Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Extract and summarize core features, constraints, and priorities from requirement documents. Use when analyzing PRDs, RFCs, business requirements, user stories, epics, or any requirement documentation to identify must-have features, technical constraints, priority levels (P0/P1/P2/MoSCoW), and key decision points. Triggers when users ask to summarize, analyze, extract, or understand requirements from documents.
Summarize long Isabelle or Coq proof scripts into high-level logical steps and reasoning flow. Use when users need to: (1) Understand the structure of a complex proof, (2) Document proof strategies for others, (3) Extract the key reasoning steps from verbose proof scripts, (4) Create readable proof outlines from detailed tactical proofs. Produces hierarchical outlines with moderate detail showing proof structure, main cases, key lemmas, and reasoning flow for both Isabelle/Isar and Coq proofs.
Generate concise, structured summaries of requirements for quick team understanding. Use when analyzing requirements from text documents (MD, TXT, DOCX) or technical specifications to create bullet-point summaries that highlight core functionality and dependencies/constraints. Ideal for sprint planning, stakeholder updates, team onboarding, or any situation requiring rapid comprehension of requirement documents.
Generate comprehensive API documentation from repository sources including OpenAPI specs, code comments, docstrings, and existing documentation. Use when documenting APIs, creating API reference guides, or summarizing API functionality from codebases. Extracts endpoint details, request/response schemas, authentication methods, and generates code examples. Triggers when users ask to document APIs, generate API docs, create API reference, or summarize API endpoints from a repository.
Reorganizes markdown documents into well-structured, consistent format while preserving content and improving readability. Use when Claude needs to: (1) Fix heading hierarchy issues (skipped levels, multiple h1s), (2) Generate or update table of contents, (3) Standardize formatting (lists, code blocks, emphasis, links), (4) Improve grammar and spelling, (5) Add missing standard sections (installation, usage, etc.), (6) Remove redundant or duplicate content, (7) Restructure technical docs, READMEs, or long-form content for better organization and flow.
Process Chinese blog posts for the justin3go.com VitePress blog: rename to English slug, add frontmatter and AI summary, and translate to English. Triggers when the user mentions processing a blog post, translating an article, adding summaries, renaming post files, or says things like 'process this post', 'translate this article to English', 'add AI summary', 'rename this blog post'. Also triggers when the user provides a Chinese markdown post file and wants it prepared for publishing in both Chinese and English versions.
Operate "my canvas" (a local infinite canvas) for image work — open the canvas, generate new images onto it, and redraw images based on arrow annotations drawn on the canvas. Use when the user wants to open the canvas, generate an image onto it, or modify/iterate an image already on the canvas (even without saying "canvas" explicitly — phrases like "change the background", "redraw this", "tweak this image" count too).