General AI agent skills

926 skills in the archive. Read a skill’s instructions or open its original repository.

• Bedtime Story

  by @anbeime

  内容创作者在需要哄睡3-12岁儿童或制作睡前音频内容时，可一键生成20个精选故事列表，或直接讲解指定寓言与成语。以0.6倍舒缓语速和亲切语气自动营造温馨哄睡氛围，轻松搞定高质量睡前陪伴。

• Atutun Xhs Cover

  by @anbeime

  阿囤囤风格小红书封面提示词生成。用于AI工具、效率方法、产品测评、教程部署、个人经验、播客推荐、职场认知类内容的爆款竖版封面设计。特点是真人出镜、超大柔和浅黄（#FDFFA7）/白色中文标题、粗黑描边、人物抠图描边、绿色勾选清单、emoji贴纸、箭头标注、高对比高密度构图。关键词：小红书封面、爆款封面、阿囤囤风格、AI教程封面、产品测评封面、封面提示词。

• Icon Generator

  by @anbeime

  网页与数字界面设计师和平面设计师在开发App、网页或设计UI界面时，当需要快速产出高质量Icon，使用此技能即可一键生成多尺寸、风格统一的标准图标，彻底解决图标设计耗时痛点，大幅提升视觉交付效率！

• Skill Template

  by @anbeime

  技能创建模板。复制此目录并修改 SKILL.md 即可创建新技能。请将所有 <占位符> 替换为实际内容。

• Okx Agent Payments Protocol

  by @internet-court

  Use when an agent hits HTTP 402 / payment-required, or the user mentions x402, x402Version, X-PAYMENT, PAYMENT-REQUIRED, PAYMENT-SIGNATURE, WWW-Authenticate: Payment, permit2, upto, metered billing, a payment channel / voucher /…

• 3d Ultra Realistic Water

  by @MengTo

  Build an ultra-realistic open ocean in Three.js with a deep-water Gerstner spectrum shaded per pixel from analytic derivatives, each wave faded at its own pixel footprint, plus Fresnel sky-cube and planar reflections, subsurface…

• Whatsapp

  by @steipete

  WhatsApp router: history/search/read/send; wacrawl read, wacli live.

• Stripe Reconciliation

  by @Devin-AXIS

  Reconcile bounded Stripe payment and payout records with supplied business records while preserving object IDs, currency, time zone, and discrepancy evidence.

• Wechat Official Assets

  by @Devin-AXIS

  Prepare selected workspace images and information cards as WeChat Official Account cover and article assets without reading outside the active workspace.

• Stripe Safe Operations

  by @Devin-AXIS

  Review and execute explicitly requested Stripe writes with exact environment, object, amount, currency, customer, and irreversible-effect confirmation.

• Wechat Official Content

  by @Devin-AXIS

  Create accurate, readable WeChat Official Account article drafts with a clear title, digest, HTML body, source links, and a reviewable call to action.

• Wechat Official Comments

  by @Devin-AXIS

  Triage WeChat article comments, prepare safe reply drafts, and only reply, feature, delete, or change comment state with explicit user intent.

• Linear Triage

  by @Devin-AXIS

  Triage Linear issues using bounded searches, duplicate checks, explicit team and project scope, and evidence-backed priority recommendations.

• Sentry Issue Investigation

  by @Devin-AXIS

  Investigate a Sentry issue from bounded event, stack, tag, environment, release, and timeline evidence before proposing a code change.

• Wechat Official Community

  by @Devin-AXIS

  Inspect WeChat Official Account followers and safely review or update custom menus with explicit before-and-after confirmation.

• Wechat Official Publishing

  by @Devin-AXIS

  Manage WeChat Official Account drafts and publication with explicit preview, confirmation, and post-publication status checks.

• 3d High Resolution Textures

  by @MengTo

  Build sharp, physically coherent high-resolution materials for 3D rendering with appropriate PBR maps, texel density, UV direction, mipmaps, anisotropic filtering, and progressive asset delivery. Use for detailed wood, stone,…

• Ooo

  by @Q00

  Start Ouroboros onboarding. Use when the user sends bare `ooo`, asks to start Ouroboros, or is using Ouroboros for the first time.

• Evaluate

  by @Q00

  Evaluate execution with three-stage verification pipeline

• Cancel

  by @Q00

  Cancel stuck or orphaned executions

• Vue Router Best Practices

  by @antfu

  Vue Router 4 patterns, navigation guards, route params, and route-component lifecycle interactions.

• Maui Shell Navigation

  by @dotnet

  Guide for implementing Shell-based navigation in .NET MAUI apps. Covers AppShell setup, visual hierarchy (FlyoutItem, TabBar, Tab, ShellContent), URI-based navigation with GoToAsync, route registration, query parameters, back…

• Support Prerendering

  by @dotnet

  Make interactive Blazor components work correctly with prerendering. USE FOR fixing duplicate data loads, UI flicker during prerender-to-interactive handoff, null references during prerender, persisting state across prerender,…

• Fetch And Send Data

  by @dotnet

  Call APIs, load data into components, and handle the async lifecycle in Blazor. USE FOR fetching data from a backend, submitting data to an API, displaying loading/error states, registering HttpClient, building service…

• Skillhub Cli

  by @iflytek

  Connect an Agent to a SkillHub registry and use the official SkillHub CLI to search, install, list, or explicitly upgrade SkillHub skills. Use when a user asks to connect SkillHub, install a SkillHub skill, or manage skills…

• Vibe Async

  by @mistralai

  Async and concurrency patterns for Mistral Vibe. Use when working with asyncio, the agent loop, Textual TUI threading, HTTP clients, streaming surfaces, or core-to-TUI communication.

• Orienting To An Inherited Seat

  by @mvschwarz

  Use when you have just been primed into an EXISTING seat through a planned handover — a different agent retired and handed you the seat plus its earned context — and you need a world model of what just happened to you. Covers…

• Openrig Herdr

  by @mvschwarz

  Use when opening OpenRig fleet terminals as a herdr wall — turning a rig, pod, mission, slice, or saved view into live interactive agent tiles via `rig terminal`, watching another rig read-only, or driving herdr on an agent's…

• Openrig Cmux

  by @mvschwarz

  Use when opening OpenRig fleet terminals into cmux — turning a rig, pod, mission, slice, or saved view into live agent tiles via `rig terminal --provider cmux`, or driving cmux on an agent's request. Same OpenRig view semantics…

• Cross Host Rig Commands

  by @mvschwarz

  Use when addressing a registered remote OpenRig host, choosing its transport, or interpreting a cross-host result.

• Ble Temperature Sensor

  by @mvanhorn

  Control BLE Temperature Sensor through the generated BLE device CLI.

• Ble Session Appliance

  by @mvanhorn

  Control BLE Session Appliance through the generated BLE device CLI.

• Ble Opaque Binary

  by @mvanhorn

  Control BLE Opaque Binary Device through the generated BLE device CLI.

• Ble Desk Lamp

  by @mvanhorn

  Control BLE Desk Lamp through the generated BLE device CLI.

• Grill With Docs

  by @vinvcn

  一个用来打磨计划或设计的持续追问式访谈，并在过程中创建文档（ADRs 和词汇表）。

• Ui

  by @graphif

  建立于 shadcn/ui 之上的附加 UI 组件

• Domain Modeling

  by @vinvcn

  构建并打磨项目的领域模型。适用于用户想明确领域术语或通用语言、记录架构决策，或其他技能需要维护领域模型时。

• To Questionnaire

  by @vinvcn

  把你无法完整回答的 decision 转成一份交给他人填写的 questionnaire。

• Wait What

  by @vinvcn

  停一下。刚才那条消息没有说清楚——重新表述一遍。

• Muapi Platform

  by @SamurAIGPT

  Setup and utility scripts for muapi.ai — configure API keys, test connectivity, and poll for async generation results

• Quick Recap

  by @BuilderIO

  Use when adding or following the red/yellow/green final status block convention for agent responses, especially by installing managed AGENTS.md or CLAUDE.md instructions.

• Remind

  by @davidondrej

  Rewrite the last response simpler and shorter in plain English, prefixed with a 3-5 sentence TLDR of the conversation so far. Manual-only, invoked as /remind.

• Before Building

  by @davidondrej

  Fire the moment the user proposes a build. Instantly surface the 1-3 consequential choices hidden in their idea. Can also be invoked with /before-building.

• Stop Overthinking

  by @davidondrej

  Manually-invoked skill that stops overthinking and forces a short, practical decision. Use only when the user explicitly invokes stop-overthinking.

• Decisions

  by @davidondrej

  Ask the agent to list all choices it made during the current work that it is not confident of. Manual-only; invoke with /decisions.

• Rename

  by @davidondrej

  Manually-invoked skill that renames the current thread or session to 2-5 lowercase descriptive words. Use when the user says "rename", "rename this", "rename thread", or "rename session".

• Self Archive

  by @davidondrej

  Archive the current bb thread and release its runtime. Use when the user explicitly asks to "self-archive", "archive yourself", or "archive this thread".

• File Tree

  by @davidondrej

  Manually-invoked skill that prints a nice file tree of the current topic in a code block. Use when the user says "file-tree" or "file tree".

• Keep Track

  by @davidondrej

  Keep track of open topics and decisions. Use when the user says "keep-track" or asks to keep a running list of remaining items.

• Loogle Search

  by @parcadei

  Search Mathlib for lemmas by type signature pattern

• Index At Creation

  by @parcadei

  Index at Creation Time

• Line Execution Checker

  by @gadievron

  Check if specific lines were executed using gcov data

• Protracted Strategy

  by @HughYau

  持久战略：面对长期、复杂、短期不可能速胜的任务，客观评估态势，划分战略防御 / 相持 / 反攻三阶段，判定当前所处阶段，设置阶段转换条件，并在困难阶段仍给出局部进攻点。当任务跨多个会话或多轮迭代、资源暂时不足、或出现"想放弃"与"一把梭"两种情绪时触发；任务能在当前会话完成时不触发。 English: Protracted strategy. For long-horizon work that cannot be won quickly,…

• Spark Prairie Fire

  by @HughYau

  星火燎原：从零起步、资源极少时，先评估客观条件，选定一个能站稳、能复用、能扩展的"根据地"（最小切入点），扎根后再逐步扩张，拒绝四处出击的流寇主义。当启动新项目、做 MVP / pilot、面对宏大目标不知从何下手、或做了很多零散事却没有积累时触发；项目已有稳固基础、只是修改现有系统时不触发。 English: Spark a prairie fire. When starting from almost nothing, assess the…

• Practice Cognition

  by @HughYau

  实践认识论：把方案、假说或判断放回实践中检验，按「实践 → 认识 → 再实践」螺旋迭代，并在开始前写明循环终止条件。当你提出了假说要验证、一次尝试失败要复盘再来、发现自己只想不做或只做不想时触发；一次性输出、答案可直接查阅、还没形成假说（先调查）时不触发。 English: Practice-cognition loop. Test a hypothesis or plan in practice, learn from the result, and…

• Seedance Prompt Zh

  by @dexhunter

  为即梦 Seedance 2.0 多模态AI视频生成模型撰写高质量提示词。当用户需要使用文本、图片、视频、音频等多模态输入创作视频提示词时触发。涵盖@引用语法、运镜复刻、特效模仿、视频延长、视频编辑、音乐卡点、电商广告、短剧创作、科普教育等场景。

• Skill Quality Gate

  by @ZJU-REAL

  发布前质量关卡：合规风险检测（敏感词、绝对化用语、平台规则） + 产物质量审核（完整性、可读性、平台适配度）。一次检查，两道把关。 当用户说"检查合规"、"质量检查"、"能不能发"、"有没有敏感词"、 "审核一下"、"发布前检查"、"质量够不够"时使用。 合并了原 skill-check-compliance 和 skill-review-deliverable 的能力。

• Skill Voice Builder

  by @ZJU-REAL

  通过结构化访谈和写作样本分析，构建创作者个人声音画像（语气/用词/节奏/风格），确保后续内容风格一致。 当用户说"声音画像""我的写作风格""风格一致""建立人设语气""voice/tone""我的表达习惯""统一文风"时使用。 和 skill-audience-profiler 的区别：本 SKILL 建创作者自己的声音画像；audience-profiler 建目标受众/粉丝画像。

• Skill Profile Builder

  by @ZJU-REAL

  首次使用引导：从社媒链接分析、从零生成账号画像 Profile。收集社媒链接+运营意图，分析已发内容与收藏喜好，生成 6 维 Profile。当用户说 创建画像/第一次用/帮我建个人设/分析我的账号建画像/从链接生成画像 时使用。与 skill-profile-manager 的区别：本 SKILL 专做首次从零分析生成；已有画像的编辑/记忆更新/导出/对比/切换找 profile-manager。

• Skill Livestream

  by @ZJU-REAL

  为直播生成完整方案：直播主题、流程时间表、开场白/过渡语/催单话术/感谢话术/互动话术。 适用于带货直播、知识分享直播、娱乐直播。 当用户说"直播策划"、"直播方案"、"直播话术"、"开播前准备"、"直播流程"、 "直播脚本"、"带货直播"、"怎么开播"、"直播怎么做"、"直播排期"、"写个直播话术"时触发。

• Style Transfer

  by @ZJU-REAL

  文案风格迁移：把一段文案从一种风格改写成另一种风格（严肃→搞笑、书面→口语、文艺→直白、正式→社交媒体感）， 支持风格参考（给一段目标风格的示例文本）。 使用时机：用户说"改成搞笑风格"、"换个风格"、"风格迁移"、"改成口语化"、"改成文艺风"、 "像 XX 那样写"、"风格改写"、"换个腔调"。 和 text-polisher 的区别：polisher 提升质量不改风格，style-transfer 改变风格不做质量评估。

• Skill Positioning Analysis

  by @ZJU-REAL

  差异化定位分析：帮账号/品牌找到差异化定位——扫描赛道、给竞品定位坐标、识别空白机会、 从人群/场景/价值/形式/人设多维找差异点，凝练一句话定位并给落地建议。当用户说"差异化定位" "怎么和竞品区分""我的定位是什么""找差异化""赛道分析""定位分析""怎么突出""同质化怎么办" "找我的独特点"时使用。

• Skill Topic Evaluator

  by @ZJU-REAL

  评估单个选题的潜力，按统一维度（流量潜力、账号匹配、 竞争差异化、时效价值、变现空间、制作成本、合规风险）打分，输出"做/不做/改方向"建议。 当用户说"这个选题值不值得做"、"评估一下"、"能不能火"、"有没有流量"、 "做不做这个"、"选题评估"、"值得做吗"、"这个话题行不行"、"帮我判断一下"时触发。 skill-content-matrix 批量生成选题池；skill-post-scorer 评估已完成内容，本 SKILL…

• Skill Trend Rider

  by @ZJU-REAL

  给定一个热点事件或话题，结合创作者账号定位，输出蹭热点的具体内容方案。 包含切入角度、内容形式、标题建议、风险提醒。 当用户说"这个热点怎么蹭"、"蹭热点"、"怎么结合"、"热点和我有关吗"、 "追热点"、"热点方案"、"借势"、"怎么追这个热点"、"热点怎么切"时触发。 和 skill-trending-topics 的区别：trending-topics 发现和筛选热点， trend-rider 拿到一个具体热点后规划怎么蹭、怎么切内容。

• Skill Trending Topics

  by @ZJU-REAL

  抓取微博、抖音、知乎、头条、B站实时热搜，筛选与创作者赛道相关的热点，输出二创选题建议。 当用户说"今天有什么热搜""热点""最近大家在聊什么""追热点""蹭热点""二创选题""热搜榜"时使用。 和 skill-news-intelligence 的区别：本 SKILL 抓分钟级实时热搜榜做快速二创选题； news-intelligence 做日级深度行业资讯聚合，不抓热搜榜。

• Health

  by @agenticnotetaking

  Run condition-based vault health diagnostics. 8 categories — schema compliance, orphan detection, link health, description quality, three-space boundaries, processing throughput, stale notes, MOC coherence. 3 modes — quick…

• Reflect

  by @agenticnotetaking

  Find connections between notes and update MOCs. Requires semantic judgment to identify genuine relationships. Use after /reduce creates notes, when exploring connections, or when a topic needs synthesis. Triggers on "/reflect",…

• Reweave

  by @agenticnotetaking

  Update old notes with new connections. The backward pass that /reflect doesn't do. Revisit existing notes that predate newer related content, add connections, sharpen claims, consider splits. Triggers on "/reweave", "/reweave…

• Validate

  by @agenticnotetaking

  Schema validation for notes. Checks against domain-specific templates. Validates required fields, enum values, description quality, and link health. Non-blocking — warns but doesn't prevent capture. Triggers on "/validate",…

• Verify

  by @agenticnotetaking

  Combined verification — recite (description quality via cold-read prediction) + validate (schema compliance) + review (health checks). Use as a quality gate after creating notes or as periodic maintenance. Triggers on "/verify",…

• Next

  by @agenticnotetaking

  Surface the most valuable next action by combining task stack, queue state, inbox pressure, health, and goals. Recommends one specific action with rationale. Triggers on "/next", "what should I do", "what's next".

• Tasks

  by @agenticnotetaking

  View and manage the task stack and processing queue. Shows pending work, active tasks, completed items, and queue state. Triggers on "/tasks", "show tasks", "what's pending", "task list", "queue status".

• Example Skill

  by @shareAI-lab

  A sample skill for demonstration

• Graphviz

  by @markdown-viewer

  Create directed/undirected graphs using DOT language with automatic layout. Best for dependency trees, call graphs, package hierarchies, and module relationships requiring fine-grained edge routing.

• Dingtalk Tag

  by @DingTalk-Real-AI

  钉钉数字员工的自然语言创建、查询、修改、发布、删除、能力资源、执行状态、本地 Profile 落盘与 DSH 接入。Use when 用户说创建或管理数字员工、改人设/岗位/响应模式、发布或询问下线能力、查执行状态或 trace、管理数字员工 Skill/MCP、把已有数字员工转换为本地 Profile，或接入本地 DSH。命令前缀：dws dingtalk-tag。

• Maintenance

  by @Chachamaru127

  File cleanup and archiving. Tidies up bloated Plans.md, session-log.md, old logs, and state files. Trigger: /maintenance, cleanup, archive, organize, split session-log. Do NOT load for: implementation, review, release, new…

• Cursor Setup

  by @Chachamaru127

  Configure and verify the Cursor backend for Claude Code Harness. Use when user invokes cursor:setup, wants Cursor as the local default implementation backend, or asks to check Cursor plugin/agent readiness. Distribution default…

• Session Send

  by @Chachamaru127

  This skill should be used when the user asks to notify other session, requests a session handoff, says tell other agent, or needs a cross-session message.

• Wecomcli Shared

  by @WecomTeam

  wecom-cli 业务技能的公共前置检查、获取机器人及授权真人身份，以及通用输出约束。任何 wecomcli-* 技能首次准备执行 wecom-cli 命令前，都必须同时读取本技能，检查 CLI 是否安装、版本是否不低于 1.2.1，以及企业微信凭证是否已授权；仅在缺失、版本过低或未授权时执行安装或初始化。本技能还定义所有技能通用的 ID 类字段禁止外露约束。本技能不处理具体业务请求。

• Alphagenome Atlas Website Links

  by @google-deepmind

  Constructs deep-links and URLs for the AlphaGenome Atlas website. Supports generating single-variant exploration links (1-based chr:pos:ref>alt), genomic locus views (1-based closed chr:start-end), candidate summary tables, and…

• Goutoujunshi

  by @shengjidaguai-china

  恋爱军师与情绪支持 skill。用于心动、暧昧、追求、聊天记录或截图分析、约会、关系确认、多人选择、冲突、冷淡、投入失衡、分手、复合、出轨、婚姻或家庭问题；也用于分析关系信号、设计主动推进或退出策略、润色可直接发送的话术，以及把冷读、自然流、Blueprint、Mystery 等经典社交体系转译成真实、互惠、可退出的沟通能力。支持分析ChatLab已有数据和经同意可撤销的长期关系档案，不负责导出聊天软件数据。首次使用时为用户及一个或多个目标对象建立包含…

• Argent Ios Simulator Setup

  by @software-mansion

  Set up and connect to an iOS simulator using argent MCP tools. Use when starting a new session, booting an iOS simulator, getting an iOS UDID, or before any iOS simulator interaction task.

• Vue Router Best Practices

  by @vuejs-ai

  Vue Router 4 patterns, navigation guards, route params, and route-component lifecycle interactions.

• Patent Write

  by @xstongxue

  基于用户提供的技术方案、草稿或参考专利，生成、改写与统稿中文发明专利的题目、摘要、背景技术、发明内容、权利要求、附图说明和具体实施方式。用于专利撰写、专利摘要、权利要求、说明书、专利润色、专利仿写、参考专利蒸馏等场景。

• Codegen Diagram

  by @xstongxue

  基于当前项目/代码生成 Draw.io 图表，支持技术栈图、系统架构图、数据结构图、E-R 图四种类型。输出符合 Draw.io 语法的 .drawio 文件（mxGraph XML），可直接导入 Draw.io 编辑。当用户提到技术栈、系统架构、数据结构、E-R 图时使用。

• Md Report Summary

  by @xstongxue

  生成高质量 Markdown 周报、工作汇报、总结、介绍等文档。无草稿时从 Web 搜索并总结；有草稿时结合草稿整理、润色、补充。当用户提到周报、工作汇报、总结、介绍、述职、复盘时使用。

• Vue Pinia Best Practices

  by @vuejs-ai

  Pinia stores, state management patterns, store setup, and reactivity with stores.

• Vue Jsx Best Practices

  by @vuejs-ai

  JSX syntax in Vue (e.g., class vs className, JSX plugin config).

• Stanley Druckenmiller Investment

  by @tradermonty

  スタンレー・ドラッケンミラーの投資哲学と戦略に基づいた投資アドバイスを提供。30年間無敗、年率30%近いリターンを達成した伝説的投資家の思考法を活用し、マクロ経済分析、リスク管理、ポジション構築、市場サイクルの読み方などについて実践的な指導を行う。投資判断、市場分析、リスク管理、ポートフォリオ構築などの相談時に使用。

• Ig5 Diff

  by @Minglink

  使用 IG5 bindiff 多特征启发式比较版本函数和变更块，结合调用关系、常量、虚表、跳转表及微码核验补丁候选，保留歧义与截断信息。

• Ig5 Triage

  by @Minglink

  使用 IG5 对新二进制样本进行只读侦察，结合入口、可疑 API、加密常量、栈帧、跳转表与虚表线索选择优先分析函数。

• Exposure Risk Quantification

  by @elementalsouls

  FAIR-aligned exposure quantification: turns a pile of recon findings into a defensible 0-100 + A-F org risk score (Likelihood x Impact, three ownership-aware factors: exposure/threat/impact), an ownership + proof demotion cap so…

• Manage Skills

  by @rohitg00

  Discover, list, create, edit, toggle, copy, move, and delete AI agent skills across 11 tools (Cursor, Claude, Agents, Windsurf, Copilot, Codex, Cline, Aider, Continue, Roo Code, Augment)

• Inbox Processor

  by @heyitsnoah

  Help organize and process items in the 00_Inbox folder according to the PARA method. Use when the user asks to process, clear, sort, triage, or organize their inbox.

• Nano Banana Pro

  by @Bitterbot-AI

  Generate or edit images via Gemini 3 Pro Image (Nano Banana Pro).

• Route By Query Shape

  by @Bitterbot-AI

  When the agent calls memory_search with a relationship-shaped query ("who did I talk to about X"), redirect to the knowledge_graph backend where it will actually find the answer.

• Calibrate Claim Confidence

  by @Bitterbot-AI

  When the agent's epistemic state (GCCRF) indicates low empowerment and falling certainty, hedges out confident absolutes ("definitely", "always", "100%") in outgoing messages.

• Openhue

  by @Bitterbot-AI

  Control Philips Hue lights/scenes via the OpenHue CLI.

• Voice Call

  by @Bitterbot-AI

  Start voice calls via the Bitterbot voice-call plugin.

• Foundatio Repositories

  by @exceptionless

  Query, aggregate, patch, or paginate Exceptionless data through its Elasticsearch repository abstractions.