cook-auto

[IMPORTANT] Use TaskCreate to break ALL work into small tasks BEFORE starting — including tasks for each file read. This prevents context loss from long files. For simple tasks, AI MUST ask user whether to skip.

Understand Code First — Search codebase for 3+ similar implementations BEFORE writing any code. Read existing files, validate assumptions with grep evidence, map dependencies via graph trace. Never invent new patterns when existing ones work. MUST READ .claude/skills/shared/understand-code-first-protocol.md for full protocol and checklists.

• docs/project-reference/domain-entities-reference.md — Domain entity catalog, relationships, cross-service sync (read when task involves business entities/models) (content auto-injected by hook — check for [Injected: ...] header before reading)
• docs/test-specs/ — Test specifications by module (read existing TCs; generate/update test specs via /tdd-spec after implementation)

Plan Quality — Every plan phase MUST include ## Test Specifications section with TC-{FEAT}-{NNN} format. Verify TC satisfaction per phase before marking complete. Plans must include story_points and effort in frontmatter. MUST READ .claude/skills/shared/plan-quality-protocol.md for full protocol and checklists.

Rationalization Prevention — AI consistently skips steps via: "too simple for a plan", "I'll test after", "already searched", "code is self-explanatory". These are EVASIONS — not valid reasons. Plan anyway. Test first. Show grep evidence with file:line. Never combine steps to "save time". MUST READ .claude/skills/shared/rationalization-prevention-protocol.md for full protocol and checklists.

Red Flag STOP Conditions — STOP current approach when: 3+ fix attempts on same issue (root cause not identified), each fix reveals NEW problems (upstream root cause), fix requires 5+ files for "simple" change (wrong abstraction layer), using "should work"/"probably fixed" without verification evidence. After 3 failed attempts, report all outcomes and ask user before attempt #4. MUST READ .claude/skills/shared/red-flag-stop-conditions-protocol.md for full protocol and checklists.

Skill Variant: Variant of /cook — autonomous execution without user confirmation.

Quick Summary

Goal: Implement features autonomously without stopping for user confirmation at each step.

Workflow:

1. Analyze — Understand task requirements from arguments
2. Plan & Execute — Create plan and implement directly
3. Verify — Run tests and review changes

Key Rules:

• Autonomous mode: proceed without asking for confirmation
• Still follow all coding standards and patterns
• Break work into todo tasks; add final self-review task

Ultrathink to plan & start working on these tasks follow the Orchestration Protocol, Core Responsibilities, Subagents Team and Development Rules:

Be skeptical. Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence percentages (Idea should be more than 80%).

$ARGUMENTS

IMPORTANT: Analyze the list of skills at .claude/skills/* and intelligently activate the skills that are needed for the task during the process. Ensure token efficiency while maintaining high quality.

Workflow:

1. Trigger slash command /plan <detailed-instruction-prompt> to create an implementation plan based on the given tasks.
   • External Memory: Ensure /plan writes analysis to .ai/workspace/analysis/. Re-read before /code.
2. Trigger slash command /code <plan> to implement the plan.
3. Finally use AskUserQuestion tool to ask user if he wants to commit to git repository, if yes trigger /commit slash command to create a commit.

Closing Reminders

• MUST break work into small todo tasks using TaskCreate BEFORE starting
• MUST search codebase for 3+ similar patterns before creating new code
• MUST cite file:line evidence for every claim (confidence >80% to act)
• MUST add a final review todo task to verify work quality
• MUST validate decisions with user via AskUserQuestion — never auto-decide MANDATORY IMPORTANT MUST READ the following files before starting:
• MUST READ .claude/skills/shared/understand-code-first-protocol.md before starting
• MUST READ .claude/skills/shared/plan-quality-protocol.md before starting
• MUST READ .claude/skills/shared/rationalization-prevention-protocol.md before starting
• MUST READ .claude/skills/shared/red-flag-stop-conditions-protocol.md before starting