documents▌

Templates and structure guidelines for common documentation types.

Expert in creating clear, comprehensive, and maintainable technical documentation.

You are a documentation expert specializing in creating comprehensive, maintainable documentation from code. Generate API docs, architecture diagrams, user guides, and technical references using AI-powered analysis and industry best practices.

Interactive demos render a Remotion composition inline in documentation pages using @remotion/player. They live in packages/docs/components/demos/.

Convert Feishu/Lark cloud documents to Markdown for AI analysis and processing. \n \n Supports four document types: docx (with embedded images), sheets, bitable, and wiki pages, all exported as Markdown \n Includes CLI commands for export, OAuth setup, and credential management; also offers Python API for direct content retrieval \n Can output to files or stdout, with automatic image downloading and optional Markdown table formatting \n Token caching and auto-refresh eliminate re-authorization;

Review requirements or plan documents through multi-persona analysis. Dispatches specialized reviewer agents in parallel, auto-fixes quality issues, and presents strategic questions for user decision.

This skill enables building document processing pipelines - chain multiple operations (extract, transform, convert) into reusable workflows with data flowing between stages.

Use this skill when:

Generates and formats changelog files for new releases with version-aware templates and highlight extraction. \n \n Handles three release types: stable minor versions, stable patches, and preview releases, each with distinct file update procedures \n Automatically processes raw markdown release notes by reformatting PR URLs to markdown links and removing contributor sections \n Generates concise 3–5 point highlight summaries for release announcements, prioritizing new features over bug fixes \n

Translate PDF documents to any language while preserving layout, colors, and styling. \n \n Three-step workflow: extract text strings, create a JSON translation mapping, then apply translations with language-specific font selection \n Supports five font families covering Latin languages, Simplified Chinese, Traditional Chinese, Japanese, and Korean \n CJK fonts automatically scale to 90% for optimal text fitting within original PDF boundaries \n Preserves all original formatting including colors