Minimal, pattern-matching code output. Write the least code that satisfies requirements. Match existing project patterns. Use Write/Edit tools only.
Scanned 5/29/2026
Install to Claude Code
Skills Directorynpx -y skills add a5c-ai/babysitter --skill code-generation --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Code Generation?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/a5c-ai-code-generation)More formats (shields.io, HTML) on the badges page.
---
name: code-generation
description: Minimal, pattern-matching code output. Write the least code that satisfies requirements. Match existing project patterns. Use Write/Edit tools only.
allowed-tools: Read, Write, Edit, Bash, Grep, Glob
---
# 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)
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.
