This skill should be used when implementing tracks, following workflow methodologies, updating plan status, or when the user asks about "TDD workflow", "how to follow workflow", "task execution", "phase completion", or "status updates". Provides patterns for executing work according to defined methodologies.
/plugin marketplace add ShalomObongo/claude-conductor/plugin install shalomobongo-claude-conductor@ShalomObongo/claude-conductorThis skill inherits all available tools. When active, it can use any tool Claude has access to.
references/tdd-patterns.mdThis skill provides patterns for executing Conductor tracks according to defined workflow methodologies, updating progress, and verifying completion.
Workflow execution is the implementation phase where plans become reality. This skill covers:
Pattern: Red → Green → Refactor
For each task requiring code:
Example Task:
### [~] Task: Add user email validation
- [x] Sub-task: Write email validation tests
- [x] Sub-task: Run tests (expect failure)
- [~] Sub-task: Implement validation logic
- [ ] Sub-task: Run tests (expect pass)
- [ ] Sub-task: Refactor for clarity
- [ ] Sub-task: Run tests (verify still passes)
Pattern: Specify → Implement → Verify
For each task:
Pattern: Implement → Test → Review
For each task:
Update plan.md markers as work progresses:
| Transition | When | Example |
|---|---|---|
[ ] → [~] | Starting work | Beginning a task |
[~] → [x] | Completing work | Finishing a task |
[~] → [!] | Encountering blocker | Cannot proceed |
[!] → [~] | Resolving blocker | Resuming work |
Update plan.md immediately when status changes:
Mirror plan.md structure in TodoWrite:
Run at phase boundaries:
Tests:
npm test # JavaScript/TypeScript
pytest # Python
go test ./... # Go
mvn test # Java
Build:
npm run build # JavaScript/TypeScript
python setup.py build # Python
go build # Go
mvn package # Java
Linting:
npm run lint # JavaScript/TypeScript
pylint src/ # Python
golangci-lint run # Go
Type Checking:
npx tsc --noEmit # TypeScript
mypy src/ # Python
After automated checks, present results and ask:
If issues found, halt and await user instructions.
Format: type(scope): description
Types:
feat: New featurefix: Bug fixrefactor: Code restructuringtest: Adding testsdocs: Documentationchore: MaintenanceExamples:
git commit -m "feat(auth): add user registration endpoint"
git commit -m "test(auth): add registration validation tests"
git commit -m "conductor(plan): mark registration task complete"
Per Task:
Per Phase:
Always commit plan.md updates:
git add conductor/tracks/<track_id>/plan.md
git commit -m "conductor(plan): Update <task/phase> status"
If implementation fails:
[!]If tests fail during verification:
If build fails:
For each phase:
Announce Phase Start:
🚀 Starting Phase: <Phase Name>
Tasks in this phase: <N>
Execute Tasks Sequentially:
[~][x]Run Automated Checks:
User Verification:
Update Phase Status:
Before implementing, load all context:
conductor/tracks/<track_id>/spec.md - Requirementsconductor/tracks/<track_id>/plan.md - Implementation planconductor/workflow.md - Methodologyconductor/tech-stack.md - Technical constraintsconductor/product.md - Product contextconductor/code_styleguides/ - Style standardsreferences/tdd-patterns.md - Detailed TDD workflowsreferences/commit-strategies.md - Advanced commit patternsexamples/workflow-execution/ - Real-world execution examplesThis skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.