Implement logo

Implement

Organization
MadAppGang
implement

Execute tasks from track plan with TDD workflow and git commit integration

Overview

PublisherMadAppGang
Repositoryclaude-code
Skill nameimplement
Stars
281
Forks
26
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 MadAppGang on GitHub. Read the source before you install it.

Installation

Install the Implement 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/MadAppGang/claude-code.git /tmp/claude-code
mkdir -p .claude/skills
cp -r /tmp/claude-code/plugins/conductor/skills/implement .claude/skills/implement
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Implement 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 Implement 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 Implement 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.

plugin: conductor updated: 2026-01-20

<status_progression>
  Task status MUST follow this progression:
  - [ ] (pending) - Not started
  - [~] (in_progress) - Currently working
  - [x] (complete) - Finished
  - [!] (blocked) - Blocked by issue

  Only ONE task can be [~] at a time.
</status_progression>

<tdd_workflow>
  Follow Test-Driven Development for each task:

  **Red Phase:**
  1. Create test file for the feature
  2. Write tests defining expected behavior
  3. Run tests - confirm they FAIL
  4. Do NOT proceed until tests fail

  **Green Phase:**
  1. Write MINIMUM code to pass tests
  2. Run tests - confirm they PASS
  3. No refactoring yet

  **Refactor Phase:**
  1. Improve code clarity and performance
  2. Remove duplication
  3. Run tests - confirm they still PASS
</tdd_workflow>

<git_commit_protocol>
  After completing each task:
  1. Stage relevant changes
  2. Commit with proper format:
     ```
     <type>(<scope>): <description>

     - Detail 1
     - Detail 2

     Task: {phase}.{task}
     ```
  3. Attach git note with task summary:
     ```bash
     git notes add -m "Task: {phase}.{task} - {title}

     Summary: {what was accomplished}

     Files Changed:
     - {file1}: {description}

     Why: {business reason}" $(git log -1 --format="%H")
     ```
  4. Update metadata.json with commit SHA
</git_commit_protocol>

<commit_types>
  | Type | Use For |
  |------|---------|
  | feat | New feature |
  | fix | Bug fix |
  | docs | Documentation |
  | style | Formatting |
  | refactor | Code restructuring |
  | test | Adding tests |
  | chore | Maintenance |
  | perf | Performance |
</commit_types>

<workflow_adherence>
  ALWAYS follow procedures in conductor/workflow.md:
  - TDD Red/Green/Refactor cycle
  - Quality gates (>80% coverage, linting)
  - Document deviations in tech-stack.md
  - Phase Completion Protocol at phase end
</workflow_adherence>

<human_approval_gates>
  Pause and ask for user approval:
  - Before starting each new phase
  - When encountering blockers
  - Before marking phase complete
  - During Phase Completion Protocol Step 5
</human_approval_gates>

</critical_constraints>

<core_principles> Focus on exactly one task. Complete it fully before moving to next. No partial implementations.

<principle name="Test First" priority="critical">
  Write failing tests BEFORE implementation.
  This is the Red phase of TDD.
  Never skip this step.
</principle>

<principle name="Continuous Status Updates" priority="critical">
  Update plan.md status immediately when:
  - Starting a task ([~])
  - Completing a task ([x])
  - Encountering a blocker ([!] with note)
</principle>

<principle name="Traceable Commits" priority="high">
  Every commit links to track/task.
  Commit messages follow type convention.
  Git notes provide audit trail.
</principle>

</core_principles>

<phase number="2" name="Task Selection">
  <step>Find first pending task (or ask user)</step>
  <step>Mark task as [~] in_progress in plan.md</step>
  <step>TaskUpdate to match</step>
  <step>Read task requirements and context</step>
</phase>

<phase number="3" name="TDD Implementation">
  <step>**Red Phase:** Write failing tests for the task</step>
  <step>Run tests, confirm they FAIL</step>
  <step>**Green Phase:** Write minimum code to pass</step>
  <step>Run tests, confirm they PASS</step>
  <step>**Refactor Phase:** Improve code quality</step>
  <step>Run tests, confirm they still PASS</step>
  <step>Verify coverage meets >80% requirement</step>
</phase>

<phase number="4" name="Quality & Commit">
  <step>Run all quality checks (lint, typecheck, test)</step>
  <step>If checks fail, fix before proceeding</step>
  <step>Stage relevant file changes</step>
  <step>Create commit with proper type and message</step>
  <step>Add git note with task summary</step>
  <step>Mark task as [x] complete in plan.md</step>
  <step>Commit plan.md update separately</step>
  <step>Update metadata.json with commit info</step>
  <step>TaskUpdate to match</step>
</phase>

<phase number="5" name="Phase Transition Check">
  <step>Check if phase is complete (all tasks [x])</step>
  <step>If NOT complete, continue to next pending task</step>
  <step>If phase IS complete, execute Phase Completion Protocol</step>
</phase>

<phase_completion_protocol> Execute when all tasks in a phase are [x]:

1. **Announce Protocol Start**
   Inform user: "Phase {N} complete. Starting verification protocol."

2. **Ensure Test Coverage**
   ```bash
   # Find files changed in this phase
   PREV_SHA=$(grep -o '\[checkpoint: [a-f0-9]*\]' plan.md | tail -1 | grep -o '[a-f0-9]*')
   git diff --name-only $PREV_SHA HEAD
   # Verify tests exist for each code file
   # Create missing tests if needed
   ```

3. **Execute Automated Tests**
   ```bash
   echo "Running: CI=true npm test"
   CI=true npm test
   # If fail: attempt fix (max 2 times), then ask user
   ```

4. **Propose Manual Verification Plan**
   Provide step-by-step manual testing instructions.
   Include specific commands and expected outcomes.

5. **Await User Confirmation**
   Ask: "Does this meet your expectations? Confirm with 'yes' or provide feedback."
   **PAUSE** - do not proceed without explicit yes.

6. **Create Checkpoint Commit**
   ```bash
   git add -A
   git commit -m "conductor(checkpoint): End of Phase {N} - {Phase Name}"
   ```

7. **Attach Verification Report**
   ```bash
   git notes add -m "Phase Verification Report
   Phase: {N} - {Phase Name}
   Automated Tests: PASSED
   Manual Verification: User confirmed
   Coverage: {X}%" $(git log -1 --format="%H")
   ```

8. **Update Plan with Checkpoint**
   Add `[checkpoint: abc1234]` to phase heading in plan.md.

9. **Commit Plan Update**
   ```bash
   git commit -m "conductor(plan): Mark phase '{Phase Name}' complete"
   ```

10. **Announce Completion**
    Inform user phase is complete with checkpoint and verification report.

</phase_completion_protocol>

<commit_message_format>

<type>(<scope>): <description>

- Detail 1
- Detail 2

Task: {phase}.{task} ({task_title})
Example:
feat(auth): Implement password hashing

- Added bcrypt dependency
- Created hashPassword utility function
- Added unit tests for hashing

Task: 2.1 (Implement password hashing)

</commit_message_format>

<git_notes_format>

Task: {phase}.{task} - {task_title}

Summary: {what was accomplished}

Files Changed:
- {file1}: {description}
- {file2}: {description}

Why: {business reason for this change}

</git_notes_format>

<blocker_handling> When encountering a blocker: 1. Mark task as [!] blocked in plan.md 2. Add note describing blocker: markdown - [!] 2.3 Implement OAuth login > BLOCKED: Waiting for API credentials from team lead 3. Ask user for guidance 4. Either resolve or skip to different task 5. Track blocker in metadata.json </blocker_handling>

<deviation_protocol> If implementation differs from tech-stack.md: 1. STOP implementation 2. Update tech-stack.md with new design 3. Add dated note explaining the change: markdown ## Changes Log - 2026-01-05: Changed from SQLite to PostgreSQL for better concurrency 4. Resume implementation </deviation_protocol>

  **Red Phase:**
  5. Create test file: tests/user-table.test.ts
  6. Write tests for user table schema
  7. Run tests - confirm they FAIL

  **Green Phase:**
  8. Create migration file
  9. Define user table schema
  10. Run tests - confirm they PASS

  **Refactor Phase:**
  11. Clean up migration code
  12. Run tests - confirm still PASS

  **Commit:**
  13. Run quality checks (all pass)
  14. Commit: "feat(db): Create user table schema"
  15. Add git note with task summary
  16. Commit plan.md update
  17. Mark 1.1 as [x] in plan.md
  18. Update metadata.json
  19. Move to next task 1.2
</correct_approach>
  **Phase Completion Protocol:**
  4. Check test coverage for all Phase 1 files
  5. Run: CI=true npm test (PASSED)
  6. Present manual verification steps to user
  7. Ask: "Does this meet your expectations?"
  8. User confirms: "yes"
  9. Create checkpoint commit
  10. Add verification report via git notes
  11. Update plan.md with [checkpoint: abc1234]
  12. Commit plan update
  13. Announce: "Phase 1 checkpoint created. Proceeding to Phase 2."
  14. Ask approval before starting Phase 2
</correct_approach>

Track: feature_auth_20260105 Phase: 2/4 - Core Authentication Task: 2.1/2.5 - Implement password hashing

[==========-----] 40% complete

Recent:

  • 1.1 Create user table schema (abc1234)
  • 1.2 Add migration scripts (def5678)
  • 1.3 Set up database connection (ghi9012)
  • 2.1 Implement password hashing (just completed)

Next:

  • 2.2 Create login endpoint
  </progress_display>

  <task_completion_template>
## Task Complete

**Track:** {track_id}
**Task:** {phase}.{task} - {task_title}
**Commit:** {short_sha}
**Type:** {feat/fix/refactor/etc.}

**TDD Cycle:**
- Red: Tests written and failing
- Green: Implementation complete, tests passing
- Refactor: Code cleaned up

**Quality Checks:**
- Lint: PASS
- Tests: PASS ({N} tests, {X}% coverage)
- TypeCheck: PASS

**Next Task:** {next_task_id} - {next_task_title}

Continue to next task? [Yes/No]
  </task_completion_template>

  <phase_completion_template>
## Phase Complete

**Track:** {track_id}
**Phase:** {N} - {phase_name}
**Checkpoint:** {checkpoint_sha}

**Verification Report:**
- Automated Tests: PASSED
- Coverage: {X}%
- Manual Verification: User confirmed

**Git Note:** Attached to checkpoint commit

**Next Phase:** {N+1} - {next_phase_name}

Proceed to next phase? [Yes/No]
  </phase_completion_template>
</formatting>

Frequently asked questions

What does the Implement AI skill do?

Execute tasks from track plan with TDD workflow and git commit integration

Why use Implement on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/MadAppGang/claude-code/tree/main/plugins/conductor/skills/implement. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Implement?

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 Implement?

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

Is the Implement AI skill free?

Yes. It is published on GitHub by MadAppGang 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 👇