How do I trigger task-execution-engine?

Trigger it by saying 'start implementation', 'run tasks', or 'resume'.

Feature Pipeline

SkillDocs & knowledge

The task-execution-engine is a skill that executes implementation tasks from design documents using markdown checkboxes. It is used when implementing features from feature-design-assistant output, resuming interrupted work, or batch executing tasks. It lets an agent carry out coding tasks listed in a design document, checking them off and picking up where it left off.

Use Feature Pipeline in Claude, ChatGPT or Ahel Desktop

Free. Sign in, add Feature Pipeline and connect your AI. About a minute.

Claude ChatGPT Ahel Desktop

Also: Claude Code · Cursor · Codex

Then ask your AI: use the Feature Pipeline skill

Details

Instructions available. Your AI can read the instructions. Execution depends on the setup they require.

Account requirements not reviewed. Check the skill instructions before use; ahel provides instructions and does not run this skill.

No other account needed.

Have a design document with implementation tasks written as markdown checkboxes.

Feature PipelineStart free

What your AI can do with it

Execute implementation tasks from design documents using markdown checkboxes
Implement features from feature-design-assistant output
Resume interrupted work
Batch execute tasks
Trigger on 'start implementation', 'run tasks', 'resume'

Getting started

Have a design document with implementation tasks written as markdown checkboxes.
Ensure the design document is available to the agent.
Trigger the skill by saying 'start implementation', 'run tasks', or 'resume'.
The agent will execute the tasks and check them off as they are completed.

What this skill tells your AI

The instructions your AI receives, as published by davila7/claude-code-templates in cli-tool/components/skills/development/task-execution-engine/SKILL.md and read by ahel’s review.

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 endpoint

See 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. CONTINUE

Unattended 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 implemented

Failed task:

- [x] **Create User model** `priority:1` `phase:model` ❌
  - files: src/models/user.py
  - [ ] User model has email field
  - reason: Missing database configuration

Resume / Recovery

To resume interrupted work, simply run again with the same design file:

/feature-pipeline docs/designs/xxx.md

The 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]

Signals

GitHub stars: 32k
Forks: 4k
Last commit: Oct 2026

Questions

What is task-execution-engine?: It is a skill that executes implementation tasks from design documents using markdown checkboxes.
When should I use task-execution-engine?: Use it when implementing features from feature-design-assistant output, resuming interrupted work, or batch executing tasks.
How do I trigger task-execution-engine?: Trigger it by saying 'start implementation', 'run tasks', or 'resume'.
What does task-execution-engine do with the tasks?: It carries out coding tasks listed in a design document, checking them off and picking up where it left off.

Advanced

Item type: skill
Key: task-execution-engine
Source: github.com/davila7/claude-code-templates

github.com/davila7/claude-code-templates

More in Docs & knowledge

handoff
Skill · mattpocock
More in Docs & knowledge canvas-design
Skill · anthropics
More in Docs & knowledge doc-coauthoring
Skill · anthropics
More in Docs & knowledge writing-for-agents
Skill · mattpocock
More in Docs & knowledge spec-driven-development
Skill · addyosmani
More in Docs & knowledge defuddle
Skill · kepano
More in Docs & knowledge