Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
document-conversion
将 DOC/DOCX/PDF/PPT/PPTX 文档转换为 Markdown 格式。自动检测 PDF 类型（电子版/扫描版），提取图片到独立目录。当管理员入库非 Markdown 文档时使用此 Skill。触发条件：入库 DOC/DOCX/PDF/PPT/PPTX 格式文件。
majiayu000/claude-skill-registry 163
-
release-prep
Use when preparing a production release or release candidate - provides a checklist-driven workflow for validation, versioning, build optimization, documentation updates, and deployment readiness.
majiayu000/claude-skill-registry 163
-
improving-prompts
Use when optimizing CLAUDE.md, AGENTS.md, custom commands, or skill files for Claude 4.5 models - applies documented Anthropic best practices systematically instead of inventing improvements
majiayu000/claude-skill-registry 163
-
research-and-report
Systematic technical research combining multi-source discovery with evidence-based analysis. Delivers authoritative recommendations backed by credible sources. Use when researching best practices, evaluating technologies, comparing approaches, discovering documentation, troubleshooting with authoritative sources, or when research, documentation, evaluation, comparison, or `--research` are mentioned.
majiayu000/claude-skill-registry 163
-
citation
Formats citations and validates source attribution for answers generated from multiple document sources (ChromaDB and web search). Use when adding source references to generated answers, validating citation accuracy, or ensuring quality of source attribution across different source types.
majiayu000/claude-skill-registry 163
-
doctype-patterns
Frappe DocType creation patterns, field types, controller hooks, and data modeling best practices. Use when creating DocTypes, designing data models, adding fields, or setting up document relationships in Frappe/ERPNext.
majiayu000/claude-skill-registry 163
-
whole-reviewer
Post-editing validation for Whole documentation. Use when: (1) After completing edits,
(2) Before marking task complete, (3) Validating cross-reference updates,
(4) Verifying bilingual consistency, (5) Final quality check.
majiayu000/claude-skill-registry 163
-
terraform-docs
Generate user-friendly documentation from Terraform code including module READMEs, architecture diagrams, runbooks, and quick references. Use when working with Terraform files (.tf), documenting infrastructure as code, or creating explanatory guides for Terraform modules and configurations.
majiayu000/claude-skill-registry 163
-
postman
API lifecycle management through Postman. Discover collections, run tests, monitor APIs, validate schemas, and publish documentation across the complete API development workflow.
majiayu000/claude-skill-registry 163
-
extract-requirements
Use this when user needs to document business requirements from undocumented legacy code. Provides systematic 6-phase extraction: automated analysis, validation rules, use cases, business rules, data models, and workflow mapping. Apply for legacy system documentation, migration planning, compliance audits, or M&A due diligence
majiayu000/claude-skill-registry 163
-
api-design
REST and GraphQL API design patterns, best practices, and conventions. Use when designing APIs, discussing HTTP methods, status codes, versioning, or API documentation. Triggers on mentions of REST, API, GraphQL, endpoint, HTTP methods, OpenAPI, swagger, API versioning.
majiayu000/claude-skill-registry 163
-
research-lookup
Look up current research information using Perplexity's Sonar Pro Search or Sonar Reasoning Pro models through OpenRouter. Automatically selects the best model based on query complexity. Search academic papers, recent studies, technical documentation, and general research information with citations.
majiayu000/claude-skill-registry 163
-
cw-official-docs
Creative writing skill for creating canonical reference documentation (wikis) for fictional worlds, characters, and story events. Use when creating or updating wiki pages, official documentation, character profiles, location documentation, or lore pages. Creates polished, sourced, encyclopedic reference material.
majiayu000/claude-skill-registry 163
-
content-collections
Production-tested setup for Content Collections - a TypeScript-first build tool that transforms
local content files (Markdown/MDX) into type-safe data collections with automatic validation.
Use when: building blogs, documentation sites, or content-heavy applications with Vite + React,
setting up MDX content with React components, implementing type-safe content schemas with Zod,
migrating from Contentlayer, or encountering TypeScript import errors with content collections.
Covers: Vite plugin setup, tsconfig path aliases, collection schemas with Zod validation,
MDX compilation with compileMDX, transform functions for computed properties, rehype/remark plugins,
React component integration with MDXContent, Cloudflare Workers deployment, and production build optimization.
Keywords: content-collections, @content-collections/core, @content-collections/vite,
@content-collections/mdx, MDX, markdown, Zod schema validation, type-safe content,
frontmatter, compileMDX, defineCollection, defineConfig, Vite plugin, tsconfig paths,
.content-collections/generated, MDXContent component, rehype plugins, remark plugins,
content schema, document transform, allPosts import, static site generation,
blog setup, documentation, Cloudflare Workers static assets, content validation errors,
module not found content-collections, path alias not working, MDX type errors,
transform function async, collection not updating
majiayu000/claude-skill-registry 163
-
today
Get today's date for web searches and date-sensitive tasks. Auto-invoke before any WebSearch that includes a year (e.g., "React 2024", "Python 2025"), when searching for current documentation, latest releases, or recent information. Ensures searches use the correct current year instead of outdated dates.
majiayu000/claude-skill-registry 163
-
docx-contracts
Fill Word document templates (contracts, forms) with structured data using docxtpl. Use when user uploads a .docx template with {{variables}} and provides data to fill it, or requests contract/form generation from template.
majiayu000/claude-skill-registry 163
-
6-blogs
majiayu000/claude-skill-registry 163
-
document-lifecycle
Unified document lifecycle management. Defines terminal statuses, unified numbering via .next-id, close procedures, and orphan detection. Load at session start.
majiayu000/claude-skill-registry 163
-
project-docs-sync
Automatically synchronize project documentation when major changes occur (new tech, architecture changes, requirements shifts). Detects significant updates and propagates changes across TECH-STACK.md, ARCHITECTURE.md, and SPECIFICATIONS.md.
majiayu000/claude-skill-registry 163
-
first-time-user-ucv-cli
Simulate a first-time UCV-CLI user experience. Tests if documentation enables new users to use the interactive variant management dashboard. Generates UX audit reports with friction points.
majiayu000/claude-skill-registry 163
-
docling
Convert documents (PPTX, PDF, DOCX, XLSX, images) to Markdown/JSON/HTML using IBM Docling. This skill should be used when user asks to convert, parse, or extract content from documents. Triggers on "convert pptx", "parse pdf", "extract from document", "конвертуй презентацію", "витягни з pdf".
majiayu000/claude-skill-registry 163
-
changelog-tracker
Analyzes uncommitted git changes and updates CHANGELOG.md and CLAUDE.md. Executes git commands, reads diffs, categorizes changes, and stages updated documentation automatically.
majiayu000/claude-skill-registry 163
-
meeting-notes-formatter
Convert raw meeting notes to structured markdown or PDF with automatic section detection, action items extraction, and attendee parsing.
majiayu000/claude-skill-registry 163
-
pymupdf
PyMuPDF (fitz) - PDF manipulation library. Use for PDF text extraction, table detection, image extraction, and document parsing.
majiayu000/claude-skill-registry 163