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. 80 149 files from 1 774 authors, of which 62 489 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.
>- Use when Codex needs Chinese-language Verilog or RTL design, existing-RTL analysis, verify-repair planning, controlled improvement planning, semantic comparison, debugging, troubleshooting, independent static lint, self-checking testbench scaffolds, or ASIC-quality review for a Verilog-target design, including synthesizable Verilog-2001 RTL, local or remote Vivado/xsim validation, artifact extraction, and workflow trace diagnosis.
视频/音频转文字 + 核心提炼。USE WHEN 用户提到：转录、转文字、字幕、视频转文字、音频转文字、抓字幕、YouTube转文字、B站转文字、视频笔记、transcript、提炼视频重点、视频总结。
Use when building or debugging WordPress Interactivity API features (data-wp-* directives, @wordpress/interactivity store/state/actions, block viewScriptModule integration, wp_interactivity_*()) including performance, hydration, and directive behavior.
Use when configuring, running, or fixing PHPStan static analysis in WordPress projects (plugins/themes/sites): phpstan.neon setup, baselines, WordPress-specific typing, and handling third-party plugin classes.
Use when building, extending, or debugging WordPress REST API endpoints/routes: register_rest_route, WP_REST_Controller/controller classes, schema/argument validation, permission_callback/authentication, response shaping, register_rest_field/register_meta, or exposing CPTs/taxonomies via show_in_rest.
Use when building UIs leveraging the WordPress Design System (WPDS) and its components, tokens, patterns, etc.
Accessibility testing for web applications using Playwright (@playwright/test), TypeScript, and axe-core. Use to write, run, or debug WCAG 2.2 AA checks, keyboard and focus tests, ARIA/semantic validation, accessible names, form labels, color contrast, or screen-reader test patterns. Keywords: accessibility, WCAG, axe-core, keyboard navigation, focus management, ARIA.
Test REST and GraphQL endpoint contracts using Playwright request fixture (TypeScript) or REST Assured (Java). Use for standalone API tests covering schemas, auth, status/error handling, pagination, idempotency, rate limits, or contract checks; not for browser E2E specs. Keywords: REST, GraphQL, API contract, schema validation, REST Assured.
A guided interview to challenge and validate QA automation plans, test strategies, and framework designs before implementation. Use when the user wants to validate a test architecture, challenge a testing decision, prepare an AI-assisted testing rollout, or uses any "grill" trigger phrase (grill my test plan, audit my QA automation framework, challenge my QA strategy, review my test architecture).
Govern Playwright TypeScript regression suites across many tests. Use when asked to plan, select, tier, execute, or optimize suites with risk/change analysis, tags, CI/CD, sharding, flaky-test management, or suite-health metrics; not for authoring one UI spec. Keywords: regression strategy, smoke tests, test selection, CI pipeline, flaky tests, test sharding, impact analysis, git diff.
Author and maintain versioned Playwright (@playwright/test) TypeScript UI specs for browser user flows. Use when asked to create, run, debug, or refactor E2E tests, form/navigation/auth flows, responsive checks, UI mocking, fixtures, Page Objects, or visual comparisons. Use api-testing for standalone REST/GraphQL contracts and playwright-cli for live browser sessions. Keywords: E2E spec, Playwright test, POM, fixtures, UI regression.
Create QA artifacts from requirements: test plans, test conditions/cases, bug reports, regression suites, traceability, and exploratory charters. Use for test planning, test design, defects, coverage, or QA deliverables. Applies ISTQB risk-based techniques and loads templates only when needed. Keywords: test plan, test case, bug report, traceability, regression suite, QA artifact.
Drive a live browser from the CLI with playwright-cli to navigate, interact, snapshot, and capture evidence. Use for ad-hoc browser commands, page inspection, screenshots, traces, network mocking, session management, or interactive debugging—not authoring @playwright/test specs. Keywords: playwright-cli, browser automation, live session, snapshot, console, tracing.
Accessibility testing toolkit using Selenium WebDriver 4+ with Java 21+ and axe-core engine. Use when asked to validate WCAG 2.2 AA compliance, scan pages or components for a11y violations, test keyboard navigation, audit color contrast, check ARIA semantics, generate accessibility reports, filter axe rules, debug screen reader issues, or implement POUR principles (perceivable, operable, understandable, robust).
Author and maintain versioned Selenium WebDriver tests with Java and JUnit 5. Use for creating, debugging, or running Selenium specs, implementing Page Objects, handling explicit waits, capturing screenshots, or setting up Maven test projects. Supports Chrome, Firefox, and Edge. Keywords: Selenium WebDriver, Java, JUnit 5, Page Object Model, explicit waits, Maven, screenshots.
Use when user asks to generate JeecgBoot CRUD code, create a new module, add/modify fields on existing module, or says "代码生成", "生成代码", "创建模块", "新增功能", "建表", "加字段", "加一个字段", "增加字段", "新增字段", "修改字段", "删除字段", "generate code", "new entity", "add field
Use when user asks to create/generate/edit/modify a BPM workflow, design a Flowable BPMN process, or says "创建流程", "生成流程", "新建流程", "设计流程", "画流程", "审批流程", "工作流", "BPM", "BPMN", "create flow", "create process", "new workflow", "generate workflow". Also triggers when user describes an approval chain like "先经理审批再HR审批" or mentions process nodes like "开始→审批→网关→结束". Also triggers for OA application creation: "创建OA应用", "创建审批单", "创建报销单", "创建请假单", "做一个OA表单带流程", "一键创建表单和流程", "create OA app", "create approval form with workflow". Also triggers for ANY operation on existing processes: "编辑流程", "修改流程", "删除监听器", "添加监听器", "删除节点", "添加节点", "修改节点", "配置节点", "流程中的", "edit process", "modify process", "delete listener", "add listener", "remove listener", "add node", "delete node", "configure node". Key rule: whenever user mentions a specific process name (like "网关测试") with any modification intent, this skill MUST be invoked FIRST before any manual API exploration.
Use when user asks to create/edit Online graph charts, data visualization, or says "创建图表", "生成图表", "新建图表", "做一个图表", "online图表", "数据图表", "柱状图", "折线图", "饼图", "统计图", "可视化", "chart", "graph", "create chart", "generate chart", "bar chart", "line chart", "pie chart". Also triggers when user describes chart requirements like "做一个销售柱状图" or mentions data visualization like "用图表展示男女比例".
JeecgBoot UniApp3 移动端 CRUD 代码生成器。Use when user asks to generate UniApp3/mobile/APP CRUD pages, create mobile list/form pages, or says '生成移动端代码', '生成APP页面', 'uniapp代码生成', '移动端CRUD', '生成uniapp页面', '手机端页面', '移动端模块', 'generate uniapp code', 'mobile CRUD', 'uniapp page', 'APP端代码', '生成小程序页面', '生成H5页面'. Also triggers when user mentions generating mobile pages for an existing backend module, or wants to add mobile support to JeecgBoot modules. Even if user just says '给XX模块加个移动端页面' or '做个手机端的XX功能', this skill should trigger.
> JeecgBoot AI 编排流程（AIFlow）全生命周期管理——通过自然语言描述需求，自动创建、编辑、查询、删除、调试、发布 AI 编排流程。 只要用户意图涉及「AI编排」「AIFlow」就必须使用本技能，包括但不限于： 创建 AI 编排流程（"做一个AI流程"、"创建aiflow"、"新建编排"、"做一个知识库问答流程"、"创建一个大模型对话流程"）， 修改已有流程（"给流程加个节点"、"改一下LLM的提示词"、"修改流程"）， 查询流程（"查看流程列表"、"有哪些AI流程"）， 删除流程（"删除流程"、"移除XX流程"）， 调试运行流程（"调试流程"、"运行流程"、"测试流程"）， 发布管理（"发布流程"、"取消发布"）， 复制流程（"复制流程"、"克隆流程"）。 关键词触发：aiflow、ai-flow、AI编排、AI流程、编排流程、大模型流程、知识库流程、LLM流程。 注意：本技能仅处理 AI 编排流程（AIFlow），不处理 BPMN 工作流（使用 jeecg-bpmn）、 不处理简流（使用 jeecg-lowcode-miniflow）。
JeecgBoot 开发规范（仅手动触发）。⚠️ 本技能只在用户显式输入 /jeecg-dev 命令时使用，禁止自动触发——编写/修改 JeecgBoot 代码、应用 GitHub PR/issue 改动、修复 bug、新增功能、重构、代码生成等场景都不要自动调用本技能。内容涵盖 update-begin/end 痕迹注释、命名规范、实体/控制器/服务模式、API 约定、建表规则与修改日志实践。MANUAL ONLY: invoke ONLY when the user explicitly runs the /jeecg-dev command. Do NOT auto-trigger on any code editing, bug fix, PR/issue application, refactoring, or code generation.
>- JeecgBoot Online表单（cgform）全生命周期管理——通过API自动创建/编辑数据库表和表单配置， 支持单表、主子表、树表，26种控件类型，以及JS/Java/SQL增强、权限配置、数据CRUD、积木报表集成。 只要用户意图涉及「Online表单」就必须使用本技能，包括但不限于： 创建或配置数据库表（"建一张请假表"、"创建online表"、"做一个带下拉选择的表"、"低代码表单"、"在线表单"、"配置表"）、 修改已有Online表字段（"加个字段"、"改字段类型"、"加子表"、"删除字段"）、 配置表单增强（"JS增强"、"自定义按钮"、"表单联动"、"Java增强"、"SQL增强"）、 配置权限（"字段权限"、"按钮权限"、"数据权限"、"授权给角色"）、 管理表单数据（"插入数据"、"查询记录"、"导出CSV"、"造测试数据"）、 以及关联积木报表（"给这个表加报表"、"集成打印"）。 即使用户只描述了业务需求而没说"online"（如"做一个员工信息管理功能，包含姓名、部门下拉、入职日期"）， 只要涉及元数据驱动的表单配置，也应触发本技能。 注意：不要与「设计器表单」(desform)混淆——desform是拖拽式表单设计器，用skill jeecg-desform处理； 也不要与「Online报表」(cgreport)或「Online图表」(onlchart)混淆——它们是SQL驱动的只读展示。
Use when user asks to generate JeecgBoot CRUD code, create a new module, add/modify fields on existing module, or says "代码生成", "生成代码", "创建模块", "新增功能", "建表", "加字段", "加一个字段", "增加字段", "新增字段", "修改字段", "删除字段", "generate code", "new entity", "add field
Use when user asks to create/edit/query Online reports, SQL reports, data reports, or says "创建报表", "生成报表", "新建报表", "查询报表", "online报表", "SQL报表", "数据报表", "统计报表", "create report", "generate report", "data report". Also triggers when user describes report requirements like "做一个销售统计报表", mentions JeecgBoot cgreport/online report, or says "查看现有报表" / "列出所有报表". This skill handles Online 报表 (SQL-driven data display/reports), not Online forms (cgform) or designer forms (desform).
JeecgBoot 系统主数据查询与管理。Use when user asks to query/create/manage system master data, or says "查询角色", "查询用户", "查询部门", "查询字典", "创建字典", "创建角色", "查岗位", "查职务", "查租户", "查数据源", "查定时任务", "系统主数据", "query roles", "query users", "query depts", "create dict", "create role", "master data". Also triggers when other skills (desform, bpmn, codegen) need to look up or create roles, users, departments, dictionaries, or positions as dependencies — follows "先查后建" (query-first-create-later) principle.
Use when user asks to create/design a big screen (大屏), full-screen data visualization, or says "创建大屏", "生成大屏", "新建大屏", "设计大屏", "做一个大屏", "BI大屏", "数据大屏", "可视化大屏", "监控大屏", "create big screen", "design big screen", "BI visualization big screen". Also triggers when user describes big screen requirements like "做一个销售数据大屏" or mentions full-screen display like "展厅展示", "监控室大屏". Make sure to use this skill for big screens (大屏) — NOT dashboards (仪表盘/看板), which use a completely different layout and styling system.
积木报表生成器 — 自然语言描述报表需求或提供截图，自动生成积木报表（支持数据报表、打印报表、分组报表、循环报表、数据填报等全类型）。Use when user says "积木报表", "jmreport", "Excel报表", "数据填报", "可视化报表", "打印报表", "分组报表", "循环报表", "按照截图生成报表", "创建积木报表", "做一个可视化报表", "积木设计器", "create jimureport", "visual report". Also triggers when user describes report requirements involving Excel-like layouts, data binding with #{}, or multi-sheet reports, or provides a screenshot to generate a report.
Use this skill before running, or recommending, any Docker command that deletes, wipes, resets, or otherwise irreversibly changes state — even if the user just says to "clean up", "clear the cache", "start fresh", "wipe everything", "nuke it", "reset", "force remove", or "tear down" Docker resources. Covers generic Docker CLI destructive operations not owned by a more specific skill — `docker rm`, `docker rm -f`, `docker container prune`, `docker kill`, `docker system prune`, `docker rmi`/`docker image rm`, `docker image prune -a`, `docker network rm`, `docker network prune`, `docker builder prune`, `docker buildx rm`, `docker context rm`, and standalone (non-Compose) `docker volume rm`/`docker volume prune`. Also indexes destructive commands owned by other Docker skills (Compose, sandbox, Desktop). Core rule — state exactly what will be lost and get explicit confirmation first, except narrow, low-friction Tier 1 container cleanup.
Use this skill when setting up, initializing, or Dockerizing a project, even if the user doesn't explicitly mention Docker but describes a need for containerized local development, adding a database or cache dependency, or running services without host-level installs. Covers Dockerfile, compose.yaml, and .dockerignore creation with Docker best practices.
Use this skill when creating, modifying, or debugging Docker Compose configurations, even if the user just says they need to wire services together, add a database to their stack, or set up a local development environment with multiple containers. Covers service definitions, health checks, dependency ordering, volumes, networks, environment variables, and development overrides.
Use this skill when creating or editing an agent.yaml (or .yml/.hcl) configuration file for Docker Agent (cagent), including defining agents, models/providers, built-in or MCP toolsets, multi-agent teams with sub_agents. Even if the user just says they want to "build an AI agent with Docker", "make a coding agent config", "add a tool to my agent", or "set up a team of agents", this skill applies. Covers agent properties (model, instruction, toolsets, sub_agents, fallback), the models/providers sections, built-in toolsets (filesystem, shell, think, todo, memory, fetch), MCP toolset references, and named commands.
Use this skill when exposing a Docker Agent as a server (MCP, HTTP API, A2A, ACP, or OpenAI-compatible chat), distributing an agent via an OCI registry with `docker agent share`, or measuring agent quality with `docker agent eval`. Even if the user just says they want to "turn my agent into an MCP server", "let Claude Desktop use my agent", "publish my agent to Docker Hub", "push my agent like an image", or "test my agent in CI", this skill applies. Covers `serve mcp/api/a2a/acp/chat` listen addresses and auth flags, `share push/pull`, eval session JSON format, scoring metrics, and the `--baseline` regression gate.
Use this skill when authoring, planning, or running a declarative `sbxenv.yaml` file for Docker Sandboxes (`sbx env create/run/plan/exec/rm`), even if the user just says they want to "check in a sandbox config", "make onboarding reproducible for a sandbox", "run a setup script before the agent starts", or "define arguments for a shared sandbox environment". Covers the sbxenv.yaml schema (schemaVersion, agent, kits, workspace/additionalWorkspaces, args, env, secrets, registries, bindings, mcp, ports, sandboxOptions), host `lifecycle:` commands (initialize/postCreate/preRemove) and their approval-plan model, multi-file merge (`-f`-style deep merge and the user-level `.sbxenv.yaml` base layer), and file-write-protection (`sandboxOptions.writableEnvFiles`).
Use this skill when writing, reviewing, or optimizing Dockerfiles, even if the user just says their image is too large, their build is slow, or they need to harden a container for production. Covers multi-stage builds, layer caching, .dockerignore, non-root users, and image size optimization.
Use this skill when running a Docker Agent with `docker agent run`, choosing a safety/approval mode, using the `--sandbox` isolation flag, setting up aliases, or troubleshooting a run (missing credentials, worktrees). Even if the user just says they want to "run my agent", "make my agent auto-approve tool calls", "run this agent safely", or "why can't my agent see my API key", this skill applies. Covers `--safety` (strict/balanced/restricted/autonomous), `--yolo`, `--sandbox` and its network allowlist, `--worktree`, `docker agent alias`, and `docker agent doctor`.
Use this skill when creating, running, reattaching to, listing, stopping, or removing Docker Sandboxes (the standalone `sbx` CLI that runs AI coding agents in isolated microVMs), even if the user just says they want to "run claude in a sandbox", "isolate an agent from my repo", "give an agent its own git clone", or "clean up old sandboxes". Covers `sbx run`/`sbx create` (including the built-in agents claude, codex, cursor, devin, docker-agent, gemini, opencode, shell), workspace bind-mount vs `--clone` isolation, additional read-only workspaces, reattaching by `--name`, `sbx ls`/`stop`/`rm`/`prune`, `sbx exec`, `sbx cp`, and `sbx ports`.
Use this skill when configuring what a Docker Sandboxes (`sbx`) sandbox can reach on the network or which credentials it authenticates with, even if the user just says they want to "let the agent call an internal API", "block all network access", "give the agent a GitHub token", or "use a private registry image for a sandbox". Covers `sbx policy init/allow/deny/ls/inspect/log/check/rm network` (global and per-sandbox egress rules, deny-over-allow precedence) and `sbx secret set/set-custom/ls/rm/import` (service secrets, dynamic secrets via --ref/--command, and registry pull credentials with their host-pulls-only-by-default injection scope).
>-
Vast.ai Python SDK — high-level API for GPU instances, volumes, serverless endpoints, and billing.
Vast.ai CLI to manage GPU instances, volumes, serverless endpoints, and billing.
Find the most valuable commercial insight and the monetization point closest to lawful revenue for a project, product, service, website, community, content account, open-source tool, or business idea. Use when a user asks how to monetize, who pays, why people do not buy, what to charge, whether to keep building, what to stop, what to do next, or asks to continue or deepen an earlier business analysis. Answer the user's actual question before asking for more information and carry the analysis forward without repeating it. When the buyer, purchased result, or delivery ability is unknown, do not select them from industry stereotypes; use explicit conditional candidates and an evidence-gathering next step. Not for investment advice, income forecasts, get-rich-quick schemes, or guaranteed results.
> Create or update an evidence-backed living Product Requirements Document (PRD) and, when useful, linked context and phase execution files under tasks/. Use for feature planning, implementation scoping, autonomous agent work, or checked-off PRDs that must be validated, reviewed, and revised during this out, update the prd, create an execution plan.
Review implementation against provided markdown requirements, specs, PRDs, or phase docs; optionally apply focused fixes. Use when a user supplies .md file paths and asks to verify correctness/completeness, check PRD phase completion, find missing or overbuilt work, assess critical issues, refactor long files/functions, or update code to match the docs.
Generate a polished CHANGELOG.md and release-notes.md from a local git repository (or a captured `.git-log.txt` dump). Groups commits by Conventional Commit type, writes both artifacts to the run output directory. Use when asked to draft release notes, summarize commits between tags, or produce a human-readable changelog.
Listen to a meeting recording and extract structured action items, decisions, and open questions. Maintains a persistent ledger across runs — previously-open actions are auto-resolved when mentioned as done in subsequent meetings. Outputs `actions.csv` (importable to Linear/Asana/Notion) + `recap.md` (paste into Slack). Use when given a meeting recording and asked for a recap or action items.
Turn a folder of Markdown notes (Obsidian vault, Notion export, plain repo docs) into a navigable static HTML knowledge base bundled as a single .zip file. Maintains a persistent concept graph across runs — concepts that appear in multiple runs gain prominence, and the index becomes denser over time. Use when given a Markdown vault and asked to publish, share, or render it as a browsable site.
Draft professional emails based on context, tone, and recipient. Use for composing business emails.
Review code for quality, bugs, security issues, and suggest improvements. Use when asked to review, audit, or improve code.
Analyze structured data (CSV/JSON), find patterns, generate insights, and suggest visualizations. Use for data analysis tasks.
Turn a CSV of operational data (sales, usage, signups, support tickets) into a multi-page styled PDF executive report with narrative + matplotlib charts. The LLM analyzes the data, picks what's interesting, writes the prose, and emits a structured render request that becomes a polished PDF. Use when given a CSV and asked for a report, summary, or analysis.
Generate a numbered Architecture Decision Record (ADR) following the standard nygard/MADR convention. Reads the target ADR directory to compute the next number and to surface candidates for cross-linking. Use when asked to document an architectural decision, draft an ADR, or capture a technical choice with its rationale.
Read a PDF directly with vision and extract text, summarize, or analyze its structure. Use when the user passes a PDF file.
Read a batch of receipt images directly via vision, classify each into expense categories, optionally reconcile against a bank statement CSV, and produce a multi-sheet Excel workbook + a PDF summary. Use when given receipt photos and asked for an expense report.
Audit a website for SEO issues and track improvements over time. Use when analyzing website SEO performance.
Generate a complete Semgrep rule bundle (rule.yml + tests.md + README.md) from a CVE description and a bad-code example. Picks an appropriate severity, infers the right CWE/OWASP mapping, and produces a ready-to-commit rule with documentation. Use when asked to draft a Semgrep rule, encode a security pattern, or productize a security finding for the codebase.
Generate a real PowerPoint .pptx deck from a Markdown outline. Picks slide layouts (title / content / closing) based on the outline structure, applies a brand accent color, optionally adds speaker notes. Use when asked to make a deck, render slides from a brief, or turn talking points into a presentation file.
Browse websites and extract structured information. Use when the user needs data from a web page.
> Analyzes conversation transcripts to extract user corrections, patterns, and preferences, then proposes skill improvements. Use this skill when users provide corrections, express preferences about code style, or when patterns emerge from successful approaches. Can be triggered manually with /reflect or automatically at session end when enabled.
> Creates Python projects with proper structure, virtual environments, and dependency management. Use when users request to create a new Python project, set up a Python development environment, or initialize a Python application with standard tooling.
Jacky Motion 2.0 的独立 SRT 自动录屏版。把中文口播稿与对应 .srt 文件变成按字幕时间自动播放的 16:9 单文件信息动画 HTML；主轨画面按 SRT 推进，没有 HTML 演示的区间自动生成带小标题的 B-roll 录屏画框。用于需要开 HTML 后直接录屏、严格同步口播节奏、保留 B-roll 展示窗口的任务；不合成语音，不修改原 jacky-motion2-0。
Claude Skills — questions
Answers built from the skills we actually parsed.