Spec Compliance Review logo

Spec Compliance Review

Community
Jason904
spec-compliance-review

This skill should be used after Codex implements a UI change and before visual acceptance review. It audits source code against project-specific visual specs, design tokens, component tree, design-system rules, OpenSpec implementation strategy, UI type, layout paradigm, and asset strategy. It reports violations without redesigning or modifying code.

Overview

PublisherJason904
Repositoryui-skill-lab
Skill namespec-compliance-review
Stars
144
Forks
9
Bundled files
15
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.

  • 15 bundled files

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

  • Open source

    Published by Jason904 on GitHub. Read the source before you install it.

Installation

Install the Spec Compliance Review 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.
    https://github.com/Jason904/ui-skill-lab/tree/main/.codex/skills/spec-compliance-review
  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/Jason904/ui-skill-lab.git /tmp/ui-skill-lab
mkdir -p .claude/skills
cp -r /tmp/ui-skill-lab/.codex/skills/spec-compliance-review .claude/skills/spec-compliance-review
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Spec Compliance Review 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 Spec Compliance Review 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 Spec Compliance Review 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.

Version: 2.0.0

spec-compliance-review

Audit implemented frontend code against the approved visual contract and design system.

This skill verifies that implementation code complies with:

  • 03_visual_spec/
  • 04_visual_spec_review/
  • 05_design_system/
  • OpenSpec design.md and tasks.md
  • source / strictness rules
  • UI Type, Layout Paradigm, and Asset Strategy

It does not modify code and does not perform screenshot-based visual acceptance.

Trigger Conditions

Use this skill when:

  • Codex has produced or modified frontend implementation
  • implementation is ready for code-level review
  • visual acceptance has not yet started
  • the user asks to check whether implementation complies with visual specs
  • the user asks to review UI implementation against tokens, component tree, or design system

Required Inputs

Read implementation code:

text
src/
app/
components/
styles/
package.json
tailwind.config.*
vite.config.*
next.config.*
playwright.config.*

Actual project paths may vary.

Read UI workflow files:

text
ui/03_visual_spec/
  visual-analysis.md
  layout-spec.md
  component-tree.md
  DESIGN.md
  tokens.json
  implementation-risks.md
  human-review-needed.md

ui/04_visual_spec_review/
  spec-review-report.md
  conflict-log.md
  revised-files-needed.md

ui/05_design_system/
  MASTER.md
  pages/target-page.md
  ux-checklist.md
  component-state-spec.md
  responsive-spec.md
  accessibility-spec.md
  implementation-constraints.md

Recommended OpenSpec files:

text
proposal.md
spec.md
design.md
tasks.md
change-summary.md

Preflight

If ui/04_visual_spec_review/spec-review-report.md says Fail, stop and output a blocked compliance report.

Do not audit implementation against failed visual specs.

Source of Truth

  1. PRD / OpenSpec spec.md
  2. reference.png
  3. visual-analysis.md / UI Type Classification
  4. layout-spec.md / Layout Paradigm
  5. implementation-risks.md / Asset Strategy
  6. component-tree.md
  7. tokens.json
  8. 05_design_system/
  9. OpenSpec design.md and tasks.md
  10. Implementation code

Main Workflow

  1. Run preflight.
  2. Read UI Type, Layout Paradigm, Asset Strategy, Rejected Assumptions, Forbidden Layouts, and Prohibited Components.
  3. Scan implementation files for token usage.
  4. Compare component structure against component-tree.md.
  5. Check UI Type / Layout Paradigm / Asset Strategy preservation.
  6. Check design-system states.
  7. Check responsive behavior from code and config.
  8. Check accessibility implementation.
  9. Check OpenSpec design/tasks compliance.
  10. Produce reports under 06_spec_review/.

Hard Rules

  • Do not modify code.
  • Do not modify visual spec files.
  • Do not modify design system files.
  • Do not modify OpenSpec files.
  • Do not perform screenshot visual acceptance.
  • Do not treat passing tests as sufficient.
  • Do not treat internal spec consistency as sufficient.
  • Do not override source / strictness labels.
  • Do not let generic web guidelines override project-specific visual contract.
  • If implementation changes UI Type, Layout Paradigm, or Asset Strategy, mark as error.
  • If implementation adds Prohibited Components or Forbidden Layouts, mark as error.

Output

Write:

text
06_spec_review/
  compliance-report.md
  violation-list.json
  source-traceability-report.md
  forbidden-regression-report.md
  recommended-fixes.md

Supporting Files

Read these references directly:

  • references/compliance-workflow.md
  • references/review-checklists.md
  • references/token-compliance-rules.md
  • references/ui-type-layout-asset-rules.md
  • references/component-state-responsive-a11y-rules.md
  • references/openspec-compliance-rules.md
  • references/violation-schema.md
  • references/severity-rules.md
  • references/external-quality-gates.md
  • references/output-files.md

Examples:

  • examples/compliance-report.example.md
  • examples/violation-list.example.json
  • examples/source-traceability-report.example.md
  • examples/forbidden-regression-report.example.md
  • examples/recommended-fixes.example.md

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 Spec Compliance Review AI skill do?

This skill should be used after Codex implements a UI change and before visual acceptance review. It audits source code against project-specific visual specs, design tokens, component tree, design-system rules, OpenSpec implementation strategy, UI type, layout paradigm, and asset strategy. It reports violations without redesigning or modifying code.

Why use Spec Compliance Review on TypingMind?

Because you install it once and use it with any model. Spec Compliance Review 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 Spec Compliance Review in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Jason904/ui-skill-lab/tree/main/.codex/skills/spec-compliance-review. 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 Spec Compliance Review?

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 Spec Compliance Review?

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

Is the Spec Compliance Review AI skill free?

Yes. It is published on GitHub by Jason904 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 👇