An autonomous agent that manages the entire lifecycle of implementing a feature from research to verification.
Install
mkdir -p .claude/skills/cook && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/17528" && unzip -o skill.zip -d .claude/skills/cook && rm skill.zipInstalls to .claude/skills/cook
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
High-autonomy "chef" for implementing new features from scratch. Handles code scanning, architectural research, technical specification, and full-stack implementation with a focus on "clean code" and project idiomatics. Use when the user says "cook this feature", "implement X", or "build Y".Key capabilities
- →Scan codebase for existing patterns and components
- →Analyze data flow and existing feature structures
- →Draft concise technical specifications
- →Implement features with atomic commits
- →Follow project's established style and idioms
- →Verify implementation with builds and tests
How it works
This skill transforms high-level feature requests into implementations through a structured workflow. It involves research, technical specification, idiomatic coding, and verification.
Inputs & outputs
When to use cook
- →Implement new feature
- →Perform architectural research
- →Build UI component
- →Full-stack implementation
About this skill
The "Cook" Workflow
This skill transforms a high-level feature request into a production-ready implementation through a structured "kitchen" process.
Phase 1: Preparation (Research & Scan)
- Scan: Use
grep_searchandglobto find existing patterns, related components, and architectural precedents. - Analyze: Understand how data flows and how existing features are structured in this specific codebase.
- Ingredients: Identify the "ingredients" needed (new classes, UI components, API endpoints, or database changes).
Phase 2: The Recipe (Clear Spec)
- Draft Spec: Create a concise technical plan.
- Check-in: Present the plan to the user.
- Clarify: If anything is ambiguous (UI details, edge cases), ASK for confirmation before touching the stove.
Phase 3: Cooking (Implementation)
- Atomic Commits: (Mental or actual if requested) Build the feature in logical, self-contained steps.
- Idiomatic Code: Follow the project's established style (naming, patterns, libraries).
- Clean Code: Prioritize readability, DRY principles, and proper error handling.
Phase 4: Taste Test (Verification)
- Verify: Run the build (
./gradlew assembleDebug) and relevant tests. - Cleanup: Remove any temporary debug logs, comments, or unused imports.
Phase 5: Serving (Final Review)
- Report: Summarize what was built and how to test it.
Guardrails
- Don't Over-Season: Stay within the scope of the requested feature.
- Fresh Ingredients: Always use the latest project conventions found in
GEMINI.md. - Safety First: Never proceed with high-impact architectural changes without an approved "Recipe".
When not to use it
- →When high-impact architectural changes are required without an approved technical plan
Limitations
- →Requires user approval for the technical plan before implementation
- →Does not proceed with high-impact architectural changes without an approved plan
- →Emphasizes following existing project conventions
How it compares
This skill provides a structured, multi-phase workflow for feature implementation, ensuring research, planning, idiomatic coding, and verification, which is more complete than ad-hoc coding.
Compared to similar skills
cook side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| cook (this skill) | 0 | 24d | No flags | Advanced |
| software-architecture | 333 | 6mo | No flags | Intermediate |
| codex | 32 | 2mo | Review | Advanced |
| game-development | 70 | 6mo | No flags | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
software-architecture
davila7
Guide for quality focused software architecture. This skill should be used when users want to write code, design architecture, analyze code, in any case that relates to software development.
codex
Lucklyric
Invoke Codex CLI for complex coding tasks requiring high reasoning capabilities. This skill should be invoked when users explicitly mention "Codex", request complex implementation challenges, advanced reasoning, or need high-reasoning model assistance. Automatically triggers on codex-related requests and supports session continuation for iterative development.
game-development
davila7
Game development orchestrator. Routes to platform-specific skills based on project needs.
senior-fullstack
davila7
Comprehensive fullstack development skill for building complete web applications with React, Next.js, Node.js, GraphQL, and PostgreSQL. Includes project scaffolding, code quality analysis, architecture patterns, and complete tech stack guidance. Use when building new projects, analyzing code quality, implementing design patterns, or setting up development workflows.
command-name
anthropics
This skill should be used when the user asks to "create a plugin", "scaffold a plugin", "understand plugin structure", "organize plugin components", "set up plugin.json", "use ${CLAUDE_PLUGIN_ROOT}", "add commands/agents/skills/hooks", "configure auto-discovery", or needs guidance on plugin directory layout, manifest configuration, component organization, file naming conventions, or Claude Code plugin architecture best practices.
python-project-structure
wshobson
Python project organization, module architecture, and public API design. Use when setting up new projects, organizing modules, defining public interfaces with __all__, or planning directory layouts.