An Agent Skill that turns code, documentation, SQL, configuration, PDFs, and media into a queryable knowledge graph, using deterministic local AST extraction for code and provenance labels for relationships.
Skills
Reusable professional capabilities and workflows for AI agents
Agent Reach gives command-capable AI agents workflows for reading and searching multiple platforms, selecting upstream tools, checking dependencies, and diagnosing channels. Some social sources require authenticated sessions or additional setup.
Obsidian Skills teaches AI assistants the file formats used for notes, wikilinks and visual canvases. Existing Obsidian users can start with file-based skills through manual copying, without programming. Command-line control and web extraction are separate optional capabilities.
More than 160 agent skills for scientific work, spanning research databases, analysis tools, and scientific writing workflows.
OpenAI's curated Skills catalog for Codex, including research, deployment, document, and development tools.
Convert technical books, PDFs, document folders, and source collections into structured Agent Skills that Codex, Claude Code, GitHub Copilot CLI, and Amp can load on demand.
AI Berkshire packages value-investing research into 20 callable Skills for company research, earnings review, industry screening, portfolio review, and data validation, with separate install paths for Claude Code and Codex.
Cangjie Skill applies the RIA-TV++ pipeline to turn books, transcripts, podcasts, courses, and interviews into verified, composable, pressure-tested Agent Skills.
An Agent Skill for Chinese writing and revision that checks whether the source material is sufficient, separates factual and fictional workflows, and reviews drafts for repetition, canned reversals, report-like phrasing, and flat sentence rhythm.
Tencent's official WeChat Reading Agent Skills use a unified API Gateway for book search, bookshelf access, reading progress, notes, reading statistics, public reviews, and personalized recommendations.









