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]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]Scanned by
NVIDIA SkillSpector
Automated static analysis (no LLM) · v2.12.0 · 2026-11-19
Partial analysis: some checks could not run on this component.
8 observations in 4 categories
- Analysis evasion 4
- Data Flow 2
- Excessive Agency 1
- MCP Least Privilege 1
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. Open one to see the lines it points at.
Incomplete referenced artifact analysis ×4Analysis evasion · SKILL.md:14
| 12 | ```bash |
| 13 | # Get next task |
| 14 | python3 scripts/task_manager.py next --file <design.md> |
| 15 | |
| 16 | # Mark task completed |
Autonomous Decision MakingExcessive Agency · SKILL.md:67
| 65 | |
| 66 | - **NO stopping** for questions |
| 67 | - **NO asking** for clarification |
| 68 | - Make autonomous decisions based on codebase patterns |
| 69 | - If blocked, mark as failed and continue |
Without declared permissions the skill's intent is opaque and cannot be validated.MCP Least Privilege · SKILL.md:1
| 1 | --- |
| 2 | name: task-execution-engine |
| 3 | description: 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 |
Tainted flow: 'updated' from pathlib.Path.read_text (line 309, file read) → pathlib.Path.write_text (file write) ×2Data Flow · scripts/task_manager.py:296
| 294 | |
| 295 | updated = update_task_status(content, args.task, "completed") |
| 296 | file_path.write_text(updated) |
| 297 | |
| 298 | if args.json: |
Learn more about NVIDIA SkillSpector or how components are reviewed.
Agent compatibility
Checked by NVIDIA SkillEvaluator Harness Check · v1.0.1 · 2026-11-18
How each agent reads this skill once it is installed, from the agents' documented loading rules. No agent was run. A note means the agent loads the skill but changes part of its text, or drops it.
Claude Code
loadsCodex
loadsCopilot CLI
loadsOpenCode
loadsHermes
loadsOpenClaw
loads
Every agent loads this skill as written. No notes.
Learn more about NVIDIA SkillEvaluator.