Documentation

DeFi protocol expert ensuring correct data formats, types, denominations, and API structures. MUST be consulted before writing ANY protocol integration code. Triggers on ANY mention of Aave, Compound, Uniswap, Curve, Balancer, or DeFi terms like liquidation, swap, flash loan, health factor.

Transform raw brain dumps into structured implementation artifacts. Use when user has messy ideas, scattered thoughts, or dictated stream-of-consciousness about something they want to build. Produces contracts, phased PRDs, and implementation specs written to ./docs/ideation/{project-name}/.

Use this when working on the Workbench UI, Workbench state/store, export/compile pipeline, or adapter/target behavior (agents-md, claude-code, github-copilot, etc.).

Write minimal, focused tests that cover core user flows and primary workflows without over-testing during development. Use this skill when deciding what to test, writing behavior-focused tests, naming test cases clearly, mocking external dependencies, or keeping tests fast. Apply when completing feature implementation and adding strategic tests, testing critical paths rather than edge cases, or deferring edge case testing to dedicated testing phases.

This skill orchestrates comprehensive documentation intelligence operations. Use when asked to "analyze documentation", "learn from docs", "create SOPs from documentation", "maximize documentation understanding", or any request involving systematic multi-agent documentation analysis with parallelization.

Generate comprehensive WIKI.md documentation for any codebase using LSP for precise code analysis. Use when user asks to document a codebase, generate technical documentation, create architecture diagrams, or analyze code structure and dependencies. Supports TypeScript, JavaScript, Python, Go, Rust, Java, and C/C++ projects.

Write clear, comprehensive documentation. Use when creating README files, API docs, guides, or when the user asks for help documenting code.

Log bug reports with technical details. Use when customer reports software bugs, errors, unexpected behavior, or system malfunctions.

Create technical implementation plans from specifications with intelligence-backed architectural decisions. Use when specification exists and user mentions tech stack, architecture, implementation approach, or asks "how to implement" or "how to build" the feature.

Design referral programs for newsletter growth. Use when: (1) Creating a newreferral program, (2) Choosing referral rewards, (3) Writing referral copy inSpanish, (4) Planning referral program launch. Produces complete program specswith copy templates.

Generates comprehensive test files for functions and classes. Use after writing a function, method, or class to quickly create unit tests with edge cases, assertions, and proper test structure. Supports multiple testing frameworks (pytest, unittest, jest, etc.) and follows testing best practices (AAA pattern, mocking, fixtures).

Use when Codex needs curated documentation context or outlines from the Context7 MCP server.

Scope and prioritize technical spikes that de-risk architecture or implementation questions.

Analyzes and processes images using Claude's vision capabilities. Supports OCR, image classification, diagram comparison, chart analysis, visual Q&A, and more. Use when users need to understand, extract, or analyze visual content.

Convert various file formats (PDF, Office documents, images, audio, web content, structured data) to Markdown optimized for LLM processing. Use when converting documents to markdown, extracting text from PDFs/Office files, transcribing audio, performing OCR on images, extracting YouTube transcripts, or processing batches of files. Supports 20+ formats including DOCX, XLSX, PPTX, PDF, HTML, EPUB, CSV, JSON, images with OCR, and audio with transcription.

Given an API description and a docs bundle (e.g. from skill.context7_docs), generate a MOVA skill skeleton for a connector: ds/env schemas, manifest, prompt profile, runtime binding stub, cases, and docs.

React component testing with Vitest and Testing Library. Use when writing unit tests for components.

Generate documentation pages for components. Use when creating docs, adding a documentation page, writing component documentation, or setting up API docs for a component. (project)

Automatically detect and add comprehensive documentation to code files across multiple languages (Python, JavaScript/TypeScript, C/C++, Dart/Flutter). Generate language-appropriate docstrings, comments, and examples following industry standards. Use when code files lack documentation, after implementing new features, or when requested to document code. Support single files and batch documentation.

Writes or updates memory files with proper YAML frontmatter in the agent's memories directory. Use when saving new project learnings or updating existing memory files.