ALWAYS activate this skill before implementing EVERY feature, plan, or fix.
End-to-end implementation with automatic workflow detection.
Principles: YAGNI, KISS, DRY | Token efficiency | Concise reports
/cook <natural language task OR plan path>
IMPORTANT: If no flag is provided, the skill will use the interactive mode by default for the workflow.
Optional flags to select the workflow mode:
--interactive: Full workflow with user input (default)--fast: Skip research, scout→plan→code--parallel: Multi-agent execution--no-test: Skip testing step--auto: Auto-approve all stepsExample:
/cook "Add user authentication to the app" --fast
/cook path/to/plan.md --auto
| Input Pattern | Detected Mode | Behavior |
|---|---|---|
Path to plan.md or phase-*.md | code | Execute existing plan |
| Contains "fast", "quick" | fast | Skip research, scout→plan→code |
| Contains "trust me", "auto" | auto | Auto-approve all steps |
| Lists 3+ features OR "parallel" | parallel | Multi-agent execution |
| Contains "no test", "skip test" | no-test | Skip testing step |
| Default | interactive | Full workflow with user input |
See references/intent-detection.md for detection logic.
[Intent Detection] → [Research?] → [Review] → [Plan] → [Review] → [Implement] → [Review] → [Test?] → [Review] → [Finalize]
Default (non-auto): Stops at [Review] gates for human approval before each major step.
Auto mode (--auto): Skips human review gates, implements all phases continuously.
Claude Tasks: Utilize all these tools TaskCreate, TaskUpdate, TaskGet and TaskList during implementation step.
| Mode | Research | Testing | Review Gates | Phase Progression |
|---|---|---|---|---|
| interactive | ✓ | ✓ | User approval at each step | One at a time |
| auto | ✓ | ✓ | Auto if score≥9.5 | All at once (no stops) |
| fast | ✗ | ✓ | User approval at each step | One at a time |
| parallel | Optional | ✓ | User approval at each step | Parallel groups |
| no-test | ✓ | ✗ | User approval at each step | One at a time |
| code | ✗ | ✓ | User approval at each step | Per plan |
✓ Step [N]: [Brief status] - [Key metrics]
Human review required at these checkpoints (skipped with --auto):
Always enforced (all modes):
project-manager subagent → run full plan sync-back (all completed tasks/steps across all phase-XX-*.md, not only current phase), then update plan.md status/progressdocs-manager subagent → update ./docs if changes warrantTaskUpdate → mark all Claude Tasks complete after sync-back verificationgit-manager subagent| Phase | Subagent | Requirement |
|---|---|---|
| Research | researcher | Optional in fast/code |
| Scout | ck:scout | Optional in code |
| Plan | planner | Optional in code |
| UI Work | ui-ux-designer | If frontend work |
| Testing | tester, debugger | MUST spawn |
| Review | code-reviewer | MUST spawn |
| Finalize | project-manager, docs-manager, git-manager | MUST spawn all 3 |
CRITICAL ENFORCEMENT:
Task(subagent_type="[type]", prompt="[task]", description="[brief]")references/intent-detection.md - Detection rules and routing logicreferences/workflow-steps.md - Detailed step definitions for all modesreferences/review-cycle.md - Interactive and auto review processesreferences/subagent-patterns.md - Subagent invocation patterns