Agent skill
cook-fast
[Implementation] Fast implementation - skip research, minimal planning
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/cook-fast
SKILL.md
[IMPORTANT] Use
TaskCreateto 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.
Prerequisites: MUST READ .claude/skills/shared/understand-code-first-protocol.md before executing.
docs/project-reference/domain-entities-reference.md— Domain entity catalog, relationships, cross-service sync (read when task involves business entities/models)docs/test-specs/— Test specifications by module (read existing TCs; generate/update test specs via/tdd-specafter implementation)
Process Discipline: MUST READ
.claude/skills/shared/rationalization-prevention-protocol.md— counter "too simple for a plan" and "I'll refactor later" evasions.
Process Discipline: MUST READ
.claude/skills/shared/red-flag-stop-conditions-protocol.md— STOP after 3+ failed attempts or when fix requires modifying 5+ files for a "simple" change.
Skill Variant: Variant of
/cook— fast implementation skipping research with minimal planning.
Quick Summary
Goal: Implement features quickly with minimal research and streamlined planning.
Workflow:
- Scout — Quick codebase scan for patterns
- Plan — Lightweight implementation plan
- Implement — Execute with code-simplifier review
Key Rules:
- Skip deep research; rely on codebase patterns
- Still requires user approval before implementing
- Break work into todo tasks; add final self-review task
Frontend/UI Context (if applicable)
When this task involves frontend or UI changes, MUST READ .claude/skills/shared/ui-system-context.md and the following docs:
- Component patterns:
docs/project-reference/frontend-patterns-reference.md - Styling/BEM guide:
docs/project-reference/scss-styling-guide.md - Design system tokens:
docs/project-reference/design-system/README.md
Be skeptical. Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence percentages (Idea should be more than 80%).
Start working on these tasks immediately with minimal planning: $ARGUMENTS
Mode: FAST - Skip research, minimal planning, trust your knowledge.
Workflow
-
Quick Planning (skip research phase)
- Analyze task requirements directly
- Create minimal todo list with
TaskCreate - NO researcher subagents, NO scout commands
- For non-trivial tasks: write brief analysis to
.ai/workspace/analysis/{task-name}.analysis.mdbefore implementing.
-
Rapid Implementation
- Use
/codedirectly on tasks - Skip multi-step planning documents
- Focus on working code over documentation
- Use
-
Quick Validation
- Run type-check and compile
- Manual spot-check over full test suite
- Skip code-reviewer subagent
-
Commit (optional)
- Ask user if ready to commit via
AskUserQuestion - If yes, use
/commit
- Ask user if ready to commit via
When to Use
- Simple features with clear requirements
- Bug fixes with known solutions
- Refactoring tasks
- When user says "just do it"
Trade-offs
| Aspect | Fast Mode | Full Mode |
|---|---|---|
| Research | Skipped | Multiple agents |
| Planning | Minimal | Full plan docs |
| Testing | Quick check | Full test suite |
| Review | Skipped | Code-reviewer |
| Speed | ~2x faster | Thorough |
IMPORTANT Task Planning Notes (MUST FOLLOW)
- Always plan and break work into many small todo tasks
- Always add a final review todo task to verify work quality and identify fixes/enhancements
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?