Test-Driven Development workflow for task implementation. Use when implementing tasks that require the Red-Green-Refactor cycle, quality gates, commit guidelines, or phase verification protocols.
/plugin marketplace add vinothpandian/v-marketplace/plugin install claude-conductor@v-marketplaceThis skill inherits all available tools. When active, it can use any tool Claude has access to.
This skill provides the Test-Driven Development methodology used by Conductor for task implementation.
plan.mdtech-stack.md before implementationCI=true for watch-mode tools (tests, linters) to ensure single execution.All tasks follow a strict lifecycle:
Choose the next available task from plan.md in sequential order.
Before beginning work, edit plan.md and change the task from [ ] to [~].
Run coverage reports using the project's chosen tools. Target: >80% coverage for new code.
Example commands by language:
pytest --cov=app --cov-report=htmlnpm test -- --coveragego test -cover ./...If implementation differs from tech stack:
tech-stack.md with new designfeat(ui): Create basic HTML structure for calculator).git log -1 --format="%H").git notes add -m "<note content>" <commit_hash>plan.md, find the completed task, update status from [~] to [x], and append the first 7 characters of the commit hash.plan.md.plan.md file.conductor(plan): Mark task '<task_name>' as completeTrigger: Execute immediately after completing a task that also concludes a phase in plan.md.
Inform the user that the phase is complete and verification has begun.
git diff --name-only <previous_checkpoint_sha> HEAD to list files modified during this phase..json, .md, .yaml), verify a corresponding test file exists. If missing, create one.CI=true npm test").Generate step-by-step instructions for the user to manually verify the phase.
Frontend example:
1. Start the development server: `npm run dev`
2. Open browser to: `http://localhost:3000`
3. Confirm you see: The new user profile page with name and email
Backend example:
1. Ensure the server is running
2. Execute: `curl -X POST http://localhost:8080/api/v1/users -d '{"name": "test"}'`
3. Confirm response: JSON with status `201 Created`
Ask: "Does this meet your expectations? Please confirm with yes or provide feedback." PAUSE and await response. Do not proceed without explicit confirmation.
Stage all changes and commit: conductor(checkpoint): Checkpoint end of Phase X
Draft and attach a detailed verification report including automated test command, manual steps, and user confirmation.
plan.md to append [checkpoint: <sha>] to the phase heading.conductor(plan): Mark phase '<PHASE NAME>' as completeInform the user that the phase is complete with verification report attached as git note.
Before marking any task complete, verify:
<type>(<scope>): <description>
[optional body]
[optional footer]
feat: New featurefix: Bug fixdocs: Documentation onlystyle: Formatting, missing semicolons, etc.refactor: Code change that neither fixes a bug nor adds a featuretest: Adding missing testschore: Maintenance tasksgit commit -m "feat(auth): Add remember me functionality"
git commit -m "fix(posts): Correct excerpt generation for short posts"
git commit -m "test(comments): Add tests for emoji reaction limits"
A task is complete when:
plan.mdThis 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 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 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.