Agent Skills
Agent Skills Directory
- 2449video-creation-collaboratoranbeime/skill
内容创作者与自媒体创作者在制作短视频时,若遇生图畸形、合成瑕疵或协同混乱,当需规范化多智能体流程时必用此技能。一键调度11个AI智能体,自动完成文案、分镜、音视频到视频合成的5阶段闭环,前置质检拦截瑕疵,高效产出统一可控的高质量短视频。
8.5k6108 tok idle · 5,656 in use - 2450video-creation-proanbeime/skill
电商运营与自媒体创作者在为美妆、家居、智能硬件等商品制作短视频时,请使用此技能。10大AI智能体协同,从卖点提炼、分镜生图到音效字幕,一键调用COZE API自动合成高质量商品视频,彻底告别本地代码依赖,轻松实现从创作、质检到数据迭代的全流程闭环。
8.5k2101 tok idle · 6,451 in use - 2451video-creation-suiteanbeime/skill
自媒体创作者与影片与视频编辑当需要从零原创、二次创作或深度分析视频时,请使用此套件。通过11个智能体协同,一键生成配音、音效与BGM并合成高质量视频,或自动抽帧提取分镜提示词,全流程大幅提升视频产出效率。
8.5k1882 tok idle · 3,392 in use - 2452video-frame-extractoranbeime/skill
影片与视频编辑、自媒体创作者在需要拆解优秀视频、提取分镜参考或反推提示词时,使用本技能可自动抽取视频关键帧,调用视觉大模型批量分析画面,一键生成结构化描述与创作提示词,轻松搞定视频内容提取与场景分析。
8.5k379 tok idle · 2,058 in use - 2453video-recreationanbeime/skill
自媒体创作者与影片与视频编辑在需要视频二创或反推参考视频时,一键完成从AI视觉分析、图文音素材生成到最终合成的全流程,自动产出包含配音与字幕的高质量二创视频,让创作效率翻倍!
8.5k1066 tok idle · 3,614 in use - 2454video-transcript-downloaderanbeime/skill
内容创作者与自媒体创作者在需要下载视频、提取视频网站字幕时,当需要获取纯文本稿或本地媒体文件请一键调用。自动清洗时间轴与杂音标记,一键下载音视频并生成干净的段落式字幕,大幅提升二创与内容处理效率。
8.5k174 tok idle · 526 in use - 2455viral-video-copywritinganbeime/skill
自媒体创作者与运营专员在缺乏爆款方法论、需拆解对标视频时使用。当需要创作短视频文案时,自动提取抖音视频信息并深度拆解开头钩子等爆款因素,一键生成符合爆款规律的原创文案,助你轻松打造高赞爆款内容。
8.5k285 tok idle · 3,231 in use - 2456voltagent-awesome-design-mdanbeime/skill
73 个真实网站 DESIGN.md 提取集合(Claude / Cursor / Vercel / Stripe / Apple / Tesla / Ferrari ...)。 把 DESIGN.md 复制到项目根目录,AI agent 读 DESIGN.md 后能生成风格一致的高质量 UI。 本仓库同步自 VoltAgent/awesome-design-md。 关键词:DESIGN.md, Google Stitch, UI 设计, 设计系统, Claude, Cursor, Vercel, Stripe, Apple, Tesla。
8.5k107 tok idle · 663 in use - 2457web-design-analyzeranbeime/skill
网页与数字界面设计师和网页开发工程师在需要逆向分析网页截图时,使用本技能一键提取配色、排版及组件特征,自动生成结构化 Design System 数据与 AI Coding Prompt,让设计还原与前端开发更高效。
8.5k267 tok idle · 1,223 in use - 2458web-to-appanbeime/skill
网页开发工程师当需要将任意网页URL封装为独立桌面客户端时,使用此技能可一键生成体积仅约5MB的跨平台(Win/Mac/Linux)原生应用安装包。支持自定义图标与高级配置,助你快速交付轻量级桌面端产品。
8.5k276 tok idle · 1,414 in use - 2459wechat-hotspot-publisheranbeime/skill
自媒体创作者和运营专员在需要全网追热点分发时,使用此技能可自动采集热点并10分制筛选优质选题,AI一键生成适配公众号、小红书、B站的爆款图文与HTML排版,直接发布至各平台草稿箱,轻松完成多平台高质量内容分发。
8.5k886 tok idle · 3,839 in use - 2460wechatsync-publisheranbeime/skill
自媒体创作者在进行全网内容分发时,使用此技能可智能筛选优质选题、AI生成多版本文章,并一键自动适配格式发布至微信公众号、知乎、掘金等6大平台,轻松实现从创作到推送的全流程自动化,大幅提升多平台运营效率!
8.5k379 tok idle · 3,623 in use - 2461x-article-publisheranbeime/skill
内容创作者在需要将 Markdown 长文发布到 X (Twitter) 时,使用此技能一键将 Markdown 自动转换为富文本并发布至 X Articles,完美保留排版,免去手动调整与重复登录烦恼,让长文分发更高效。
8.5k768 tok idle · 2,030 in use - 2462x-article-publisheranbeime/skill
自媒体创作者与内容创作者在需要将 Markdown 长文发布到 X (Twitter) Articles 编辑器时使用。技能自动将 Markdown 转换为富文本并完美保留排版,支持持久化免密登录与封面上传,一键完成发布,大幅提升长文分发效率。
8.5k773 tok idle · 2,034 in use - 2463xiaohongshu-makeupanbeime/skill
自媒体创作者与电商运营在推广美妆护肤产品时,当需要创作或优化小红书笔记、生成AI配图提示词时,使用此技能可一键生成高转化爆款笔记、吸睛标题与精准标签,自动产出专业文生图提示词,轻松打造小红书爆款内容。
8.5k86 tok idle · 2,115 in use - 2464brainstormingjnMetaCode/superpowers-zh
在任何创造性工作之前必须使用此技能——创建功能、构建组件、添加功能、修改行为,或筹划任何新东西,无论是软件还是软件之外(一场分享、一门生意、一次装修)。
8.4k452 tok idle · 2,807 in use - 2465chinese-code-reviewjnMetaCode/superpowers-zh
中文 review 沟通参考——话术模板、分级标注(必须修复/建议修改/仅供参考)、国内团队常见反模式应对。仅在用户显式 /chinese-code-review 时调用,不要根据上下文自动触发。
8.4k62 tok idle · 2,496 in use - 2466chinese-commit-conventionsjnMetaCode/superpowers-zh
中文 commit 与 changelog 配置参考——Conventional Commits 中文适配、commitlint/husky/commitizen 中文模板、conventional-changelog 中文配置。仅在用户显式 /chinese-commit-conventions 时调用,不要根据上下文自动触发。
8.4k65 tok idle · 2,625 in use - 2467chinese-documentationjnMetaCode/superpowers-zh
中文文档排版参考——中英文空格、全半角标点、术语保留、链接格式、中文文案排版指北约定。仅在用户显式 /chinese-documentation 时调用,不要根据上下文自动触发。
8.4k62 tok idle · 3,080 in use - 2468chinese-git-workflowjnMetaCode/superpowers-zh
国内 Git 平台配置参考——Gitee、Coding.net、极狐 GitLab、CNB 的 SSH/HTTPS/凭据/CI 接入差异与镜像同步配置。仅在用户显式 /chinese-git-workflow 时调用,不要根据上下文自动触发。
8.4k69 tok idle · 3,653 in use - 2469diagnosing-superpowersjnMetaCode/superpowers-zh
当一次 superpowers 会话出了问题、你的人类伙伴想知道原因时使用——重复劳动、无视计划、磕磕绊绊、结果质量差、某个技能没触发、"太慢了"、"为什么这么贵"、"它到底在干什么"——或者想给 superpowers 维护者整理一份 bug 报告;适用于当前会话,或按 id / 路径指定的过往会话,任何工具均可
8.4k111 tok idle · 1,862 in use - 2470executing-plansjnMetaCode/superpowers-zh
当你要在当前会话里亲自担任实现者执行一份实现计划时使用——你的人类伙伴选择了内联执行,或者没有可用的子智能体工具
8.4k46 tok idle · 5,583 in use - 2471mcp-builderjnMetaCode/superpowers-zh
在构建 MCP 服务器或 MCP 工具时使用 —— 系统化的生产级 MCP 构建方法论,覆盖工具设计、错误处理、传输层选择与测试,让 AI 助手连接外部能力
8.4k52 tok idle · 2,146 in use - 2472receiving-code-reviewjnMetaCode/superpowers-zh
收到代码审查反馈后、实施建议之前使用,尤其当反馈不明确或技术上有疑问时——需要技术严谨性和验证,而非敷衍附和或盲目执行
8.4k51 tok idle · 1,808 in use - 2473using-git-worktreesjnMetaCode/superpowers-zh
当需要开始与当前工作区隔离的功能开发,或在执行实现计划之前使用——通过原生工具或 git worktree 回退机制确保隔离工作区存在
8.4k44 tok idle · 1,841 in use - 2474using-superpowersjnMetaCode/superpowers-zh
在开始任何对话时使用——确立如何查找和使用技能,要求在任何响应(包括澄清性问题)之前调用 Skill 工具
8.4k38 tok idle · 1,280 in use - 2475verification-before-completionjnMetaCode/superpowers-zh
在宣称工作完成、已修复或测试通过之前使用,在提交或创建 PR 之前——必须运行验证命令并确认输出后才能声称成功;始终用证据支撑断言
8.4k50 tok idle · 1,021 in use - 2476workflow-runnerjnMetaCode/superpowers-zh
在 Claude Code / OpenClaw / Cursor 中直接运行 agency-orchestrator YAML 工作流——无需 API key,使用当前会话的 LLM 作为执行引擎。当用户提供 .yaml 工作流文件或要求多角色协作完成任务时触发。
8.4k61 tok idle · 1,631 in use - 2477yao-agentYaoApp/yao
Agent management expert. ALWAYS invoke this skill when you need to list available agents, download or reference agent source code, deploy agent code to the host, or query the LLM connector matrix. Do not guess agent structures — use this skill first.
8.2k53 tok idle · 673 in use - 2478yao-audioYaoApp/yao
Audio expert. ALWAYS invoke this skill when the user asks to transcribe, recognize, or convert speech/audio to text.
8.2k29 tok idle · 332 in use - 2479yao-boardYaoApp/yao
Kanban board and task query expert. ALWAYS invoke this skill when the user asks about boards, tasks, task status, or project progress. Do not guess task state — use this skill first.
8.2k43 tok idle · 220 in use - 2480yao-daemonYaoApp/yao
Daemon process management — start, monitor, restart, stop long-running services. ALWAYS invoke this skill when the user asks to start, check, restart, or stop background services, dev servers, or daemon processes.
8.2k48 tok idle · 1,121 in use - 2481yao-decisionYaoApp/yao
Typed decision expert. ALWAYS invoke this skill when you need structured classification, scoring, or probability estimation — routing tickets, grading content, detecting intent, or any task requiring typed answers with calibrated confidence.
8.2k44 tok idle · 1,200 in use - 2482yao-docYaoApp/yao
Yao process documentation expert. ALWAYS invoke this skill when the user needs to discover available processes, read process signatures, or validate process names. Do not guess process APIs — use this skill first.
8.2k43 tok idle · 336 in use - 2483yao-imageYaoApp/yao
Image expert. ALWAYS invoke this skill when you need to read, analyze, describe, or generate images. Use for screenshots, photos, charts, diagrams, AI-generated images, or any visual content.
8.2k44 tok idle · 1,712 in use - 2484yao-jobYaoApp/yao
Background job management — start, monitor, wait, stop long-running commands. ALWAYS invoke this skill when the user asks to run background tasks, check job status, read job output, or manage long-running commands.
8.2k46 tok idle · 1,036 in use - 2485yao-ocrYaoApp/yao
OCR text recognition expert. ALWAYS invoke this skill when you need to extract text from images or PDFs — including invoices, receipts, ID cards, bank cards, business licenses, tables, handwritten documents, or any visual text content.
8.2k50 tok idle · 1,451 in use - 2486yao-processYaoApp/yao
Yao process execution expert. ALWAYS invoke this skill when the user needs to call a Yao process, query data models, run scripts, or check process permissions. Do not call processes without checking this skill first.
8.2k47 tok idle · 314 in use - 2487yao-secretYaoApp/yao
Secret management expert. ALWAYS invoke this skill when you need to read API keys, tokens, or other secrets configured by the user. Never hardcode credentials — use this skill to retrieve them securely.
8.2k43 tok idle · 308 in use - 2488yao-webYaoApp/yao
Web information retrieval expert. ALWAYS invoke this skill when the user needs to search the web, fetch a URL, or access real-time information beyond training data. Do not guess or use stale knowledge — use this skill first.
8.2k48 tok idle · 238 in use - 2489yao-workspaceYaoApp/yao
Workspace file I/O expert. ALWAYS invoke this skill when you need to list workspaces, read or write files in a workspace on a remote node, or browse workspace directories. Use this for cross-node file operations — for local sandbox files, use standard filesystem tools instead.
8.2k59 tok idle · 805 in use - 2490yao-workspace-configYaoApp/yao
Workspace Git identity and credential management. ALWAYS invoke this skill when the user asks about configuring Git user info, adding HTTPS tokens, importing SSH keys, or managing workspace-level Git authentication.
8.2k42 tok idle · 631 in use - 2491agent-browsermvschwarz/openrig
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.
8.1k108 tok idle · 3,477 in use - 2492agent-operated-softwaremvschwarz/openrig
Use when designing, building, operating, or diagnosing an ongoing application whose live backend or control loop includes OpenRig agents, including applications with a Markdown, YAML, or JSON agent control plane or a thin surface over specialist agent roles.
8.1k51 tok idle · 910 in use - 2493agent-operated-workflowsmvschwarz/openrig
Use when a bounded real-world procedure has a deterministic happy path but brownfield, variable, or partially knowable state; when an operation must resume from verified evidence; or when deciding whether agent judgment or ordinary code should own a procedure's control loop.
8.1k55 tok idle · 730 in use - 2494agent-startersmvschwarz/openrig
Use when creating, refreshing, packaging, inspecting, promoting, or deprecating a named per-seat starting point — Agent Starter manifest authoring, the 6-state lifecycle (captured → named → inspectable → used → promoted → deprecated), provenance honesty, and refusal rules. NOT a VM image; a managed starting point composed from agent role + startup context + optional native session source + provenance.
8.1k84 tok idle · 1,317 in use - 2495agent-startup-and-context-ingestionmvschwarz/openrig
Use when designing or auditing how an agent becomes useful after launch — AGENTS.md overlays, role files, skills, rig specs, workflow specs, startup checklists, refocus messages, "rig context" surface. Covers the 4 failure modes that make startup context fail (old rig spec misses current operating mode; current agents never told about new guidance; startup file as dumping ground; orchestrator transmits implementation without preserving product intent).
8.1k95 tok idle · 1,276 in use - 2496applying-a-permission-policymvschwarz/openrig
Use before launching a team during agent-guided setup, or when a user asks to configure OpenRig command permissions, reduce repeated native approval prompts, or apply a selected rig/seat permission policy.
8.1k46 tok idle · 2,819 in use