conductor-implement
Execute tasks from a track's implementation plan following TDD workflow
About this skill
The `conductor-implement` skill empowers an AI agent to systematically execute tasks derived from an implementation plan, strictly adhering to a Test-Driven Development (TDD) workflow and predefined workflow rules (e.g., from `conductor/workflow.md`). It provides the agent with structured guidance, best practices, and checklists necessary for navigating complex development tasks, ensuring clarity of goals, validation of outcomes, and delivery of actionable steps for successful implementation.
Best use case
An AI agent needs to implement a software feature or task described in a project's implementation plan, and the development process mandates a TDD approach with specific workflow rules to follow.
Execute tasks from a track's implementation plan following TDD workflow
The AI agent will provide a structured plan, actionable steps, or a detailed breakdown for implementing a given task, ensuring TDD principles are applied, best practices are considered, and validation steps are incorporated. It clarifies requirements, applies relevant development standards, and guides towards a verified outcome.
Practical example
Example input
Implement the 'User Profile Update' feature. Refer to the `user_profile_plan.md` document for the implementation details and ensure all work follows our standard TDD workflow outlined in `conductor/workflow.md`.
Example output
Understood. To implement the 'User Profile Update' feature following TDD and your workflow, I will proceed as follows: 1. **Clarify Goals & Constraints**: Review `user_profile_plan.md` to identify specific update fields, validation rules, and any integration points. Confirm security requirements. 2. **Outline Test Cases (Red)**: Define failing unit and integration tests for updating each profile field (e.g., name, email, password) and for error handling (e.g., invalid input, unauthorized access). 3. **Implement Minimal Code (Green)**: Write the minimal code required to make the defined tests pass for each profile field. 4. **Refactor & Extend Tests**: Refactor the code for clarity and efficiency. Add additional tests for edge cases, performance, and security vulnerabilities. 5. **Validate Outcomes**: Verify that all tests pass, the feature behaves as expected according to `user_profile_plan.md`, and adheres to TDD principles. Provide a summary of the implementation and verification steps. Which specific aspect of 'User Profile Update' would you like to start with, or would you like me to begin by outlining initial failing tests for basic field updates?
When to use this skill
- Working on implement track tasks or workflows
- Needing guidance, best practices, or checklists for implement track
When not to use this skill
- The task is unrelated to implement track
- You need a different domain or tool outside this scope
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/conductor-implement/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How conductor-implement Compares
| Feature / Agent | conductor-implement | Standard Approach |
|---|---|---|
| Platform Support | Claude | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | medium | N/A |
Frequently Asked Questions
What does this skill do?
Execute tasks from a track's implementation plan following TDD workflow
Which AI agents support this skill?
This skill is designed for Claude.
How difficult is it to install?
The installation complexity is rated as medium. You can find the installation instructions above.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
Best AI Skills for Claude
Explore the best AI skills for Claude and Claude Code across coding, research, workflow automation, documentation, and agent operations.
AI Agents for Coding
Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.
ChatGPT vs Claude for Agent Skills
Compare ChatGPT and Claude for AI agent skills across coding, writing, research, and reusable workflow execution.
SKILL.md Source
# Implement Track
Execute tasks from a track's implementation plan, following the workflow rules defined in `conductor/workflow.md`.
## Use this skill when
- Working on implement track tasks or workflows
- Needing guidance, best practices, or checklists for implement track
## Do not use this skill when
- The task is unrelated to implement track
- You need a different domain or tool outside this scope
## Instructions
- Clarify goals, constraints, and required inputs.
- Apply relevant best practices and validate outcomes.
- Provide actionable steps and verification.
- If detailed examples are required, open `resources/implementation-playbook.md`.
## Pre-flight Checks
1. Verify Conductor is initialized:
- Check `conductor/product.md` exists
- Check `conductor/workflow.md` exists
- Check `conductor/tracks.md` exists
- If missing: Display error and suggest running `/conductor:setup` first
2. Load workflow configuration:
- Read `conductor/workflow.md`
- Parse TDD strictness level
- Parse commit strategy
- Parse verification checkpoint rules
## Track Selection
### If argument provided:
- Validate track exists: `conductor/tracks/{argument}/plan.md`
- If not found: Search for partial matches, suggest corrections
### If no argument:
1. Read `conductor/tracks.md`
2. Parse for incomplete tracks (status `[ ]` or `[~]`)
3. Display selection menu:
```
Select a track to implement:
In Progress:
1. [~] auth_20250115 - User Authentication (Phase 2, Task 3)
Pending:
2. [ ] nav-fix_20250114 - Navigation Bug Fix
3. [ ] dashboard_20250113 - Dashboard Feature
Enter number or track ID:
```
## Context Loading
Load all relevant context for implementation:
1. Track documents:
- `conductor/tracks/{trackId}/spec.md` - Requirements
- `conductor/tracks/{trackId}/plan.md` - Task list
- `conductor/tracks/{trackId}/metadata.json` - Progress state
2. Project context:
- `conductor/product.md` - Product understanding
- `conductor/tech-stack.md` - Technical constraints
- `conductor/workflow.md` - Process rules
3. Code style (if exists):
- `conductor/code_styleguides/{language}.md`
## Track Status Update
Update track to in-progress:
1. In `conductor/tracks.md`:
- Change `[ ]` to `[~]` for this track
2. In `conductor/tracks/{trackId}/metadata.json`:
- Set `status: "in_progress"`
- Update `updated` timestamp
## Task Execution Loop
For each incomplete task in plan.md (marked with `[ ]`):
### 1. Task Identification
Parse plan.md to find next incomplete task:
- Look for lines matching `- [ ] Task X.Y: {description}`
- Track current phase from structure
### 2. Task Start
Mark task as in-progress:
- Update plan.md: Change `[ ]` to `[~]` for current task
- Announce: "Starting Task X.Y: {description}"
### 3. TDD Workflow (if TDD enabled in workflow.md)
**Red Phase - Write Failing Test:**
```
Following TDD workflow for Task X.Y...
Step 1: Writing failing test
```
- Create test file if needed
- Write test(s) for the task functionality
- Run tests to confirm they fail
- If tests pass unexpectedly: HALT, investigate
**Green Phase - Implement:**
```
Step 2: Implementing minimal code to pass test
```
- Write minimum code to make test pass
- Run tests to confirm they pass
- If tests fail: Debug and fix
**Refactor Phase:**
```
Step 3: Refactoring while keeping tests green
```
- Clean up code
- Run tests to ensure still passing
### 4. Non-TDD Workflow (if TDD not strict)
- Implement the task directly
- Run any existing tests
- Manual verification as needed
### 5. Task Completion
**Commit changes** (following commit strategy from workflow.md):
```bash
git add -A
git commit -m "{commit_prefix}: {task description} ({trackId})"
```
**Update plan.md:**
- Change `[~]` to `[x]` for completed task
- Commit plan update:
```bash
git add conductor/tracks/{trackId}/plan.md
git commit -m "chore: mark task X.Y complete ({trackId})"
```
**Update metadata.json:**
- Increment `tasks.completed`
- Update `updated` timestamp
### 6. Phase Completion Check
After each task, check if phase is complete:
- Parse plan.md for phase structure
- If all tasks in current phase are `[x]`:
**Run phase verification:**
```
Phase {N} complete. Running verification...
```
- Execute verification tasks listed for the phase
- Run full test suite: `npm test` / `pytest` / etc.
**Report and wait for approval:**
```
Phase {N} Verification Results:
- All phase tasks: Complete
- Tests: {passing/failing}
- Verification: {pass/fail}
Approve to continue to Phase {N+1}?
1. Yes, continue
2. No, there are issues to fix
3. Pause implementation
```
**CRITICAL: Wait for explicit user approval before proceeding to next phase.**
## Error Handling During Implementation
### On Tool Failure
```
ERROR: {tool} failed with: {error message}
Options:
1. Retry the operation
2. Skip this task and continue
3. Pause implementation
4. Revert current task changes
```
- HALT and present options
- Do NOT automatically continue
### On Test Failure
```
TESTS FAILING after Task X.Y
Failed tests:
- {test name}: {failure reason}
Options:
1. Attempt to fix
2. Rollback task changes
3. Pause for manual intervention
```
### On Git Failure
```
GIT ERROR: {error message}
This may indicate:
- Uncommitted changes from outside Conductor
- Merge conflicts
- Permission issues
Options:
1. Show git status
2. Attempt to resolve
3. Pause for manual intervention
```
## Track Completion
When all phases and tasks are complete:
### 1. Final Verification
```
All tasks complete. Running final verification...
```
- Run full test suite
- Check all acceptance criteria from spec.md
- Generate verification report
### 2. Update Track Status
In `conductor/tracks.md`:
- Change `[~]` to `[x]` for this track
- Update the "Updated" column
In `conductor/tracks/{trackId}/metadata.json`:
- Set `status: "complete"`
- Set `phases.completed` to total
- Set `tasks.completed` to total
- Update `updated` timestamp
In `conductor/tracks/{trackId}/plan.md`:
- Update header status to `[x] Complete`
### 3. Documentation Sync Offer
```
Track complete! Would you like to sync documentation?
This will update:
- conductor/product.md (if new features added)
- conductor/tech-stack.md (if new dependencies added)
- README.md (if applicable)
1. Yes, sync documentation
2. No, skip
```
### 4. Cleanup Offer
```
Track {trackId} is complete.
Cleanup options:
1. Archive - Move to conductor/tracks/_archive/
2. Delete - Remove track directory
3. Keep - Leave as-is
```
### 5. Completion Summary
```
Track Complete: {track title}
Summary:
- Track ID: {trackId}
- Phases completed: {N}/{N}
- Tasks completed: {M}/{M}
- Commits created: {count}
- Tests: All passing
Next steps:
- Run /conductor:status to see project progress
- Run /conductor:new-track for next feature
```
## Progress Tracking
Maintain progress in `metadata.json` throughout:
```json
{
"id": "auth_20250115",
"title": "User Authentication",
"type": "feature",
"status": "in_progress",
"created": "2025-01-15T10:00:00Z",
"updated": "2025-01-15T14:30:00Z",
"current_phase": 2,
"current_task": "2.3",
"phases": {
"total": 3,
"completed": 1
},
"tasks": {
"total": 12,
"completed": 7
},
"commits": [
"abc1234: feat: add login form (auth_20250115)",
"def5678: feat: add password validation (auth_20250115)"
]
}
```
## Resumption
If implementation is paused and resumed:
1. Load `metadata.json` for current state
2. Find current task from `current_task` field
3. Check if task is `[~]` in plan.md
4. Ask user:
```
Resuming track: {title}
Last task in progress: Task {X.Y}: {description}
Options:
1. Continue from where we left off
2. Restart current task
3. Show progress summary first
```
## Critical Rules
1. **NEVER skip verification checkpoints** - Always wait for user approval between phases
2. **STOP on any failure** - Do not attempt to continue past errors
3. **Follow workflow.md strictly** - TDD, commit strategy, and verification rules are mandatory
4. **Keep plan.md updated** - Task status must reflect actual progress
5. **Commit frequently** - Each task completion should be committed
6. **Track all commits** - Record commit hashes in metadata.json for potential revertRelated Skills
nerdzao-elite
Senior Elite Software Engineer (15+) and Senior Product Designer. Full workflow with planning, architecture, TDD, clean code, and pixel-perfect UX validation.
nerdzao-elite-gemini-high
Modo Elite Coder + UX Pixel-Perfect otimizado especificamente para Gemini 3.1 Pro High. Workflow completo com foco em qualidade máxima e eficiência de tokens.
multi-platform-apps-multi-platform
Build and deploy the same feature consistently across web, mobile, and desktop platforms using API-first architecture and parallel implementation strategies.
monorepo-architect
Expert in monorepo architecture, build systems, and dependency management at scale. Masters Nx, Turborepo, Bazel, and Lerna for efficient multi-project development. Use PROACTIVELY for monorepo setup,
minecraft-bukkit-pro
Master Minecraft server plugin development with Bukkit, Spigot, and Paper APIs.
memory-safety-patterns
Cross-language patterns for memory-safe programming including RAII, ownership, smart pointers, and resource management.
macos-spm-app-packaging
Scaffold, build, sign, and package SwiftPM macOS apps without Xcode projects.
legacy-modernizer
Refactor legacy codebases, migrate outdated frameworks, and implement gradual modernization. Handles technical debt, dependency updates, and backward compatibility.
i18n-localization
Internationalization and localization patterns. Detecting hardcoded strings, managing translations, locale files, RTL support.
framework-migration-deps-upgrade
You are a dependency management expert specializing in safe, incremental upgrades of project dependencies. Plan and execute dependency updates with minimal risk, proper testing, and clear migration pa
fp-refactor
Comprehensive guide for refactoring imperative TypeScript code to fp-ts functional patterns
dotnet-backend-patterns
Master C#/.NET patterns for building production-grade APIs, MCP servers, and enterprise backends with modern best practices (2024/2025).