Claude Skills
The open format is called Agent Skills and works in Claude Code, Codex, Cursor and other agents — most people know it as Claude Skills.
Every Agent Skill we could find on GitHub, deduplicated by content. 79 437 files from 1 744 authors, of which 61 785 are unique — the rest is the same skill repackaged into someone else's repository. For each one: what it weighs in tokens, whether it ships runnable scripts, and which MCP servers it needs.
> Review academic papers for correctness, quality, and novelty using OpenJudge's multi-stage pipeline. Supports PDF files and LaTeX source packages (.tar.gz/.zip). psychology, environmental_science, mathematics, social_sciences. Use when the user asks to review, evaluate, critique, or assess a research paper, check references, or verify a BibTeX file.
> Benchmark LLM reference recommendation capabilities by verifying every cited paper against Crossref, PubMed, arXiv, and DBLP. Measures hallucination rate, per-field accuracy (title/author/year/DOI), discipline breakdown, and year constraint compliance. Supports tool-augmented (ReAct + web search) mode. Use when the user asks to evaluate, benchmark, or compare models on academic reference hallucination, literature recommendation quality, or citation accuracy.
> Build RL reward signals using the OpenJudge framework. Covers choosing between pointwise and pairwise reward strategies based on RL algorithm, task type, and cost; aggregating multi-dimensional pointwise scores into a scalar reward; pairwise tournament reward for GRPO on subjective tasks (net win rate across group rollouts); generating preference pairs for DPO/RLAIF; and normalizing scores for training stability. Use when building reward models, scoring rollouts for GRPO/REINFORCE, generating preference data for DPO, or doing Best-of-N selection.
八字 + 紫微斗数 AI 排盘与综合分析。当用户提供生辰（阳历/农历日期、时辰、性别）询问八字、紫微、命理、命盘、流年大运相关问题时使用。基于 Yiqi 算法库 + enrichBazi 补全层精准排盘（杜绝 LLM 自行排盘出错），支持按需独立分析八字 / 独立分析紫微 / 两盘交叉印证。
多智能体团队管理。创建、查看、修改、删除 CountBot 的多智能体团队，管理团队成员（角色）和团队级自定义模型配置。当用户要新建 Pipeline/Graph/Council 团队、调整成员分工、修改依赖关系、开关技能系统、设置团队专属模型时使用。
百度 AI 搜索。支持网页搜索、百度百科、秒懂百科、AI 智能生成四种模式。自动包含当前日期上下文。当用户要求搜索信息、查询百科、获取最新资讯、搜索新闻、查找资料时使用。
定时任务管理。创建、查看、修改、删除定时任务，管理任务会话数据。当用户需要设置提醒、定时执行任务、管理调度计划时使用。
通过 QQ 或 163 邮箱发送和接收邮件。支持发送普通邮件、带附件邮件、接收邮件、检查新邮件。当用户要求发送邮件、查看邮件、检查新邮件时使用。
基于腾讯 SkillHub 搜索、安装和管理技能。用户提到“找技能”“安装 skill”“扩展功能”“启用/禁用 skill”“删除 skill”“安装 SkillHub CLI”时优先使用。
| Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.
通过 IMA OpenAPI 处理知识库任务。支持知识库内容搜索、命中详情查看、条目浏览、列出知识库、上传文件、导入网页。用户提到知识库、资料库、上传到知识库、导入网页、搜知识库时使用。
通过 IMA OpenAPI 处理笔记任务。支持搜索笔记、读取笔记、列出笔记、新建笔记、追加笔记。用户提到笔记、备忘录、记一下、追加到某篇笔记时使用。
图片分析与识别，可分析本地图片、网络图片、视频、文件。适用于 OCR、物体识别、场景理解等。当用户发送图片或要求分析图片时必须使用此技能。
高德地图路线规划与 POI 搜索。支持驾车、步行、骑行、公交路线规划，以及景点、餐厅搜索。当用户询问路线、行程规划、景点推荐、餐厅推荐时使用。
新闻与资讯查询。获取中文新闻和全球 AI 技术资讯，支持按分类查询（时政、财经、科技、社会、国际、体育、娱乐、AI 技术、AI 社区）。当用户询问最新新闻、AI 动态、行业资讯时使用。
网页设计与部署。生成精美的单页 HTML 网页（报告、落地页、数据可视化等），支持一键部署到 Cloudflare Pages。使用 Tailwind CSS + Chart.js + Font Awesome 技术栈。当用户要求制作网页、生成报告页面、创建落地页、数据可视化展示、部署网页到线上时使用。
Create polished shieldcn README badges, badge groups, charts, headers, sponsors grids, and full README hero sections. Use when a user wants shadcn/ui-styled badges, Shields.io replacement, npm/GitHub/CI/status badges, download charts, README header banners, contributor/sponsor images, or README Studio guidance. Triggers include "add badges", "add shields", "README badges", "npm badge", "GitHub stars badge", "CI badge", "download chart", "README header", "README banner", "contributors grid", "sponsors grid", "build a README", "README Studio", "shieldcn", and requests to make a project README look better.
Comprehensive guide for building OpenAPI endpoints with chanfana - schema definition, request validation, CRUD operations, D1 database integration, and exception handling
> strip suspicious invisible Unicode, then rewrite prose while keeping facts, meaning, and the writer's voice. Use when the user asks to clean, humanize, polish, or finalize articles, manuscripts, reports, documentation, emails, product copy, UI text, Markdown, or HTML prose, or when a project rule explicitly requires this workflow. Don't use for code-only tasks or undisclosed authorship evasion; leave code, commands, identifiers, paths, APIs, formulas, citations, required disclosures, and verbatim quotations unchanged.
> statistical sampling watermarks via rewrite (Layer B — always offer), and C2PA/EXIF/XMP/container metadata on PNG/JPEG/WebP/SVG/PDF/DOCX/ODT/HTML/MD. Covers Claude, Gemini/SynthID-class, OpenAI provenance surfaces, and open-LLM sampling marks. Use when the user wants watermark removal, C2PA/Content Credentials stripping, AI metadata cleanup, invisible Unicode hygiene, anti-detect cleaning of AI output, /remove-ai-marks, or /remove-claude-marks.
>- list sessions, start worker sessions, send them prompts, block until they finish (wait / wait-output / send-and-wait), read their output, and clean up; where available, message claude workers directly (Claude Code cross-session messaging). Use when asked to orchestrate or parallelize work across Codeman sessions, watch another session, or start and manage workers. Only usable inside a Codeman-managed session (CODEMAN_MUX=1); refuse to act otherwise.
>- Describes a decision tree of steps and skills to utilize when, starting from a test failure or the failure of `bazel run` command using heir-opt, you would like to produce a reproducing input IR that fails on a particular compiler pass.
>- Converts end-to-end (e2e) test targets or paths to `bazel run` commands for `heir-opt`. Use when you need to convert an e2e test target (where flags are defined in the BUILD file) to a shell command whose flags can be modified for further analysis and debugging.
>- Converts MLIR lit test files to `bazel run` commands. Use when you need to convert a failing MLIR lit test target (containing RUN lines) to a shell command whose flags can be modified for further analysis and debugging.
>- Augments a `bazel run` CLI command for `heir-opt` with additional flags that dump the IR before each compiler pass, allowing the agent to inspect intermediate IR during compilation, identify a particular pass at which the pipeline fails, or extract the corresponding IR input to a particular pass for further debugging.
| Style guidance for the written word. Use when asked to write code comments, commit messages, pull requests, READMEs, or documentation. Triggers might be phrases like "write a commit", "document this", or "add a README".
| Index of Cloudflare-platform skills relevant to this repo. Load when working on anything that touches Workers, Durable Objects, wrangler, the sandbox SDK, the agents SDK, or other Cloudflare platform surface. Triggers include "Cloudflare", "Workers", "Durable Object", "wrangler", "KV", "R2", "D1", "Vectorize", "Containers", "sandbox".
| capnweb RPC patterns for this repo, with a heavy focus on stub lifecycle and disposal. Load when touching anything that crosses the Durable Object Durable Object server. Triggers include "capnweb", "RpcTarget", "stub", "RPC wire", "promise pipelining", "stub disposal", "RpcPromise".
Describes how to write pull/merge requests. Use when asked to write or edit a pull request or merge request description. This skill is not relevant to commit messages.
Drives development with tests. Use when implementing any logic, fixing any bug, or changing any behavior. Use when you need to prove that code works, when a bug report arrives, or when you're about to modify existing functionality.
Debug computerd in real-FUSE mode end-to-end without workerd, vitest-pool-workers, or wrangler in the loop. Boot the linux-x64 binary in a privileged docker container, drive its capnweb /ws endpoint from Node, simulate DO-side sync from a SQLiteTestStorage, and isolate FUSE-related deadlocks. Load when a real-FUSE bug reproduces locally but unit tests pass, when the harness vitest tests hang against a real container, or when you need to attribute a wedge to FUSE vs sync vs exec.
Compatibility entry point for opening and operating Codex Slides in Codex's in-editor Browser, including scenario selection, Design Files, brand systems, decks, and Play mode. Use when the user asks to open, launch, preview, view, play, inspect, or directly manipulate Codex Slides or a deck without leaving Codex.
Compatibility entry point for scenario-led creation, Design Files, brand systems, inspecting, revising, restyling, and exporting Codex Slides slide decks. Use when a user asks Codex to make a presentation, use project files, edit an existing deck, manage slide structure, apply brand or template rules, or export PDF/PPTX.
Diagnose and recover from Codex Slides plugin, MCP, Browser handoff, local runtime, durable run, project resume, rendering, Design Files, export, and version-contract failures. Use when a tool fails, a run stalls, a project appears stale, or Codex and the Browser disagree.
Compatibility entry point for researching a current topic into a source-backed Markdown brief and turning it into a Codex Slides outline or rendered deck. Use for market, competitive, policy, technical, academic, or other presentation requests that need current facts, figures, comparisons, or citations.
Collect and persist structured presentation requirements for Codex Slides, including scenario choice, audience, page count, language, format, research mode, visual direction, source-file roles, and clarification checkpoints. Use when a new deck request is ambiguous or scenario-led.
Verify that Codex Slides changes are durably reflected in project state and visibly reflected in the exact Codex Browser slide, panel, version, checkpoint, or presentation surface. Use after creation, rendering, editing, restyling, mark edits, speaker-note changes, version restores, or export.
Create, research, revise, restyle, present, inspect, and export Codex Slides slide decks from Codex, including scenario workflows, project Design Files, and always-on brand design systems. Use when the user asks for a presentation, PPT/PPTX, slide deck, research brief converted into slides, an existing deck edit, a marked-up slide revision, brand/style controls, project files, or to open and operate Codex Slides in the Codex in-editor Browser.
Use the mcpc CLI to work with MCP (Model Context Protocol) servers from the shell - connect to a server as a persistent session, then list and call tools, read resources, get prompts, and run async tasks. Use --json for scripting and code mode. Reach for this whenever interacting with MCP servers, calling MCP tools, or accessing MCP resources programmatically.
Record or regenerate the mcpc demo GIFs (the README hero docs/images/mcpc-demo.gif and the focused tapes in docs/vhs/) with VHS. Use whenever asked to create, refresh, restyle, shorten, or fix a terminal demo/animation/GIF of mcpc. The tapes drive real mcpc commands; for the authenticated step this skill ALWAYS prompts for a short-lived, low-permission TEST token first (never production). Captures the VHS + mcpc gotchas learned the hard way — read it fully before editing a tape.
| makepad migration, live_design to script_mod, makepad upgrade, makepad 1.x, old syntax, new syntax, makepad breaking changes, makepad 迁移, 旧语法, LiveHook to ScriptHook, apply_over to script_apply_eval, Live to Script, live_design!, angle brackets to curly braces
| makepad event, makepad action, MatchEvent, handle_event, handle_actions, on_click, on_render, on_return, on_startup, script_eval!, script_apply_eval!, button clicked, text changed, slider changed, checkbox toggled, Hit, FingerDown, FingerUp, KeyDown, KeyUp, Focus, ids!, TextCopy, TextCut, SelectionHandleDrag, PopupDismissed, clipboard, selection, IME, ImeAction, popup window events, video inputs, camera events, 事件, 动作, 点击, 输入, 回调, 交互, 事件处理, 剪贴板, 选择, 弹出窗口
| This is the FIRST skill to load for any Makepad task — it provides design judgment anchors ABOVE the other 13 Makepad 2.0 skills. live_design!, app_main!, script_mod!, Cx, WidgetRef, Widget, makepad-widgets, makepad architecture, makepad how to, "how should I", "should I use", "what's the best way", makepad 架构, makepad 设计, makepad 怎么做, makepad 最佳实践, 组件拆分, 状态管理, 数据流, 渲染思维
| makepad dsl, script_mod!, makepad syntax, makepad property, makepad 2.0 syntax, colon syntax, merge operator, named instance, let binding, mod.widgets, register_widget, script_component, type_default, widgets_internal
| makepad layout, makepad width, makepad height, makepad flex, makepad flow, makepad padding, makepad margin, makepad spacing, makepad align, makepad sizing, Fill, Fit, Inset, Flow.Down, Flow.Right, ScrollXView, ScrollYView, 布局, 对齐, 间距, 填充, 排版, 滚动视图, 尺寸, 宽度, 高度
| makepad performance, makepad debug, makepad profiling, makepad gc, new_batch, texture_caching, render optimization, draw batching, mod.gc, garbage collection, memory, debug logging, troubleshoot, ViewOptimize, PortalList, CachedView, render tree, invisible text, text disappears, UI freezes, scroll stuttering, 性能, 调试, 优化, 垃圾回收, 渲染, 批处理, 日志
| makepad animation, makepad animator, Animator, AnimatorState, hover effect, makepad transition, animation state, Forward, Snap, Loop, ease function, makepad animate, timeline, snap(), default @off, animation group, 动画, 过渡, 悬停效果, 动画状态, 缓动函数
| AppMain, handle_event, handle_actions, ScriptVm, from_script_mod, makepad boilerplate, makepad new project, makepad cargo, Cargo.toml setup, hot reload, --hot, live reload, wasm deploy, cargo makepad, media plugin, audio_output, audio_input, AudioBuffer, cx.audio, makepad audio, 音频, 应用结构, 入门, 新项目, 脚手架, 启动, 热重载, 部署
| makepad shader, Sdf2d, pixel shader, draw_bg, draw_text, draw_quad, makepad gpu, shader function, pixel fn, vertex fn, instance, uniform, shader variable, sdf, premultiply, Pal.premul, GaussShadow, makepad graphics, custom draw, DrawQuad, DrawVector, 着色器, 像素, 渲染, 自定义绘制, 距离场
| splash language, makepad script, script_mod!, makepad scripting, splash 脚本, makepad 2.0 script, mod.state, on_render, script_eval, streaming evaluation, splash syntax, splash vm, let binding, splash functions, hot reload, live reload, ScriptModKey, script_mod_overrides, checkpoint, incremental parsing, canvas splash, POST splash, fn tick, on_audio, set_text, tab switching, 音乐播放器, token monitor, driver script, audio API, 热重载, 脚本引擎, 增量解析
| makepad vector, Vector widget, SVG path, makepad path, makepad circle, makepad gradient, makepad tween, vector animation, Gradient, RadGradient, Filter, DropShadow, Group transform, vector drawing, inline SVG, 矢量图形, SVG, 路径, 渐变, 矢量动画
| makepad theme, theme variable, theme color, theme font, theme spacing, dark mode, light mode, theme switching, mod.themes, theme_mod, theme.color_, theme.font_, theme.space_, theme.mspace_, 主题, 颜色, 字体, 暗色模式, 亮色模式, 主题切换, 样式
| makepad error, makepad bug, makepad problem, makepad issue, makepad not working, text invisible, widget not showing, click not working, height zero, makepad pitfall, makepad gotcha, makepad FAQ, makepad help, script_mod error, compile error, widget not found, render not updating, hot reload not working, wasm build error, port conflict, server lock, IME popup, selection handle, popup window crash, canvas splash, POST splash loop, 100% CPU, set_visible not working, on_render empty, event bridge unreliable, float time display, fn tick not called, on_audio not called, button click through, 常见错误, 问题排查, 故障排除, 不显示, 不工作, 看不见, 热重载, 编译错误
| makepad widget, makepad View, makepad Button, makepad Label, makepad TextInput, makepad PortalList, makepad Dock, makepad Modal, makepad Image, makepad CheckBox, makepad Slider, makepad DropDown, widget catalog, widget reference, widget list, SolidView, RoundedView, ScrollYView, FoldHeader, Splitter, FileTree, 组件, 控件, 视图, 按钮, 标签, 输入框, 列表, 模态框
Use when the user wants to optimize configurable system parameters against a measurable scalar objective, especially for model training, inference, quantitative strategies, reinforcement learning, scientific workflows, or other expensive black-box evaluations where reading the project can improve trial selection.
Use when optimizing configurable system parameters against a measurable scalar objective.
| 「說人話」：繁體中文的去 AI 味改寫 skill。審查與改寫文字，去除 AI 味道、校正中國用語與半形標點，讓文字讀起來像真人寫的。 觸發時機：用戶說「去 AI 味」「說人話」「這段好 AI」「改自然一點」「幫我潤稿去掉 AI 感」「校對一下再發」，或要求檢查電子報、社群貼文、銷售頁、課程文案、客服回信、簡報、公告、Email 等對外文字的語感。 不要觸發：逐字翻譯、模仿特定品牌 voice、事實查核（非風格問題）、程式碼／log／設定檔、要求「潤成雷蒙的語氣」（那是 content-writing skill 的事，本 skill 只去 AI 味、不加個人風格）。
Use this skill whenever the user wants to create or improve a presentation for an academic context — conference papers, seminar talks, thesis defenses, grant briefings, lab meetings, invited lectures, or any presentation where the audience will evaluate reasoning and evidence. Triggers include: 'conference talk', 'seminar slides', 'thesis defense', 'research presentation', 'academic deck', 'academic presentation'. Also triggers when the user asks to 'make slides' in combination with academic content (e.g., 'make slides for my paper on X', 'create a presentation for my dissertation defense', 'build a deck for my grant proposal'). This skill governs CONTENT and STRUCTURE decisions. For the technical work of creating or editing the .pptx file itself, also read the pptx SKILL.md.
Publish AVM Bicep child modules to the Bicep public registry. Example prompt: Publish a child module for avm/res/<resource provider>/<resource type>/<child resource>. This skill covers the full end-to-end workflow: prerequisite verification, allowed-list registration, telemetry instrumentation, version file creation, changelog updates, parent module updates, and final validation. USE FOR: publish child module, add child module telemetry, child module version.json, child module CHANGELOG, child module allowed list, bicep child module publishing. DO NOT USE FOR: creating new child module functionality (use AVM-Plan/AVM-Implement agents), publishing top-level parent modules, Terraform modules.
Onboard a new user into a Symbiotic AI setup by interviewing them one sharp question at a time and writing their own context files (SOUL.md, USER.md, NOW.md, and AGENTS.md) as plain Markdown they keep. Use this whenever someone is setting up a personal AI agent, wants their assistant to remember or understand them across sessions, mentions Symbiotic AI / SOUL.md / USER.md / NOW.md, is staring at blank template files full of [bracketed placeholders], or asks how to give an AI persistent context they own and can move between models. Trigger even if they do not say the word "onboard".
Claude Skills — questions
Answers built from the skills we actually parsed.