
Turns your feature design documents into executable task lists using markdown checkboxes, then grinds through them autonomously without stopping to ask questions. The task manager script tracks what's done, what failed, and what's next, so you can resume work after interruptions. Works in unattended mode by making decisions based on existing codebase patterns rather than waiting for clarification. Designed to pair with feature design tools where you generate a task list upfront, then let this execute the whole thing in one session. The checkbox format is clean, everything lives in the design doc itself, and you get clear status markers for completed and failed tasks.
$ npx -y skills add davila7/claude-code-templates --skill task-execution-engine --agent claude-codeInstalls into .claude/skills of the current project.
Execute implementation tasks directly from design documents. Tasks are managed as markdown checkboxes - no separate session files needed.
# Get next task
python3 scripts/task_manager.py next --file <design.md>
# Mark task completed
python3 scripts/task_manager.py done --file <design.md> --task "Task Title"
# Mark task failed
python3 scripts/task_manager.py fail --file <design.md> --task "Task Title" --reason "..."
# Show status
python3 scripts/task_manager.py status --file <design.md>
Tasks are written as markdown checkboxes in the design document:
## Implementation Tasks
- [ ] **Create User model** `priority:1` `phase:model`
- files: src/models/user.py, tests/models/test_user.py
- [ ] User model has email and password_hash fields
- [ ] Email validation implemented
- [ ] Password hashing uses bcrypt
- [ ] **Implement JWT utils** `priority:2` `phase:model`
- files: src/utils/jwt.py
- [ ] generate_token() creates valid JWT
- [ ] verify_token() validates JWT
Sponsors