Claude
Chat app · Skill upload
In Claude, open Customize → Skills and use Create skill to upload the ZIP. Skill availability depends on your plan and workspace settings.
Official Claude setup →Community skill · Free instruction package
Execute tasks from a track's implementation plan following TDD workflow
Community instruction package. Read the full workflow below, then choose your app in the setup guide. Package instructions and compatibility claims have not been individually verified; check dependencies and license before use.
CHOOSE YOUR AI APP
Choose your app below for setup instructions. Keep the complete downloaded folder together. Each package may need tools, dependencies or permissions that your app does not provide.
Chat app · Skill upload
In Claude, open Customize → Skills and use Create skill to upload the ZIP. Skill availability depends on your plan and workspace settings.
Official Claude setup →Chat app · Access varies
Where Skills is available, open Plugins → Skills → Create → Upload from your computer. Otherwise, copy the instructions into a chat and add your brief; this does not install a skill or include its supporting files.
Official ChatGPT setup →Agent · Project skills
Extract the complete skill folder into your project’s .agents/skills directory. Ask the agent to use the skill for your task.
.agents/skills/conductor-implement/SKILL.mdOfficial Google Antigravity setup →Code editor · Project skills
Extract the complete folder into .cursor/skills. Check the editor’s skill settings and ask the agent to use it.
.cursor/skills/conductor-implement/SKILL.mdOfficial Cursor setup →Coding agent · Project skills
Extract the complete folder into .claude/skills. Ask Claude to use the named skill, or use its slash command when available.
.claude/skills/conductor-implement/SKILL.mdOfficial Claude Code setup →For text-only workflows, you can also paste the instructions into an AI conversation. Copying text does not enable scripts, connect accounts or grant tool access. App subscriptions may cost extra. Logos identify the products; KuchhBhi is independent and is not endorsed by these companies.
Execute tasks from a track's implementation plan, following the workflow rules defined in conductor/workflow.md.
resources/implementation-playbook.md.Verify Conductor is initialized:
conductor/product.md existsconductor/workflow.md existsconductor/tracks.md exists/conductor:setup firstLoad workflow configuration:
conductor/workflow.mdconductor/tracks/{argument}/plan.mdRead conductor/tracks.md
Parse for incomplete tracks (status [ ] or [~])
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:
Load all relevant context for implementation:
Track documents:
conductor/tracks/{trackId}/spec.md - Requirementsconductor/tracks/{trackId}/plan.md - Task listconductor/tracks/{trackId}/metadata.json - Progress stateProject context:
conductor/product.md - Product understandingconductor/tech-stack.md - Technical constraintsconductor/workflow.md - Process rulesCode style (if exists):
conductor/code_styleguides/{language}.mdUpdate track to in-progress:
In conductor/tracks.md:
[ ] to [~] for this trackIn conductor/tracks/{trackId}/metadata.json:
status: "in_progress"updated timestampFor each incomplete task in plan.md (marked with [ ]):
Parse plan.md to find next incomplete task:
- [ ] Task X.Y: {description}Mark task as in-progress:
[ ] to [~] for current taskRed Phase - Write Failing Test:
Following TDD workflow for Task X.Y...
Step 1: Writing failing test
Green Phase - Implement:
Step 2: Implementing minimal code to pass test
Refactor Phase:
Step 3: Refactoring while keeping tests green
Commit changes (following commit strategy from workflow.md):
git add -A
git commit -m "{commit_prefix}: {task description} ({trackId})"
Update plan.md:
[~] to [x] for completed taskgit add conductor/tracks/{trackId}/plan.md
git commit -m "chore: mark task X.Y complete ({trackId})"
Update metadata.json:
tasks.completedupdated timestampAfter each task, check if phase is complete:
[x]:Run phase verification:
Phase {N} complete. Running verification...
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: {tool} failed with: {error message}
Options:
1. Retry the operation
2. Skip this task and continue
3. Pause implementation
4. Revert current task changes
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
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
When all phases and tasks are complete:
All tasks complete. Running final verification...
In conductor/tracks.md:
[~] to [x] for this trackIn conductor/tracks/{trackId}/metadata.json:
status: "complete"phases.completed to totaltasks.completed to totalupdated timestampIn conductor/tracks/{trackId}/plan.md:
[x] CompleteTrack 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
Track {trackId} is complete.
Cleanup options:
1. Archive - Move to conductor/tracks/_archive/
2. Delete - Remove track directory
3. Keep - Leave as-is
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
Maintain progress in metadata.json throughout:
{
"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)"
]
}
If implementation is paused and resumed:
Load metadata.json for current state
Find current task from current_task field
Check if task is [~] in plan.md
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
The instruction package is free to download. Your AI app, model usage, connected services and third-party assets may have separate costs.
It is a set of instructions for a compatible AI assistant. It does not run by itself, connect accounts or install an MCP server.
Check that the named folder contains SKILL.md directly, not a second nested ZIP folder. Confirm that your editor supports skills and that its current settings allow this location. See the official documentation below.