AI Skills Hub - Browse 180,000+ Agent Skills

Build Convex schemas, queries, mutations, actions, and client usage with strict validators and indexes. Use for data modeling, function authoring, argument/return validation, and performance guidance. Use proactively when work touches convex/schema.ts, functions, or api.* references. Examples: - user: "Design tables for multi-tenant app" → defineSchema/defineTable with indexes - user: "Write a mutation" → args/returns validators + auth checks - user: "Optimize query" → add index and withIndex range expression - user: "Use useQuery" → show generated hook usage

Automatically generate project documentation from Python source code. Use when creating README, API docs, or architecture diagrams from docstrings and type hints.

Use when you need to understand authority, resolve conflicts, trace governed_by chains, or validate what governs a document.

重大事故复盘分析报表，面向 FO/BO Leader。分析重大事故 (P1/P2) 的影响面与时间线、根因与控制点、改进项闭环追踪；支持单次复盘与横向对比。支持 DOCX 和 HTML 输出，中英文双语。

Specialized for# Claude.ai Specialized Skill

Build and debug Hatchet workflows (Python/TypeScript/Go). DAGs, events, cron, rate limiting, durable tasks.

Create a release PR with version bump and changelog update

Windows registry operation safety guidelines for context menu editing. Use when modifying, adding, or deleting registry keys under HKCR (HKEY_CLASSES_ROOT), implementing enable/disable toggles, or working with shell/shellex entries. Triggers on: any code that calls Registry.ClassesRoot, CreateSubKey, DeleteSubKeyTree, or modifies context menu registry paths.

Review local git changes with tuicr TUI via tmux split pane

Use when storing, fetching, or managing context capsules. Helps with session handoffs, multi-agent coordination, or preserving decisions across sessions.

Use this skill to validate that all IStorage implementations (MemoryStorage, SupabaseStorage) return identical object shapes. Critical for factory pattern to work correctly.

Provides robust mechanisms for agents to dynamically load and execute markdown workflows.

Deploy receiver code and OpenHAB configuration to the Raspberry Pi server. Use when deploying receiver.py changes, updating OpenHAB items/rules/sitemaps, performing full deployments, or previewing deployments with dry-run.

Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.

Execute MySQL operations through Docker container client. Use when you need to: (1) Execute SQL queries or modifications on remote MySQL databases, (2) Run DDL statements (CREATE/ALTER/DROP tables), (3) Execute SQL script files, (4) Export query results, (5) Perform database migrations or bulk operations. Supports both single SQL commands and batch file execution.

使用企业微信机器人api，发送企业微信群聊通知

Create a git worktree for PRD work with a descriptive branch name. Infers PRD from context or asks user.

夸克网盘文件操作 - 上传、下载、分享、管理文件。通过 quarkpan CLI 实现。

Searches and downloads high-quality, free images from Pixabay using the API. Use when the user needs visual assets (photos/illustrations) for materials.

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

Migrate bUnit test files from deprecated beta API (1.0.0-beta-10) to bUnit 2.x stable API. Use this when working on .razor test files in BlazorWebFormsComponents.Test that contain old patterns like TestComponentBase, Fixture, or SnapshotTest.

Use when creating or modifying database migrations in db/migrate. Covers reversibility, data safety, indexing, and column types.

Use when creating or modifying background jobs in app/jobs. Covers idempotency, thin jobs, ApplicationJob inheritance, and error handling.

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.

Bayesian modeling with PyMC. Build hierarchical models, MCMC (NUTS), variational inference, LOO/WAIC comparison, posterior checks, for probabilistic programming and inference.

Production-ready reinforcement learning algorithms (PPO, SAC, DQN, TD3, DDPG, A2C) with scikit-learn-like API. Use for standard RL experiments, quick prototyping, and well-documented algorithm implementations. Best for single-agent RL with Gymnasium environments. For high-performance parallel training, multi-agent systems, or custom vectorized environments, use pufferlib instead.

Query NCBI Gene via E-utilities/Datasets API. Search by symbol/ID, retrieve gene info (RefSeqs, GO, locations, phenotypes), batch lookups, for gene annotation and functional analysis.

Microscopy data management platform. Access images via Python, retrieve datasets, analyze pixels, manage ROIs/annotations, batch processing, for high-content screening and microscopy workflows.

텔레그램 그룹/채널에서 메시지를 수집하여 Markdown으로 저장하는 스킬. Telethon(User API) 기반으로 동작하며, 지정된 채팅에서 최근 N시간 동안의 메시지를 가져온다.

업비트 거래소와 연동하여 암호화폐를 매매하는 스킬. pyupbit 라이브러리 기반으로 동작하며, 시세 조회, 주문, 잔고 확인 등 전체 기능을 지원한다.

Routes DigitalOcean App Platform tasks to specialized sub-skills. Use when working with App Platform deployments, migrations, database configuration, networking, or troubleshooting.

Configure DigitalOcean Spaces (S3-compatible object storage) for App Platform apps. Use when setting up file uploads, static assets, CDN, access logging, or per-app credential management.

Migrate applications from Heroku, AWS, Render, Railway, Fly.io, or Docker Compose to DigitalOcean App Platform. Use when converting existing apps, mapping services, refactoring platform-specific code, or creating app specs from other platform configurations.

Configure domains, routing, CORS, VPC, static IPs, and inter-service communication for DigitalOcean App Platform. Use when setting up custom domains, subdomain routing, cross-origin API access, or secure database connectivity.

Configure DigitalOcean Gradient AI serverless inference and Agent Development Kit. Use when adding LLM inference, model access keys, serverless AI endpoints, or building AI agents with ADK on App Platform.

This skill should be used when the user needs to control the browser via HTTP API, supporting tab management, page content retrieval, script execution, Cookie operations, and more.

Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.

Expert assistance for working with the Nix ecosystem, including NixOS, Home Manager, and Nix Flakes. Provides package/option search capabilities, flake templates, debugging guides, and comprehensive documentation for Nix language and Nixpkgs. Use this skill when: (1) Searching for NixOS packages or options, (2) Creating or configuring Nix flakes, (3) Setting up development environments with Nix, (4) Writing Nix expressions or debugging Nix code, (5) Working with NixOS configurations, Home Manager, or any Nix-related tasks.

Build and deploy PostgreSQL-compatible serverless distributed SQL databases with Aurora DSQL - manage schemas, execute queries, and handle migrations with DSQL-specific requirements. Use when wanting a good solution for developing a scalable or distributed SQL database, user asks to use Amazon Aurora DSQL, or a project is already built with DSQL. Includes MCP tools for direct database interaction.

Turborepo monorepo build system guidance. Triggers on: turbo.json, task pipelines, dependsOn, caching, remote cache, the "turbo" CLI, --filter, --affected, CI optimization, environment variables, internal packages, monorepo structure/best practices, and boundaries.

Inline orchestration workflow for automated bug detection and fixing. Provides step-by-step phases for bug-hunter detection, priority-based fixing with bug-fixer, and verification cycles.

Translate PowerPoint (.pptx) files using a high-fidelity, context-aware batching strategy. Preserves formatting (bold, italic, colors) while ensuring file stability by avoiding geometry modifications. Supports DeepSeek (default), OpenAI, Gemini, and more.

使用 Whisper 将音频/视频转换为文字，支持词级别时间戳。Use when user wants to 语音转文字, 音频转文字, 视频转文字, 字幕生成, transcribe audio, speech to text, generate subtitles, 识别语音.

Convert local files to shareable URLs. Use this tool when: (1) You generate files that need to be shared with users - get accessible URLs instead of outputting raw content; (2) You generate HTML/web pages that need to reference assets (images, CSS, JS) - upload assets first to get URLs for embedding. Also supports transferring third-party URLs to your own domain.

Manage RHDH plugins - onboard, update, maintain, and triage plugins in the Extensions Catalog. Supports both Plugin Owners and Core Team workflows.

Read and interact with Apple Mail via osascript on macOS. Use when you need to: (1) List mail accounts, (2) List mailboxes/folders for an account, (3) Get messages from a specific mailbox, (4) Read message content. Works with Apple Mail app on macOS only.

Access WHOOP fitness tracker data via API, including recovery scores, sleep metrics, workout stats, daily strain, and body measurements. Use when the user asks about their WHOOP data, fitness metrics, recovery status, sleep quality, workout performance, or wants to track health trends.

Connect to Cloudflare API for DNS management, tunnels, and zone administration. Use when user needs to manage domains, DNS records, or create tunnels.

Discover and control Apple media/AirPlay devices (HomePod, Apple TV, AirPlay speakers) from macOS. Use when you want to scan for AirPlay devices, map names→IPs/IDs, pair/connect, and control playback/volume using pyatv (atvremote) and Airfoil.

Toolkit per testare applicazioni web locali con Playwright: verifica UI, screenshot e debug.

[Cosa misura questo criterio]

Suite completa de validacion para Sphinx y contenido RST. Usar para verificar builds, validar estructura, detectar errores, y asegurar calidad antes de commits.

Create high‑quality videos using Remotion (React + programmatic animation) and render to MP4.

Generate comprehensive impact reports for SQL suppression code changes in the MO leads pipeline. Use when analyzing bug fixes, rule changes, or modifications to suppression logic in mo_leads_with_suppression.sql or related files.

Comprehensive Word document creation, editing, and analysis. Use when working with .docx files: creating new documents, editing with tracked changes, adding comments, extracting text, or analyzing document structure.

Integrate lifecycle hooks across AI coding tools (Claude Code, Gemini CLI, Cursor, OpenCode) and any CLI. Use when: (1) installing/removing hooks, (2) creating OpenCode plugins, (3) setting up auto-formatting, testing, notifications, security policies, (4) wrapping CLI tools without hooks API. Triggers on: "add hook", "install hook", "hook integration", "PreToolUse", "PostToolUse", "beforeShellExecution", "auto-format", "notify on complete", "wrap CLI", "intercept command".

Sincroniza metadata de skills a las tablas "Auto-invoke Skills" en archivos AGENTS.md. Trigger: Después de crear o modificar skills, ejecuta sync para actualizar AGENTS.md.

量化回测（严格无未来函数、成本口径明确、可复现）。适用于：验证因子/入场出场规则/参数是否有效，或对比不同出场策略（MACD/布林带/止盈等）的收益-回撤-持有期表现；必须输出“可复核”的回测报告（区间、成本、执行假设、核心指标、局限性）。

Deterministically find license information for Python packages by checking PyPI metadata first, then falling back to Git repository LICENSE files using shallow cloning.

Debug and monitor GitLab CI/CD pipelines for merge requests. Check pipeline status, view job logs, and troubleshoot CI failures. Use this when the user needs to investigate GitLab CI pipeline issues, check job statuses, or view specific job logs.

Generate slack summaries of vLLM CI SIG Slack channel activity for the RHAIIS midstream release team

Export and upload the current chat conversation as a markdown file attachment to a JIRA ticket for later review and documentation.

Analyze Python package build complexity by inspecting PyPI metadata. Evaluates compilation requirements, dependencies, distribution types, and provides recommendations for wheel building strategies.

Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

Add source URLs to workdesk/sources.md one-by-one with validation and duplication checking. Use when user provides links to add to the journal. Does NOT generate summaries.

Implement a GitHub issue with automated PR creation

Right-sizes Technical Task Lists (TTLs) by scoring project complexity across multiple dimensions and adjusting task granularity to match scope. Use when a TTL has too many tasks for a simple project (over-engineering), too few tasks for a complex project (under-specification), or when task count needs validation against project size. Scores projects as Micro/Tiny/Small/Medium/Large/Enterprise and provides target phase and task counts. Prevents scope mismatch between project complexity and task breakdown detail.

Fetch and convert zread.ai documentation to markdown using a local toc.html. Use when the user provides a zread.ai docs base URL plus a toc file (or asks to follow toc links) and wants the docs saved as .md files via a Python script.

Bulletproof LinkedIn inbox monitoring with progressive autonomy. Monitors messages hourly, drafts replies in your voice, and alerts you to new conversations. Supports 4 autonomy levels from monitor-only to full autonomous.

Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.

Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.

Use when generating, parsing, or analyzing StoBe DFT calculation input files. Invoke for X-ray spectroscopy (NEXAFS/XANES), core-hole calculations, transition potential methods, or quantum chemistry workflows.

Capture solved problems as categorized documentation with YAML frontmatter for fast lookup

Orchestrate a configurable, multi-member CLI planning council (Codex, Claude Code, Gemini, OpenCode, or custom) to produce independent implementation plans, anonymize and randomize them, then judge and merge into one final plan. Use when you need a robust, bias-resistant planning workflow, structured JSON outputs, retries, and failure handling across multiple CLI agents.

Generate diagrams from text using Mermaid syntax. Use when asked to create flowcharts, sequence diagrams, class diagrams, ER diagrams, state diagrams, Gantt charts, pie charts, or any visual diagram. Converts Mermaid markdown to PNG, SVG, or PDF.

Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.

Kiểm tra xem domain có available để đăng ký không (hỗ trợ .jp, .co.jp, .com, .net, .ai, .io...)

创建基础模拟器件：NMOS、PMOS、MIM电容、多晶硅电阻、Via过孔堆叠。支持指定尺寸、指数、dummy结构等参数。

导出与查询：导出GDS文件、查询组件列表、获取组件详细信息等，用于版图输出和状态查询。

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

管理 oh-my-opencode 的 agent 和 category 模型配置。当用户需要查看当前模型配置、修改特定 agent/category 的模型、按提供商批量替换模型、或在取消/添加订阅时调整配置时使用此技能。触发关键词：oh-my-opencode 模型、agent 模型、更换模型、替换提供商、模型配置。

阿里云云效 DevOps 平台集成技能。提供代码管理、流水线、项目管理、组织管理、制品仓库、应用交付、测试管理等完整 DevOps 能力。当用户需要与云效平台交互时使用，包括：(1) 代码仓库操作（分支、文件、合并请求）(2) 流水线创建和运行 (3) 项目和工作项管理 (4) 组织成员管理 (5) 制品仓库查询 (6) 应用部署和发布 (7) 测试用例管理。触发词：云效、Codeup、Flow、Projex、AppStack、DevOps。

提供 HelloAGENTS 工作流入口与命令/模块导航，并处理 ~auto/~plan/~exec/~help 等指令；当用户输入 /helloagents、$helloagents 或任何 HelloAGENTS ~命令时使用。

Add burned-in subtitles/captions to video clips. Supports SRT/VTT subtitle files, customizable styling (font, size, color, position), and platform-specific presets for TikTok, YouTube Shorts, and Instagram Reels.

Trim and cut videos by timestamp with precision. Supports both stream copy (fast) and re-encoding (quality) modes. Use when you need to extract specific segments from videos, create clips from highlights, or cut unwanted portions.

Convert videos to 9:16 portrait format (1080x1920) for TikTok, YouTube Shorts, Instagram Reels, and Facebook Reels. Supports smart cropping (focus on faces/subjects), center cropping, and letterboxing. Maintains aspect ratio and quality.

Process multiple videos in batch mode for efficiency. Supports batch download from YouTube URLs, batch autocut for multiple videos, and batch export to multiple platforms. Generates consolidated reports with all clips.

Download videos from YouTube URLs. Use when user wants to download a YouTube video for processing, editing, or transcription. Supports different quality options, audio-only extraction, and playlist downloads.

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

Use when interpreting Culture Index surveys, CI profiles, behavioral assessments, or personality data. Supports individual interpretation, team composition (gas/brake/glue), burnout detection, profile comparison, hiring profiles, manager coaching, interview transcript analysis for trait prediction, candidate debrief, onboarding planning, and conflict mediation. Handles PDF vision or JSON input.

Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.

Manage Architecture Decision Records (ADRs) using adr-tools. Use this to initialize, create, list, and link ADRs to document architectural evolution.

Get stock prices, quotes, fundamentals, earnings, options, dividends, and analyst ratings using Yahoo Finance. Uses yfinance library - no API key required.

Manages project knowledge using ByteRover context tree. Provides two operations: query (retrieve knowledge) and curate (store knowledge). Invoke when user requests information lookup, pattern discovery, or knowledge persistence. Developed by ByteRover Inc. (https://byterover.dev/)

A workflow for generating professional educational videos with Chinese narration, whiteboard effects, and interactive annotations in Remotion.

Use when 需要在本地 HarmonyOS Markdown 文档中检索候选 API/组件并输出证据链，再在对话中完成二次筛选与总结时

extracting device parameters (Vth, SS, DIBL, Ion/Ioff) from IV or CV measurement data.

A robust, modular skill for programmatically managing Metabase Collections, Questions, Dashboards, Metrics, and Models.