code-generation
Minimal, pattern-matching code output. Write the least code that satisfies requirements. Match existing project patterns. Use Write/Edit tools only.
Best use case
code-generation is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Minimal, pattern-matching code output. Write the least code that satisfies requirements. Match existing project patterns. Use Write/Edit tools only.
Teams using code-generation should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/code-generation/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How code-generation Compares
| Feature / Agent | code-generation | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Minimal, pattern-matching code output. Write the least code that satisfies requirements. Match existing project patterns. Use Write/Edit tools only.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Code Generation ## Overview Guides code output to be minimal and pattern-matching. Write the least amount of code that satisfies the requirements while following existing project conventions. ## Principles 1. **Minimal**: Write the least code that makes tests pass 2. **Pattern-matching**: Follow existing project conventions (check patterns.md) 3. **Tool discipline**: Use Write/Edit for files, Bash only for runners and linters 4. **No gold plating**: Do not add features beyond what is required 5. **No premature optimization**: Optimize only when performance tests demand it ## Code Quality Checks - Follow project naming conventions - Match existing file structure and organization - Use established error handling patterns - Maintain consistent import ordering - Follow TypeScript strictness (no `any`, proper narrowing) ## When to Use - During TDD GREEN phase (minimal implementation) - During TDD REFACTOR phase (pattern alignment) - When implementing fixes in DEBUG workflow ## Agents Used - `component-builder` (primary consumer) - `bug-investigator` (fix implementation)
Related Skills
pdf-generation
Professional PDF documentation generation. Convert Markdown to PDF with custom templates, styling, table of contents, cross-references, and optimized output for print and archival.
diagram-generation
Multi-format diagram generation from text descriptions. Create Mermaid, PlantUML, D2, and Graphviz diagrams including flowcharts, sequence diagrams, architecture diagrams (C4), and data models.
test-data-generation
Synthetic test data generation and management using Faker.js and similar tools. Generate realistic test data, create data factories, implement database seeding, and manage test data anonymization.
procedural-generation
Procedural level generation skill for PCG algorithms.
rag-embedding-generation
Batch embedding generation with caching, rate limiting, and multiple provider support
specification-generation
Convert requirements into structured technical specifications with architecture decisions
Epic Generation
Transform PRD into a technical implementation plan with architecture decisions and dependency mapping.
process-builder
Scaffold new babysitter process definitions following SDK patterns, proper structure, and best practices. Guides the 3-phase workflow from research to implementation.
babysitter
Orchestrate via @babysitter. Use this skill when asked to babysit a run, orchestrate a process or whenever it is called explicitly. (babysit, babysitter, orchestrate, orchestrate a run, workflow, etc.)
yolo
Run Babysitter autonomously with minimal manual interruption.
user-install
Install the user-level Babysitter Codex setup.
team-install
Install the team-pinned Babysitter Codex workspace setup.