PRD v0.1 Spark.
Prd V01 User Value Articulation
mattgierhart/PRD-driven-context-engineering
Transform validated pain points into articulated user value statements for PRD v0.1 Spark.
Prd V02 Competitive Landscape Mapping
mattgierhart/PRD-driven-context-engineering
Map the competitive landscape before positioning your product for PRD v0.2 Market Definition.
Related
Questions about Ghm Harvest
What does Ghm Harvest do?
Extracts durable insights from temp/ files to SoT during EPIC Phase E. Ghm Harvest is an agent skill from mattgierhart/PRD-driven-context-engineering. Extracts durable insights from temp/ files to SoT during EPIC Phase E.
When should I use Ghm Harvest?
Ghm Harvest fits situations like: at EPIC completion; explicit /ghm-harvest invocation.
How do I install Ghm Harvest in Claude Code?
Run `npx skills add mattgierhart/PRD-driven-context-engineering --skill ghm-harvest -a claude-code`. Or copy the skill folder (.claude/skills/ghm-harvest in mattgierhart/PRD-driven-context-engineering) into .claude/skills/ghm-harvest in your project. Claude Code loads it when a task matches its description.
How do I install Ghm Harvest in Codex?
Run `npx skills add mattgierhart/PRD-driven-context-engineering --skill ghm-harvest -a codex`. Or copy the skill folder (.claude/skills/ghm-harvest in mattgierhart/PRD-driven-context-engineering) into .agents/skills/ghm-harvest in your project. Codex loads it when a task matches its description.
Can I use Ghm Harvest in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add mattgierhart/PRD-driven-context-engineering --skill ghm-harvest -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ghm-harvest, .gemini/skills/ghm-harvest, .github/skills/ghm-harvest and .opencode/skills/ghm-harvest in your project.
What does Ghm Harvest need to run?
SKILL.md names no scripts, command-line tools or credentials: Ghm Harvest is instructions for the agent only. Its frontmatter pre-approves these tools: Read, Write, Edit, Glob, Grep.
Does Ghm Harvest access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Ghm Harvest safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Ghm Harvest use?
Ghm Harvest is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Ghm Harvest use?
About 1.1k tokens (SKILL.md is roughly 4.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 3.3k tokens, read only when the agent opens those files.
What are the alternatives to Ghm Harvest?
Skills that share tags, products or a category with Ghm Harvest: Idea Refinement (addyosmani/agent-skills, 105k stars), Coherence Auditor (GoogleChrome/modern-web-guidance-src, 1.1k stars), Agent Development Specification (SmartSunruiyang/Agent-development-specification, 150 stars) and Agent Relay (AgentWorkforce/relay, 872 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Ghm Harvest?
mattgierhart (a GitHub user) maintains it in mattgierhart/PRD-driven-context-engineering, which has 180 GitHub stars. The repository holds 45 skills in this directory. The repository was last updated on August 31, 2026.
Source: mattgierhart/PRD-driven-context-engineering on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.