Verify

Community

hegemonart

verify

Stage 5 of 5 orchestrator that spawns design-auditor, design-verifier, and design-integration-checker in sequence, interprets pass/gap result, and drives the gap-response loop (inline fix, save-and-exit, or accept-as-is). Use when implementation is complete and ready for final pre-ship verification. Activates for requests involving checking finished UI against the design system, running a pre-ship review, or final verification.

Overview

Publisher	hegemonart
Repository	`get-design-done`
Skill name	`verify`
Stars	3
Forks	1
Bundled files	1
License	MIT
Links	Skill source Repository

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.
1 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by hegemonart on GitHub. Read the source before you install it.

Installation

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

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.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/hegemonart/get-design-done/tree/main/scripts/skill-templates/verify
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.

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/hegemonart/get-design-done.git /tmp/get-design-done
mkdir -p .claude/skills
cp -r /tmp/get-design-done/scripts/skill-templates/verify .claude/skills/verify

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Verify 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 Verify 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 Verify 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.

Get Design Done - Verify

Stage 5 of 5 in the get-design-done pipeline. Thin orchestrator. Verification intelligence lives in three agents: design-auditor, design-verifier, and design-integration-checker.

Full procedure detail: ./verify-procedure.md.

State Integration

mcp__gdd_state__transition_stage with to: "verify"; on gate failure surface error.context.blockers to the user without advancing.
mcp__gdd_state__get -> snapshot state. Read state.must_haves (verification checklist - each M-XX flips to pass or fail).
Quality-gate gate (D-08, D-09) - inspect state.quality_gate?.run?.status:
- "fail" -> refuse to advance; call mcp__gdd_state__add_blocker with the iteration count + commands_run; exit. Do NOT open the stage.
- "timeout" / "skipped" -> print one-line warning naming the status + commands_run, continue normally (signals, not walls).
- "pass" / null -> continue silently. Full decision tree: ./verify-procedure.md §Quality-gate gate.
Resume detection - if state.position.status==in_progress and .design/DESIGN-VERIFICATION.md exists: RESUME to Step 2 (gap-response loop). Otherwise call mcp__gdd_state__update_progress with task_progress: "0/3", status: "in_progress" and proceed.
Missing STATE.md is a hard block - verify is never the entry point; upstream stages own bootstrap.

Flipping a must-have status: mcp__gdd_state__add_must_have with the SAME id updates in-place (no separate update tool). Detail: ./verify-procedure.md §Flipping a must-have status.

Connection probes

Run preview / storybook / chromatic probes at stage entry, then issue ONE batched mcp__gdd_state__probe_connections call with all results. Full probe specs (project detection, dev-server probe, CLI presence, token check) and downstream loops (storybook a11y, chromatic visual delta) are in ./verify-procedure.md §Connection Probes.

Prerequisites + flags

DESIGN-PLAN.md prerequisite (normal mode): missing -> block with "Verify requires DESIGN-PLAN.md. Run {{command_prefix}}plan first, or use --post-handoff if starting from a Claude Design handoff bundle."
Post-handoff mode (--post-handoff OR STATE.md status: handoff-sourced): skip the DESIGN-PLAN.md check; pass post_handoff: true + handoff_path to design-verifier; DESIGN-VERIFICATION.md gains a ## Handoff Faithfulness section. Detail: ./verify-procedure.md §Post-Handoff Mode.
Flags: --auto -> auto_mode=true (no interactive prompts; on gaps: save-and-exit); --post-handoff -> see above.
Parallelism decision: read .design/config.json + reference/parallelism-rules.md. Default serial (verifier depends on auditor output). Record via mcp__gdd_state__set_status before spawning. Detail: ./verify-procedure.md §Parallelism Decision.

Step 1 - Spawn Auditor + Verifier + Integration Checker

Initialize the fix-loop iteration counter to 0. Each full checker is preceded by a cheap Haiku gate that may return {spawn: false} to short-circuit (lazy-gate pattern from Plan 10.1-04 / D-21); skipped agents append lazy_skipped: true to .design/telemetry/costs.jsonl.

1a. design-auditor (retrospective 7-pillar audit) -> .design/DESIGN-AUDIT.md. Wait for ## AUDIT COMPLETE, then mcp__gdd_state__update_progress task_progress: "1/3".

1b-gate -> 1b. design-verifier (5-phase verification, reads auditor output) -> .design/DESIGN-VERIFICATION.md. Wait for ## VERIFICATION COMPLETE, then task_progress: "2/3".

1c-gate -> 1c. design-integration-checker (per-decision wiring check on each D-XX in DESIGN-CONTEXT.md) -> reports Connected / Orphaned / Missing counts. Wait for ## INTEGRATION CHECK COMPLETE, then task_progress: "3/3".

Full agent prompts, lazy-gate decision logic, and telemetry-row shapes: ./verify-procedure.md §Step 1.

Step 2 - Interpret Result

Consolidate gaps from both sources: verifier ## GAPS FOUND (G-NN entries) and integration-checker (Orphaned -> MAJOR, Missing -> BLOCKER).

No gaps (PASS) -> for each M-XX in the entry snapshot: add_must_have with status: "pass". Proceed to Stage exit.
Gaps + auto_mode=true -> preserve DESIGN-VERIFICATION.md, set_status: "blocked", add_blocker with the gap count, exit with the failure message.
Gaps + auto_mode=false -> proceed to Step 3.

Detail: ./verify-procedure.md §Step 2.

Step 3 - Gap Response Loop

Present the gap summary + 3-option menu ([1] Fix now, [2] Save and exit, [3] Accept as-is).

[1] Fix now -> if iteration counter >= 3 fall back to [2]; otherwise increment counter, spawn design-fixer for BLOCKER+MAJOR gaps (each fix is an atomic fix(design-gap-GNN): commit), wait for ## FIX COMPLETE, then re-spawn design-verifier with re_verify=true and loop to Step 2.
[2] Save and exit -> preserve DESIGN-VERIFICATION.md, set_status: "blocked", add_blocker, checkpoint, exit.
[3] Accept as-is -> flip each unmet M-XX to status: "fail", add_blocker with "accepted with N unresolved gaps", proceed to Stage exit.

Full prompts + branching: ./verify-procedure.md §Step 3.

Stage exit

mcp__gdd_state__update_progress -> task_progress: "<verified>/<total>", status: "verify_complete".
mcp__gdd_state__set_status -> "pipeline_complete" (all pass, no gaps) or "verify_failed_requires_loop" (gaps remain).
mcp__gdd_state__checkpoint - stamps last_checkpoint and appends verify_completed_at. No direct STATE.md writes.

After Completion

Print the === Verify complete === summary (status, gap counts, agent paths, next-step suggestion) from ./verify-procedure.md §After Completion.

Rationalizations - Thought to Reality

The reasons an agent gives to skip or weaken verification, and what each one lets through:

Thought	Reality
"The implementation looks right, I can skip the verifier spawn."	Skipping verification ships unchecked must-haves; the 5-phase verifier exists to catch what "looks right" misses.
"The integration-checker is redundant with the auditor."	The auditor scores quality; the integration-checker proves each D-XX is actually wired - an orphaned decision passes the audit but fails the product.
"These gaps are minor, I'll accept-as-is without a blocker."	Accept-as-is without recording the unresolved gaps erases the trail; the next cycle re-discovers them from scratch.
"The quality gate timed out, I'll treat that as a pass."	Timeout is a signal, not a pass - masking it lets a genuinely failing gate slip through to ship.
"I'll loop the fixer a fourth time to clear the last gap."	The 3-iteration cap exists because a gap surviving three fixes is a design problem, not a code problem - save and escalate.
"Post-handoff bundles don't need the faithfulness check."	Skipping the handoff-faithfulness section means a divergence from the source design ships unflagged.

VERIFY COMPLETE

Bundled files

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

verify-procedure.md24 KB

Frequently asked questions

What does the Verify AI skill do?

Why use Verify on TypingMind?

Because you install it once and use it with any model. Verify 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 Verify in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/hegemonart/get-design-done/tree/main/scripts/skill-templates/verify. 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 Verify?

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 Verify?

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

Is the Verify AI skill free?

Yes. It is published on GitHub by hegemonart 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

Pptx Author

NousResearch

OrganizationPopular

Build PowerPoint decks headless with python-pptx.

Pokemon Player

Play Pokemon via headless emulator + RAM reads.

Docx

Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files) or Word templates (.dotx files). Triggers include: any mention of 'Word doc', 'word document',…

Openclaw Docker E2e Authoring

openclaw

OrganizationPopular

Author OpenClaw Docker E2E and live provider Docker lanes.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Get Design Done - Verify

State Integration

Connection probes

Prerequisites + flags

Step 1 - Spawn Auditor + Verifier + Integration Checker

Step 2 - Interpret Result

Step 3 - Gap Response Loop

Stage exit

After Completion

Rationalizations - Thought to Reality

VERIFY COMPLETE

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now