Qa Commit logo

Qa Commit

Organization
WellApp-ai
qa-commit

Verify implementation against QA Contract (G#N, AC#N), auto-invoke debug on RED

Overview

PublisherWellApp-ai
RepositoryWell
Skill nameqa-commit
Stars
342
Forks
48
Bundled files
Instructions only
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by WellApp-ai on GitHub. Read the source before you install it.

Installation

Install the Qa Commit 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/WellApp-ai/Well.git /tmp/Well
mkdir -p .claude/skills
cp -r /tmp/Well/cursor-rules/skills/qa-commit .claude/skills/qa-commit
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Qa Commit 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 Qa Commit 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 Qa Commit 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.

QA Commit Skill

Verify that the current commit satisfies its assigned QA Contract criteria (G#N Gherkin scenarios and AC#N acceptance criteria). Returns GREEN (pass) or RED (fail, triggers debug).

When to Use

  • After pr-review passes, before git commit
  • During Agent Mode commit-level workflow
  • Manually with "use qa-commit skill"

Input: Commit Context

Before running, identify:

  1. Current commit from Commit Plan
  2. Assigned criteria: "Satisfies: G#X, AC#Y, ..."
  3. Related files being changed

Phase 1: Load QA Contract

Retrieve the assigned criteria for this commit:

markdown
## Commit: [Name]
**Satisfies:** G#1, G#2, AC#1, AC#3

### Criteria to Verify:
- G#1: [Scenario description]
- G#2: [Scenario description]
- AC#1: [Acceptance criteria]
- AC#3: [Acceptance criteria]

Phase 2: Technical Validation

Use Cursor tools for technical checks:

2.1 ReadLints

ReadLints:
  paths: [changed files]

Expect: No errors related to committed functionality

2.2 Type Safety

bash
npm run typecheck

Expect: Exit code 0

2.3 Related Tests (if exist)

bash
npm run test -- --grep "[feature name]"

Expect: All tests pass

Phase 3: Gherkin Verification (Backend - G#N)

For each G#N assigned to this commit:

3.1 Endpoint Existence

Verify the API endpoint exists and is implemented:

SemanticSearch: "Where is [endpoint] implemented?"

3.2 Response Shape

Check response matches expected schema:

Grep: "interface.*Response" in related files

3.3 Error Handling

Verify error cases are handled:

Grep: "throw|catch|error" in handler files

Gherkin Checklist

G#NScenarioStatusNotes
G#1[Name]PASS/FAIL[Details]
G#2[Name]PASS/FAIL[Details]

Phase 4: Acceptance Verification (Frontend - AC#N)

For each AC#N assigned to this commit:

4.1 Component Existence

Verify component is implemented:

Glob: **/*[ComponentName]*.tsx

4.2 Storybook Story (if AC involves visual)

Check Storybook story exists:

Glob: **/*[ComponentName]*.stories.tsx

4.3 Browser MCP Verification (if running)

For interactive acceptance criteria:

Browser MCP:
1. browser_navigate to Storybook URL
2. browser_snapshot to check state
3. browser_click/browser_type to test interaction
4. browser_take_screenshot for evidence

Acceptance Checklist

AC#NCriteriaStatusEvidence
AC#1[Criteria]PASS/FAIL[Screenshot/Notes]
AC#3[Criteria]PASS/FAIL[Screenshot/Notes]

Phase 5: Generate Verification Report

markdown
## Verification Report

**Commit:** [Name]
**Satisfies:** G#1, G#2, AC#1, AC#3

### Technical Validation

| Check | Status |
|-------|--------|
| ReadLints | PASS/FAIL |
| TypeCheck | PASS/FAIL |
| Tests | PASS/FAIL/SKIP |

### Gherkin Scenarios (Backend)

| ID | Scenario | Status | Notes |
|----|----------|--------|-------|
| G#1 | [Name] | PASS/FAIL | [Details] |
| G#2 | [Name] | PASS/FAIL | [Details] |

### Acceptance Criteria (Frontend)

| ID | Criteria | Status | Evidence |
|----|----------|--------|----------|
| AC#1 | [Criteria] | PASS/FAIL | [Link/Notes] |
| AC#3 | [Criteria] | PASS/FAIL | [Link/Notes] |

### Verdict

**[GREEN / RED]**

[If GREEN: All criteria verified, ready to commit]
[If RED: Failed criteria listed, invoking debug skill]

Phase 6: Handle Verdict

GREEN Verdict

markdown
All criteria verified. Proceeding to git commit.

RED Verdict - Auto-Invoke Debug

markdown
**Verification failed. Auto-invoking debug skill.**

### Failed Criteria:
- [G#N or AC#N]: [What failed]
- [G#N or AC#N]: [What failed]

### Context for Debug:
- Error messages: [from ReadLints]
- Expected behavior: [from QA Contract]
- Actual behavior: [observed]

Invoking debug skill with context...

After debug fixes, re-run qa-commit to verify.

Integration with Debug

When verdict is RED:

  1. Automatically invoke debug skill
  2. Pass context:
    • Failed G#N or AC#N
    • Error messages from ReadLints/Shell
    • Browser console/network errors (if applicable)
  3. Debug skill fixes issue
  4. Re-run qa-commit
  5. Repeat until GREEN or user intervention

MCP Tools Used

ToolPurpose
ReadLintsGet lint/type errors
ShellRun tests, typecheck
Browser MCPStorybook verification
SemanticSearchFind implementations
GrepSearch for patterns

Invocation

Invoked by:

  • commit.mdc - After pr-review passes
  • agent.mdc - Part of commit-level workflow

Or manually with "use qa-commit skill".

Frequently asked questions

What does the Qa Commit AI skill do?

Verify implementation against QA Contract (G#N, AC#N), auto-invoke debug on RED

Why use Qa Commit on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/WellApp-ai/Well/tree/main/cursor-rules/skills/qa-commit. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Qa Commit?

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 Qa Commit?

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

Is the Qa Commit AI skill free?

Yes. It is published on GitHub by WellApp-ai 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 👇