Ghm Gate Check logo

Ghm Gate Check

Community
mattgierhart
ghm-gate-check

Validates gate criteria before PRD lifecycle advancement by delegating to the readiness scoring pipeline (scripts/readiness.py). Returns a graduated PASS / WARN / BLOCK verdict with top blockers and their causal chain. Triggers before advancing from v0.X to v0.Y or explicit `/ghm-gate-check`.

Overview

Publishermattgierhart
RepositoryPRD-driven-context-engineering
Skill nameghm-gate-check
Stars
179
Forks
11
Bundled files
3
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 3 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by mattgierhart on GitHub. Read the source before you install it.

Installation

Install the Ghm Gate Check AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/mattgierhart/PRD-driven-context-engineering.git /tmp/PRD-driven-context-engineering
mkdir -p .claude/skills
cp -r /tmp/PRD-driven-context-engineering/plugins/prd-ce/skills/ghm-gate-check .claude/skills/ghm-gate-check
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Ghm Gate Check in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Ghm Gate Check on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Ghm Gate Check is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Gate Check

Validate whether the PRD stage is ready to advance to the next version. Delegates to the three-layer readiness scorer — SoT files → EPICs → stage — then surfaces the leverage view (what to fix first, and which EPICs it unblocks).

Workflow Overview

  1. Compute → run scripts/readiness.py run --quiet to refresh status/readiness.json
  2. Read → parse status/readiness.json
  3. Report → PASS / WARN / BLOCK verdict with top blockers and causal links
  4. Recommend → actionable next steps (always highest-leverage first)

Authority

references/gate-criteria.md remains the canonical source of mandatory artifacts per gate. The scorer's GATE_REQUIREMENTS table mirrors it. Do not hand-roll checklists here — the scoring engine is the single source of truth.

Step 1: Compute

Run the orchestrator. It runs SoT → EPIC → stage in dependency order and writes status/readiness.json.

bash
python scripts/readiness.py run --quiet
# exit 0 = all pass, 1 = warn, 2 = block, 3 = error

If the exit code is 3, report a runtime error and stop. If 0/1/2, proceed to Step 2.

Fallback: no scripts available

If scripts/readiness.py is missing or Python is unavailable, fall back to reading status/readiness.json directly. If that's also absent, report: "Readiness not yet computed — install scripts/requirements.txt and run python scripts/readiness.py run."

Step 2: Read

bash
cat status/readiness.json

Extract:

  • summary.current_stage — the gate being evaluated and its score
  • summary.top_blockers — ranked SoT files blocking progress
  • stages.{target} — detailed stage block (dimensions, unmet_criteria, caps)
  • epics.{id} — per-EPIC scores (cite the lowest ones)

Step 3: Report

Use this template. Fill every field from the JSON — do not improvise scores.

markdown
## Gate Check Report: {stage.gate_description}

**Verdict**: [PASS | WARN | BLOCK]
**Stage Score**: {stage.score} / 100  (warn < {threshold_warn}, block < {threshold_block})
**Date**: {now}

### Stage Dimensions

| Dimension | Score | Weight |
|-----------|-------|--------|
| required_ids_present | {score} | {weight} |
| relevant_sot_readiness | {score} | {weight} |
| cross_ref_integrity | {score} | {weight} |
| downstream_epic_readiness | {score or "n/a"} | {weight or "—"} |

### Top Blockers (leverage view)

1. **{file}** (score {score}) — blocks {N} EPICs: {EPIC-XX, …} — impact {impact}
2.
### Unmet Criteria (high severity first)

- [high] {ref}: {reason}
- [medium] {ref}: {reason}

### Recommendation

**If PASS**: Advance to {next_version}. Run `ghm-status-sync` to update the README dashboard.

**If WARN / BLOCK**: Do not advance. Address top blockers in order — fixing the highest-impact SoT file cascades up the graph.

**Next action**: {top_blockers[0] → concrete fix}

Verdict bands

Stage scoreVerdictMeaning
≥ 70PASSSafe to advance
50–69WARNAdvance with documented risk; log in PRD change log
< 50BLOCKCannot advance — per rule 05-lifecycle-gates, update the EPIC and STOP

Step 4: Recommend

Always prioritize by impact = (100 − score) × #EPICs blocked. The top blocker is the single highest-leverage fix; cite its blocking_epics list so the human understands what unblocks.

Quality Gates

  • Stage score cited from JSON, not estimated
  • Top blockers include their consumer EPICs
  • Recommendation is actionable (specific file, specific action)
  • Verdict matches the score band exactly (don't round up)

Anti-Patterns

PatternExampleFix
Ignoring the score"Feels ready; pass"Cite stage.score verbatim
Skipping blockers"Minor stuff, advance anyway"Block if score < 50; warn if < 70
Hand-rolling criteriaRe-checking IDs manuallyTrust the scorer; if wrong, fix GATE_REQUIREMENTS in _readiness/stage.py
Forcing PASSOverriding the verdictNever override; the score is the contract

Boundaries

DO:

  • Delegate computation to readiness.py
  • Cite specific scores, files, and EPICs from the JSON
  • Surface the top_blockers leverage view

DON'T:

  • Modify status/readiness.json directly — it's computed output
  • Create missing artifacts inside this skill (that's the author's job)
  • Override PASS/BLOCK verdicts subjectively

Handoff

After a report:

  • PASS: Trigger ghm-status-sync; the gate advancement updates the README dashboard
  • WARN: Same as PASS but note the risks in the PRD change log
  • BLOCK: Return control to the human. The top_blockers[0] fix is the single most important next action

References

  • references/gate-criteria.md — canonical gate requirements (consumed by scorer)
  • references/examples.md — pass/warn/block report examples
  • .claude/rules/07-readiness-protocol.md — the discipline rule
  • docs/READINESS_PROTOCOL.md — full schema

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Ghm Gate Check AI skill do?

Validates gate criteria before PRD lifecycle advancement by delegating to the readiness scoring pipeline (scripts/readiness.py). Returns a graduated PASS / WARN / BLOCK verdict with top blockers and their causal chain. Triggers before advancing from v0.X to v0.Y or explicit `/ghm-gate-check`.

Why use Ghm Gate Check on TypingMind?

Because you install it once and use it with any model. Ghm Gate Check is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Ghm Gate Check in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/mattgierhart/PRD-driven-context-engineering/tree/main/plugins/prd-ce/skills/ghm-gate-check. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Ghm Gate Check?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Ghm Gate Check?

As many as you like. As long as a model supports skills, you can use Ghm Gate Check with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Ghm Gate Check AI skill free?

Yes. It is published on GitHub by mattgierhart under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇