guanyang/open-agent-hub

这个仓库里有 111 个技能，GitHub 星标 ★ 969。

• academy-guide>
• advanced-evaluationThis skill should be used for advanced LLM evaluation: LLM-as-judge systems, dir
• algorithmic-artCreating algorithmic art using p5.js with seeded randomness and interactive para
• baoyu-article-illustratorAnalyzes article structure, identifies positions requiring visual aids, generate
• baoyu-comicKnowledge comic creator supporting multiple art styles and tones. Creates origin
• baoyu-compress-imageCompresses images to WebP (default) or PNG with automatic tool selection. Use wh
• baoyu-cover-imageGenerates article cover images with 5 dimensions (type, palette, rendering, text
• baoyu-danger-gemini-webGenerates images and text via reverse-engineered Gemini Web API. Supports text g
• baoyu-danger-x-to-markdownConverts X (Twitter) tweets and articles to markdown with YAML front matter. Use
• baoyu-diagramCreate professional, dark-themed SVG diagrams of any type — architecture diagram
• baoyu-electron-extractExtracts resources and JavaScript from any installed Electron app (`.asar` bundl
• baoyu-format-markdownFormats plain text or markdown files with frontmatter, titles, summaries, headin
• baoyu-image-cardsGenerates infographic image card series with 12 visual styles, 8 layouts, and 3
• baoyu-image-genAI image generation with OpenAI GPT Image 2.5, Azure OpenAI, Google, OpenRouter,
• baoyu-imagineAI image generation with OpenAI GPT Image 2, Azure OpenAI, Google, OpenRouter, D
• baoyu-infographicGenerate professional infographics with 21 layout types and 22 visual styles. An
• baoyu-markdown-to-htmlConverts Markdown to styled HTML with WeChat-compatible themes. Supports code hi
• baoyu-post-to-wechatPosts content to WeChat Official Account (微信公众号) via API or Chrome CDP. Supports
• baoyu-post-to-weiboPosts content to Weibo (微博). Supports regular posts with text, images, and video
• baoyu-post-to-xPosts content and articles to X (Twitter). Supports regular posts with images/vi
• baoyu-slide-deckGenerates professional slide deck images from content. Creates outlines with sty
• baoyu-translate>-
• baoyu-url-to-markdownFetch any URL and convert to markdown using baoyu-fetch CLI (Chrome CDP with sit
• baoyu-wechat-summarySummarizes WeChat group chat highlights into a structured digest using the local
• baoyu-xhs-imagesGenerates infographic image card series with 12 visual styles, 8 layouts, and 3
• baoyu-youtube-transcriptDownloads YouTube video transcripts/subtitles and cover images by URL or video I
• bdi-mental-statesThis skill should be used when modeling agent mental states with BDI concepts: b
• brainstormingYou MUST use this before any creative work - creating features, building compone
• brand-guidelinesApplies Anthropic's official brand colors and typography to any sort of artifact
• canvas-designCreate beautiful visual art in .png and .pdf documents using design philosophy.
• claude-academy-guide>
• claude-api|-
• vercel-composition-patterns
• context-compressionThis skill should be used when long-running agent sessions need context compress
• context-degradationThis skill should be used for diagnosing and mitigating context degradation: los
• context-fundamentalsThis skill should be used to explain or reason about the foundational concepts o
• context-optimizationThis skill should be used for improving context efficiency: context budgeting, o
• defuddleExtract clean Markdown from HTML pages with Defuddle CLI.
• discernment-nudge>
• dispatching-parallel-agentsUse when facing 2+ independent tasks that can be worked on without shared state
• doc-coauthoringGuide users through a structured workflow for co-authoring documentation. Use wh
• docxUse this skill whenever the user wants to create, read, edit, or manipulate Word
• evaluationThis skill should be used when building agent evaluation systems: deterministic
• executing-plansUse when you have a written implementation plan to execute in a separate session
• filesystem-contextThis skill should be used when agent work needs file-backed context: durable scr
• finishing-a-development-branchUse when implementation is complete, all tests pass, and you need to decide how
• frontend-designGuidance for distinctive, intentional visual design when building new UI or resh
• harness-engineeringThis skill should be used when designing autonomous agent harnesses: research lo
• hosted-agentsThis skill should be used when designing hosted or background agent infrastructu
• internal-commsA set of resources to help me write all kinds of internal communications, using
• json-canvasCreate and edit JSON Canvas files (.canvas) with nodes, edges, groups, and conne
• knapRender Markdown from templates and structured data using Knap CLI. Use when the
• latent-briefingThis skill should be used when the user asks to \"share memory between agents\",
• long-horizon-promptingThis skill should be used when writing, enhancing, or evaluating the launch prom
• mcp-builderGuide for creating high-quality MCP (Model Context Protocol) servers that enable
• mediabunnyMultimedia handling with the Mediabunny library
• memory-systemsThis skill should be used for persistent semantic memory in agent systems: cross
• multi-agent-patternsThis skill should be used when designing multi-agent systems that need context i
• notebooklmUse this skill to query your Google NotebookLM notebooks directly from Claude Co
• obsidian-basesCreate and edit Obsidian Bases (.base files) with views, filters, formulas, and
• obsidian-cliInteract with Obsidian vaults using the Obsidian CLI to read, create, search, an
• obsidian-markdownCreate and edit Obsidian Flavored Markdown with wikilinks, embeds, callouts, pro
• pdfUse this skill whenever the user wants to do anything with PDF files. This inclu
• planning-with-filesPersistent file-based planning for multi-step AI-agent work. Keeps task_plan.md,
• pptxUse this skill any time a .pptx or .potx file is involved in any way — as input,
• project-developmentThis skill should be used for project-level decisions about LLM-powered systems:
• vercel-react-best-practicesReact and Next.js performance optimization guidelines from Vercel Engineering. T
• vercel-react-native-skills
• receiving-code-reviewUse when receiving code review feedback, before implementing suggestions, especi
• remotion-best-practicesBest practices and domain knowledge for building videos programmatically with Re
• mediabunnyMultimedia handling with the Mediabunny library
• remotion-captionsDealing with captions in Remotion
• remotion-createCreating a new Remotion video
• remotion-docsSearch and fetch Remotion documentation pages
• remotion-interactivityBest practices for writing Remotion animations that stay intuitive for agents an
• remotion-markupBest practices for writing Remotion React Markup
• remotion-renderBest practices for rendering videos
• remotion-saasBuilding video apps with Remotion - framework, rendering and Player advice
• remotion-best-practicesRouter for all Remotion skills
• remotion-captionsTranscribing, displaying and animating captions
• remotion-createCreate a new Remotion video
• remotion-docsSearch Remotion documentation
• remotion-interactivityStructure Remotion markup for interactivity
• remotion-mapsRemotion Map animation knowledge
• remotion-markupContent, animation and effects best practices
• remotion-multimediaInteracting with Mediabunny
• remotion-renderExport a Remotion video
• remotion-saasBuild an app with Remotion
• remotion-studioPreview a Remotion video
• remotion-upgradeUpgrade Remotion, and related packages
• requesting-code-reviewUse when completing tasks, implementing major features, or before merging to ver
• self-improvement-loopsThis skill should be used when the harness, scaffold, workflow, or optimizer its
• skill-creatorCreate new skills, modify and improve existing skills, and measure skill perform
• slack-gif-creatorKnowledge and utilities for creating animated GIFs optimized for Slack. Provides
• subagent-driven-developmentUse when executing implementation plans with independent tasks in the current se
• supabase-postgres-best-practicesPostgres best practices maintained by Supabase, for Postgres running anywhere. L
• systematic-debuggingUse when encountering any bug, test failure, or unexpected behavior, before prop
• test-driven-developmentUse when implementing any feature or bugfix, before writing implementation code
• theme-factoryToolkit for styling artifacts with a theme. These artifacts can be slides, docs,
• tool-designThis skill should be used for the tool-interface layer of an agent system specif
• ui-ux-pro-maxUI/UX design intelligence for web and mobile. Includes 50+ styles, 161 color pal
• using-git-worktreesUse when starting feature work that needs isolation from current workspace or be
• using-superpowersUse when starting any conversation - establishes how to find and use skills, req
• verification-before-completionUse when about to claim work is complete, fixed, or passing, before committing o
• web-artifacts-builderSuite of tools for creating elaborate, multi-component claude.ai HTML artifacts
• web-design-guidelinesReview UI code for Web Interface Guidelines compliance. Use when asked to "revie
• webapp-testingToolkit for interacting with and testing local web applications using Playwright
• writing-plansUse when you have a spec or requirements for a multi-step task, before touching
• writing-skillsUse when creating new skills, editing existing skills, or verifying skills work
• xlsxUse this skill any time a spreadsheet file is the primary input or output. This
• replace-with-skill-name-using-hyphensUse when [describe triggering conditions, symptoms, or specific errors].