Skills publicadas
Mostrando 12 de 36video-transcribe
Video/audio transcription, visual frame analysis, Groq Whisper long-form transcripts, timestamped Obsidian notes, and keyframe-based visual summaries. Use for video links, audio links, 字幕/转录/视频总结/画面分析/图文笔记, especially when the result must replace watching the video. Keywords: video, transcribe, 转录, 视频, 音频, audio, subtitle, 字幕, summary, 总结, 图文笔记, 视频内容, 画面分析, visual analysis, keyframe, whisper, groq
linuxdo
Read LINUX DO forum content via Discourse JSON API + Chrome Cookie auth. Actions: check login, latest topics, top/trending, full-text search, read topic details, browse categories. Keywords: linuxdo, linux.do, l站, 帖子, 搜索, 最新, 热门, 分类, discourse, forum.
screenshot
Use when the user explicitly asks for a desktop or system screenshot (full screen, specific app or window, or a pixel region), or when tool-specific capture capabilities are unavailable and an OS-level capture is needed.
llm-wiki
Karpathy 风格 LLM Wiki / markdown knowledge base 工作流。用于 ingest、query、lint 持久化知识库;先做 orientation,再按 analysis -> generation 维护 wiki。
openai-docs
Use when the user asks how to build with OpenAI products or APIs and needs up-to-date official documentation with citations (for example: Codex, Responses API, Chat Completions, Apps SDK, Agents SDK, Realtime, model capabilities or limits); prioritize OpenAI docs MCP tools and restrict any fallback browsing to official OpenAI domains.
ui-ux-pro-max
UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 9 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html
orbit-os
知识库 OrbitOS Obsidian Vault 共享配置。Vault 结构、格式规则、排版规范。被 orbit-* 系列 skill 自动引用;也可在知识库相关操作中直接调用以获取上下文。
context-hub
Use Context Hub (chub) for curated, versioned API/SDK docs and agent skills. Keep OpenAI tasks on official docs first.
git-ops
Use when Sam asks Codex to create, rename, compare, commit, push, merge, promote, or clean up Git branches. Covers Sam's feature branch naming convention, safe Git pre-checks, JetBrains DontCommit handling, commit-message defaults, push and release promotion verification, branch rename upstream cleanup, branch sync comparison, and submodule/gitlink handling.
skill-creator
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
fireworks-tech-graph
Use when the user needs technical/system diagrams or image generation with structured, editable SVG output and optional PNG export: architecture, flowchart, sequence, swimlane, data flow, ER/state-machine, agent/memory, or concept map. Trigger on: "架构图" "流程图" "时序图" "泳道图" "系统图" "数据流图" "sequence diagram" "flowchart" "swimlane" "ER diagram" "state machine" "SVG diagram" "生成图片" "画图" "生图".
online-doc-html
Export Markdown files to paste-friendly standalone HTML for online document editors. Use when the user wants to copy local Markdown content into an online document, reduce manual formatting work, preserve tables/code blocks/headings, convert SVG diagrams to PNG, embed images into HTML, or says "在线文档", "粘贴到在线文档", "Markdown 转 HTML", "图片复制不过去", "导出在线文档 HTML".