Task Execution Engine
Execute implementation tasks from design documents using markdown checkboxes. Use when (1) implementing features from feature-design-assistant output, (2) resuming interrupted work, (3) batch executing tasks. Triggers on 'start implementation', 'run tasks', 'resume'.
npx claude-code-templates@latest --skill development/task-execution-engine Scanned by NVIDIA SkillSpector
Automated static analysis (no LLM) · v2.12.0 · 2026-10-17
Partial analysis: some checks could not run on this component.
SkillSpector looks for patterns such as shell commands, credential access, network calls or unpinned dependencies. An observation is something worth reading in the files before you install, not a confirmed vulnerability. Components that run code locally, like hooks, MCP servers and security tooling, naturally show more of them.
- Autonomous Decision MakingExcessive Agency · SKILL.md:67
- Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: file_read, file_write.MCP Least Privilege · SKILL.md:1
- Tainted flow: 'updated' from pathlib.Path.read_text (line 295, file read) → pathlib.Path.write_text (file write)Data Flow · scripts/task_manager.py:296
- Tainted flow: 'updated' from pathlib.Path.read_text (line 309, file read) → pathlib.Path.write_text (file write)Data Flow · scripts/task_manager.py:310
Learn more about NVIDIA SkillSpector.
Content
Feature Pipeline
Execute implementation tasks directly from design documents. Tasks are managed as markdown checkboxes - no separate session files needed.
Quick Reference
# 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>Task Format
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
- [ ] **Create auth API** `priority:3` `phase:api` `deps:Create User model,Implement JWT utils`
- files: src/api/auth.py
- [ ] POST /register endpoint
- [ ] POST /login endpointSee references/task-format.md for full format specification.
Execution Loop
LOOP until no tasks remain:
1. GET next task (task_manager.py next)
2. READ task details (files, criteria)
3. IMPLEMENT the task
4. VERIFY acceptance criteria
5. UPDATE status (task_manager.py done/fail)
6. CONTINUEUnattended Mode Rules
- NO stopping for questions
- NO asking for clarification
- Make autonomous decisions based on codebase patterns
- If blocked, mark as failed and continue
Status Updates
Completed task:
- [x] **Create User model** `priority:1` `phase:model` ✅
- files: src/models/user.py
- [x] User model has email field
- [x] Password hashing implementedFailed task:
- [x] **Create User model** `priority:1` `phase:model` ❌
- files: src/models/user.py
- [ ] User model has email field
- reason: Missing database configurationResume / Recovery
To resume interrupted work, simply run again with the same design file:
/feature-pipeline docs/designs/xxx.mdThe task manager will find the first uncompleted task and continue from there.
Integration
This skill is typically triggered after /feature-analyzer completes:
User: /feature-analyzer implement user auth
Claude: [designs feature, generates task list]
Design saved to docs/designs/2026-01-02-user-auth.md
Ready to start implementation?
User: Yes / 开始实现
Claude: [executes tasks via task-execution-engine]