AI Skills Hub - Browse 180,000+ Agent Skills

Import Plaud recording transcripts to Obsidian vault. Use when user wants to sync or import Plaud recordings.

Import Notion pages and databases to Obsidian with full markdown conversion and automatic hierarchical organization. Use when user wants to import from Notion, sync Notion content, migrate to Obsidian, or create local backups of Notion pages.

Techniques for handling 10M+ records in SAS - partitioning, indexing, hash objects, and optimization

全面的电子表格创建、编辑和分析，支持公式、格式设置、数据分析和可视化。当 Claude 需要处理电子表格（.xlsx、.xlsm、.csv、.tsv 等）时使用：(1) 创建带公式和格式的新电子表格 (2) 读取或分析数据 (3) 在保留公式的同时修改现有电子表格 (4) 在电子表格中进行数据分析和可视化 (5) 重新计算公式

将 Python 函数或模块封装为标准化的 FastAPI RESTful API 服务，包含统一响应、日志追踪、文档生成等功能

Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Agent needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification

字幕生成与烧录。转录→词典纠错→审核→烧录。触发词：加字幕、生成字幕、字幕

Performs SAST (Static Analysis Security Testing), dependency auditing, and secret scanning on the codebase.

Convex backend development patterns, validators, indexes, actions, queries, mutations, file storage, scheduling, React hooks, components, and testing. Use when writing Convex code, debugging Convex issues, planning Convex architecture, or writing Convex tests.

Manage Git branches and PRs using Graphite CLI (gt) instead of raw git commands. Use this skill when committing code changes, amending commits, creating branches, or submitting pull requests. Triggers on git commit, git push, creating PRs, amending changes, stacking branches, or any version control workflow.

Expert guidance for LazyVim Neovim configuration. Use when configuring Neovim with LazyVim, writing plugin specs, adding language servers, customizing keymaps, enabling extras, troubleshooting lazy-loading, or any LazyVim/lazy.nvim related task. Triggers on mentions of LazyVim, lazy.nvim, Neovim configuration, plugin specs, opts pattern, mason, lspconfig, or ~/.config/nvim.

Use Codex CLI (codex) as a sub-agent for second opinions and code reviews; then apply changes with Codex.

Standardize and automate a Ticket → roles → file handoff → validation engineering pipeline (Command Center autopilot) for repos that use a single in-progress ticket queue (e.g. `docs/tickets/QUEUE.md`) and per-ticket run folders (e.g. `docs/ai/runs/TICKET_ID`). Use when you want multi-role AI execution with strict guardrails (Spec Keeper, Builder, Reviewer, Runner) and prompts/workers.json generated to run in parallel Windows terminals.

Launch multiple terminal windows/panes on Windows to run parallel CLI jobs (Codex sessions, gemini-cli, claude, tests) and write outputs to files.

专注于 FPGA 嵌入式软核（RISC-V/Microblaze）的 C 语言底层驱动开发与系统固件优化。

Build full-stack applications with Bun.js and Elysia.js. Use this skill when working with Bun runtime, Bun native APIs (SQL databases, Redis, S3), Bun workspaces/monorepos, Elysia.js web framework, or migrating from Fastify to Elysia. Covers setup, routing, validation, authentication, WebSocket, and end-to-end type safety with Eden.

Bitfinex cryptocurrency exchange API for trading, funding, wallets, and market data. Supports REST and WebSocket APIs for both public and authenticated endpoints. Use this skill when integrating with Bitfinex exchange for trading bots, portfolio management, or market data analysis.

List the contents of an npm package tarball before publishing. Use when the user wants to see what files are included in an npm bundle, verify package contents, check tarball size, or debug npm publish issues.

Reads Excel (.xlsx) files and converts to Markdown format. Handles multiple sheets and large tables. Use when needing to read Excel spreadsheets. Requires openpyxl package.

Reads PDF files and extracts text content in Markdown format. Handles tables and multi-page documents. Use when needing to read PDF documents. Requires pdfplumber package.

Reads Microsoft Word (.docx) files and extracts text content. Use when needing to read .docx documents. Requires python-docx package.

Expert guidance for working with the python-seabreeze library and Ocean Optics spectrometers. Use this skill when you need to: (1) Connect to or list Ocean Optics spectrometers, (2) Configure acquisition parameters like integration time, (3) Capture spectral data (wavelengths and intensities), (4) Troubleshoot connection or backend issues (cseabreeze vs pyseabreeze), or (5) Develop new features or fix bugs in the python-seabreeze codebase.

metadata.description,

Skill for working with JSONL (JSON Lines) format registries. Use when creating, querying, updating, or managing data stored in JSONL format for skill registries, logs, or datasets.

Skill for converting between different skill formats. Use when transforming skills from anthropics/skills format to GitHub Copilot format, or vice versa. Handles SKILL.md parsing, validation, and structure transformation.

This skill should be used when building professional PowerPoint presentations, creating slide decks with icons or AI-generated images, capturing application screenshots for appendices, or converting HTML slides to PPTX format. Integrates Go Bananas for hero image generation, react-icons with Sharp for icon rendering, Playwright for authenticated screenshot capture, and pptxgenjs for final PPTX output. Use for: "create presentation", "build pptx", "PowerPoint presentation", "create slide deck", "add screenshots to slides", "generate presentation images", "HTML to PowerPoint", "icons for slides", "capture app screenshots for presentation", "Go Bananas presentation images", "Sharp image processing".

Valida endpoints MCP contra especificación 2024-11-05

Converts complex PDF documents into structured Markdown with semantic image extraction and layout analysis using PaddleOCR (PP-StructureV3). Use when you need to digitize PDFs while preserving: 1. Document hierarchy (headings, numbering, and sections). 2. Tables (automatically converted to clean Markdown tables). 3. Images (extracted, semantically renamed based on nearby titles/text, and referenced). 4. Reading order recovery (fixing multi-column or complex layouts). **CRITICAL**: This skill MUST be executed using its own internal virtual environment.

Skill de soporte experto para la asignatura de Simulación (SCD-1022) - Ingeniería en Sistemas Computacionales del TecNM. Proporciona herramientas para el análisis, modelado y experimentación de sistemas mediante simulación de eventos discretos. Cubre generación de números pseudoaleatorios, pruebas estadísticas, variables aleatorias y marcos de trabajo para proyectos de simulación.

在对话结束时，将用户反馈/有效做法沉淀到目标 Skill 的 evolution.json，并自动缝合回 SKILL.md（可反复对齐，避免升级覆盖）。

CLI to deploy and manage applications, add-ons, and configurations on Clever Cloud PaaS. Use when the user needs to deploy apps, view logs, manage environment variables, configure domains, or interact with Clever Cloud services.

Multi-agent code review system that spawns three independent Claude sub-agents to review PR diffs. Each agent receives files in different randomized order to reduce ordering bias. Issues are classified as high/medium/low severity. Results are aggregated using consensus voting - only issues identified by 2+ agents where at least one rated it medium or higher severity are reported and posted as PR comments. Use when reviewing PRs, performing code review with multiple perspectives, or when consensus-based issue detection is needed.

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

CRITICAL: Use for Makepad troubleshooting and reference. Triggers on: troubleshoot, error, debug, fix, problem, issue, no matching field, parse error, widget not found, UI not updating, code quality, refactor, responsive layout, adaptive, api docs, reference, documentation, 故障排除, 错误, 调试, 问题, 修复

Transform screen recordings into enriched meeting notes with transcripts, key frame extraction, and Obsidian integration. This skill should be used when processing MP4 screen recordings, creating meeting summaries from video, extracting visual context from recordings, or when the user mentions transcribing meetings or screen captures.

Extract and analyze specific cells from Jupyter notebooks without loading entire files. This skill should be used when working with .ipynb files, viewing notebook plots or tables, or when the user references specific cell outputs. Enables selective extraction of plots, tables, and code outputs from large notebooks.

Capture screenshots with Playwright and send them to Slack with context. Use this skill when you need to: (1) Share visual evidence of a bug, UI state, or test result (2) Document the current state of a page for review (3) Send automated screenshot reports during E2E testing (4) Provide visual context for debugging discussions Triggers: "screenshot to slack", "send screenshot", "capture and share", "share this page"

Process feature tickets from markdown files exported from any ticket system (Linear, GitHub Issues, Jira, Asana, ClickUp, etc.). Extracts requirements, converts design images to ASCII, generates JSON state files, and manages development progress using the Ralph Wiggum methodology. Use when (1) processing feature request tickets, (2) tracking feature development progress, (3) running acceptance criteria verification, (4) working with ticket markdown files, or (5) implementing systematic one-feature-at-a-time workflows.

Verify current step and advance to the next step

Architecture-first planning for complex tasks

通过 Google NotebookLM 查询私有知识库。支持浏览器自动化、持久化认证和多文档管理。大幅减少幻觉，提供基于来源的回答。

Execute a single step from a spec. Used by spec-step-executor agent and main process when running steps directly.

通过 SMTP 发送邮件。支持纯文本、HTML 和附件邮件。当用户需要发送邮件、发送报告、发送通知时使用此 skill。用户需在 .env 文件中配置 SMTP 服务器信息。

下载PubMed文献并录入知识库。支持通过PMID、关键词搜索和下载文献元数据，并可下载PDF全文。用户需在.env文件中配置NCBI_API_KEY。

Query the OpenAI developer documentation via the OpenAI Docs MCP server using CLI (curl/jq). Use whenever a task involves the OpenAI API (Responses, Chat Completions, Realtime, etc.), OpenAI SDKs, ChatGPT Apps SDK, Codex, MCP integrations, endpoint schemas, parameters, limits, or migrations and you need up-to-date official guidance.

Provides React Native performance optimization guidelines for FPS, TTI, bundle size, memory leaks, re-renders, and animations. Applies to tasks involving Hermes optimization, JS thread blocking, bridge overhead, FlashList, native modules, or debugging jank and frame drops.

Background Worker - Dispatch edits/tasks to keep main context clean

Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks

Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.

A high-performance Agent Skill to inject a secure, anti-fraud authentication layer into any Next.js/React project. It automates the setup of Better Auth, Drizzle ORM, Resend (with email verification & password reset), and Device Fingerprinting.

Effect-TS (Effect) guidance for TypeScript: designing and implementing Effect-based code, modeling expected errors vs defects, managing dependencies with Context/Layer/Effect.Service, handling resource lifecycles with Scope, running effects at the program edge, using Effect.gen, validating data with Effect Schema, and testing time with TestClock. Use when asked to build, refactor, review, or explain Effect code or when converting Promise/async code to Effect.

Claude Skills meta-skill: extract domain material (docs/APIs/code/specs) into a reusable Skill (SKILL.md + references/scripts/assets), and refactor existing Skills for clarity, activation reliability, and quality gates.

Intelligently organizes your files and folders across your computer by understanding context, finding duplicates, suggesting better structures, and automating cleanup tasks. Follows your file organization rules (D:\cursor\file\Si Yuan\claude\ for docs, .claude-temp\ for temp files). Reduces cognitive load and keeps your digital workspace tidy without manual effort.

Svelte runes guidance. Use for reactive state, props, effects, attachments, or migration. Covers $state, $derived, $effect, @attach. Prevents reactivity mistakes.

Svelte component patterns. Use for web components, component libraries (Bits UI, Ark UI, Melt UI), form patterns, or third-party integration.

z.string().optional(),

Use when configuring GitHub Actions to build, package, and publish applications (especially Electron) as Windows executables, or when encountering permission (403 Forbidden) and PowerShell environment issues in CI runners.

Orchestrates Bubble RAG API interactions for knowledge base management, document processing, and intelligent Q&A retrieval. Use when you need to query project documentation, upload files to knowledge base, or manage RAG configurations.

전략 수립 4단계(시각화)를 수행합니다. 내러티브 설계, 슬라이드 기획, PPTX 파일 생성 및 검증(Audit).

Guide for configuring and using GLM (Zhipu AI) MCP servers. This skill should be used when users want to set up or troubleshoot GLM MCP servers including Web Search Prime, Web Reader, and Visual Understanding (GLM-4.6V).

Performs manual testing of Story AC via executable bash scripts saved to tests/manual/. Creates reusable test suites per Story. Worker only.

Creates 4 root documentation files (CLAUDE.md, docs/README.md, documentation_standards.md, principles.md). L3 Worker invoked by ln-110-project-docs-coordinator.

微信小程序实时日志监听 - console 输出和网络请求

Build evaluation datasets for AIFindr agents by adding queries with expected responses extracted from a knowledge base. Use when asked to add queries to a W&B dataset, create evaluation test cases, or build ground truth datasets from documents. Requires W&B dataset name, project, query, and knowledge base path.

Update OpenCode configuration, agents, commands, skills, and rules through safe config-only changes. Use for natural-language requests that translate to edits in opencode.json/jsonc, .opencode/*, AGENTS.md, and Claude-compatible files.

Convert Markdown articles to WeChat Official Account formatted HTML with beautiful themed layouts. Use when user wants to convert markdown to WeChat article, publish to WeChat, or format articles for WeChat Official Account.

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification

Sirv REST API integration for image and file management. Use when working with Sirv CDN, uploading/downloading files to Sirv, managing image metadata, searching files, creating 360 spins, converting videos, or any Sirv API operations. Covers authentication, file operations, metadata, search queries, async jobs, and account management.

Expert guidance on image optimization for web performance. Use when working with image formats (WebP, AVIF, JPEG, PNG, GIF, SVG, HEIC, JPEG XL), compression settings, responsive images, lazy loading, CDNs, Core Web Vitals, or any image-related web development task. Covers format selection, quality settings, srcset/sizes, picture element, art direction, fetchpriority, placeholder strategies (LQIP, blur-up, blurhash), container queries, HDR/wide color gamut, AI-powered image tools, edge/serverless processing, and performance optimization.

Sirv dynamic imaging URL API for on-the-fly image transformation. Use when building image URLs with Sirv CDN, resizing images via URL parameters, adding watermarks/text overlays, cropping, applying filters, format conversion (WebP, AVIF), or any Sirv URL-based image manipulation. Covers 100+ URL parameters for scaling, cropping, effects, text, watermarks, frames, and optimization.

Fetch and analyze error logs from Google Cloud Logging for Cloud Functions. Groups errors by pattern, identifies frequency, and provides root cause insights. Use when debugging GCP errors, investigating Cloud Functions failures, analyzing production issues, or when the user mentions Google Cloud logs, GCP errors, or Cloud Functions issues.

Guide for creating new Pluto Duck skills (SKILL.md) and safely scaffolding skill folders under /skills/. Use when the user asks to create/make/build/scaffold/initialize a skill, or to update/validate an existing skill definition.

Terraform infrastructure-as-code standards with project-specific context loading. Use when writing, reviewing, or refactoring Terraform modules. Covers module organization, versioning, security scanning with Checkov, and automatic documentation generation.

AI-powered TradeMe marketplace search. Fetches listings via API, then uses Claude to analyze descriptions and images to find the best matches for nuanced requirements like "good condition", "stylish", "looks safe for a beginner". Use when someone wants to find items on TradeMe with smarter filtering than keywords - e.g., "find a solid second-hand bike for my 9 year old near Mt Eden, good condition, pink if possible". Triggers: TradeMe, Trade Me, marketplace search, find listings, buy second-hand, NZ marketplace.

Explain how to implement and evolve MVVM features using the repo’s `@web-loom/mvvm-core`, the shared `models`/`view-models` packages, and the reference MVVM apps (React/Angular/Vue). Use when Codex is asked about MVVM wiring, state management, or integrating the core packages with framework-specific UIs.

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup

FastAPI dev/prod runbook (Uvicorn reload, Gunicorn)

Phoenix operations and deployment: releases, runtime configuration, clustering, libcluster, telemetry/logging, secrets, assets, background jobs, and production hardening on the BEAM.

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

Systematically trace bugs backward through call stack to find original trigger

Master error handling patterns across languages including exceptions, Result types, error propagation, and graceful degradation to build resilient applications. Use when implementing error handling, designing APIs, or improving application reliability.

Cypress end-to-end and component testing patterns for web apps: reliable selectors, stable waits, network stubbing, auth handling, CI parallelization, and flake reduction

Architectural analysis before any refactoring or significant change. Use BEFORE modifying, replacing, or deleting modules. Prevents lost behaviors and edge case bugs.

Verify secrets and environment variables are properly configured. Use before deployment, after adding new services, or when debugging auth issues.

Creates a PR from the current branch without deleting the worktree. Use this when you want to keep the worktree for local modifications.

Creates git worktrees from TASK.md files for parallel feature development. Each worktree gets its own TASK.md with requirements and quality standards.

Scaffold a new OFBiz component (plugin) using Gradle. Use when starting a new feature set or isolating custom code.

Define and implement OFBiz services. Use when creating new services in services.xml, modifying attributes, or debugging dispatcher.

Create and manage OFBiz data files (Entity Engine XML). Use when adding Seed/Demo data, fixing foreign keys, or configuring entity resources.

Implement OFBiz services in Java. Use when writing core domain logic, strict typing, or performance-critical code.

Manage OFBiz entity definitions (Data Model). Use when creating/modifying entities, debugging DB errors, or adding views.

Write Groovy logic for OFBiz services and scripts. Use when creating/debugging Groovy services or implementing entity logic.

Embedded C firmware patterns for HAL/driver layering, state machines, ring buffers, and low-level safety practices. Use for MCU firmware architecture and device driver design.

Execute read-only Redis queries with multi-connection support and security enforcement.

Download videos from YouTube, Bilibili, Douyin, Xiaohongshu, Instagram, Twitter with best quality MP4 format

Execute read-only SQL queries against MySQL/PostgreSQL/OceanBase databases with multi-connection support and defense-in-depth security.

2つのPDFファイルを比較し、内容が同一かどうかを判定（動的メタデータ除外）

Archive completed PRD stories to docs.local/. Use when planning a sprint transition, archiving completed work, or resetting the PRD for a fresh start.

Git and GitHub CLI operations - commits, PRs, issues, branches. No MCP required.