AI Skills Hub - Browse 180,000+ Agent Skills

GIF动图切分工具，将超过指定帧数的GIF文件自动拆分成多个小文件。适用于微信公众号等平台上传GIF时遇到"帧数超限"的问题。

TanStack Query (React Query) v5 best practices for fetching, caching, synchronizing and updating server state in React applications. Use when writing, reviewing, or refactoring code that involves: (1) Data fetching with useQuery, useSuspenseQuery, useInfiniteQuery, (2) Mutations with useMutation and cache invalidation, (3) Query key design and query function patterns, (4) Optimistic updates and cache manipulation, (5) Pagination and infinite scroll implementations, (6) Prefetching and request waterfall optimization, (7) Server-side rendering (SSR) with Next.js pages/app router or Remix, (8) Suspense integration and streaming with Server Components, (9) TanStack Query TypeScript patterns (queryOptions, type inference, global type registration), (10) Testing components that use React Query hooks, (11) Setting up QueryClient, QueryClientProvider, staleTime, gcTime, retry configuration, (12) Any @tanstack/react-query imports or configuration.

TSL (Three.js Shading Language) and WebGPU shader development with Three.js. Write, review, and refactor GPU shaders using TSL's node system, compute shaders, and WebGPU renderer. Use when: (1) Setting up WebGPURenderer in Three.js or React Three Fiber, (2) Writing TSL shaders with Fn, uniform, varying, texture, (3) Creating or modifying node materials (MeshStandardNodeMaterial, SpriteNodeMaterial, etc.), (4) Using positionNode, colorNode, normalNode or other material nodes, (5) Writing compute shaders with instancedArray, storage, compute(), computeAsync(), (6) Building particle systems with sprite and SpriteNodeMaterial, (7) Post-processing with TSL (pass, bloom, fxaa, PostProcessing class), (8) Porting GLSL shaders to TSL or WGSL, (9) Using wgslFn, glslFn, or code() for native shader code, (10) Working with StorageTexture, textureStore, or GPU buffers, (11) Implementing instanced meshes with compute pipeline, (12) Any Three.js WebGPU or TSL related development.

Starte Multi-Agent Experten-Diskussionen über die lokale OpenBotMan API.

Create, edit, and analyze Excel spreadsheets (.xlsx). Use when Claude needs to build financial models, data exports, or any spreadsheet with proper formulas and formatting.

Execute autonomous multi-step research using Google Gemini Deep Research Agent. Use for: market analysis, competitive landscaping, literature reviews, technical research, due diligence. Takes 2-10 minutes but produces detailed, cited reports. Costs $2-5 per task.

Fetches real-time FOREX news and market data from Yahoo Finance for major currency pairs (EUR/USD, GBP/USD, USD/JPY, etc.). Analyzes sentiment and provides trading context.

Process payments via Stripe, PayPal, or ACH. Use when paying invoices, processing customer payments, or managing payment methods. Handles payment scheduling, execution, and confirmation with full audit trail.

Advanced web tools for searching, summarizing, and scraping content using SearXNG private search, AI summarization, and headless browser automation.

Create high-quality AI Skills (knowledge, tool, or hybrid) using the local standards and templates. Trigger: Use when the user asks to create a new skill, package a repeated pattern (≥ 3 uses), standardize a workflow, or generate a reusable rule set.

RSS news aggregator. Fetches headlines from curated feeds across three categories: news, games, and finance. Use when the user asks about current news, headlines, what's happening, what's going on, or says "what's up in news", "what's up in finance", "what's up in games", or the German equivalents "was geht mit nachrichten", "was geht mit money", "was geht mit gaming". Also activates for requests like "give me a news rundown", "latest headlines", "market news", "gaming news", "tech news", "finance roundup", or "briefing". Returns structured JSON from public RSS feeds — no API keys, no web search needed.

Validate frontmatter metadata in handovers, plans, and scripts following Toolkit standards. Performs frictionless validation with hard stops for critical issues and suggestions for optional improvements.

Use this skill when troubleshooting CC-Demon daemon issues, understanding cron expressions, managing scheduled jobs, configuring the Telegram gateway, or debugging job execution failures. Triggers on questions about "demon daemon", "demon not running", "cron schedule", "telegram bot setup", "job failed", "demon logs", "scheduled task", or "demon config".

Manage TikTok profiles to scrape. Switch accounts, add multiple profiles, or list saved profiles.

Debug Kubernetes pods, nodes, and workloads. Use when pods are failing, containers crash, nodes are unhealthy, or users mention debugging, troubleshooting, or diagnosing Kubernetes issues.

Manage Helm charts, releases, and repositories. Use for Helm installations, upgrades, rollbacks, chart development, and release management.

Kanban-style task management dashboard for AI assistants. Manage tasks via CLI or dashboard UI. Use when user mentions tasks, kanban, task board, mission control, or wants to track work items with status columns (backlog, in progress, review, done).

This skill should be used when the user asks about resource usage, CPU, memory, network, disk, or service performance. Covers questions like "how much memory is my service using" or "is my service slow".

Comprehensive ARG (Alternate Reality Game) design toolkit for creating immersive puzzle experiences. This skill should be used when: (1) Designing an ARG or puzzle trail from scratch, (2) Creating hidden content with ciphers, steganography, or encoding, (3) Building trailheads (entry points) to hidden content, (4) Connecting puzzle elements in a cohesive narrative, (5) Implementing specific ciphers or encoding methods, (6) Choosing platforms for ARG deployment (Discord, Twilio, YouTube), (7) Reviewing ARG design for TINAG principles. MANDATORY TRIGGERS: ARG, alternate reality game, puzzle trail, cipher, steganography, hidden message, trailhead, TINAG, puzzle hunt, transmedia, unfiction, encode message, hide data

连接调试版Chrome浏览器，分析当前页面的DOM结构、交互元素和CSS样式信息

Design Databricks lakehouse ML pipelines with Unity Catalog medallion layers, Spark ETL, model zoo evaluation, and MLflow tracking/registry. Use for requests to architect, document, or outline notebook-style plans for Databricks ML workflows, experiment tracking, or governance-ready pipelines.

Design CI/CD pipelines for Kubernetes workloads including container build, test, security scans, Helm or Kustomize packaging, environment promotion, and rollback. Use for requests to plan deployment pipelines, GitOps flows, or cluster release strategies.

Plan and implement object detection pipelines in computer vision, including dataset design, labeling, augmentation, model selection, training, evaluation, and deployment. Use when asked to design, optimize, or troubleshoot object detection projects.

Manage long-running background processes (bots, scrapers, monitors, servers) with reliable detached execution, automatic health monitoring, auto-restart on failure, and proactive alerts. Use when launching any process that should survive session disconnects, when checking process health, or when a background task keeps dying silently.

Generate Mermaid stateDiagram-v2 diagrams from code or specs, with extraction summary and uncertainty notes.

Launch tokens on Streme (streme.fun) - the streaming token platform on Base. Use when deploying SuperTokens with built-in staking rewards, Uniswap V3 liquidity, and optional vesting vaults. Triggers on "launch token on streme", "deploy streme token", "create supertoken", or any Streme token deployment task.

将简道云导出的Lowes订单数据转换为ShipStation系统导入模板。支持CSV和Excel格式，自动处理尺寸取整、重量转换和多数量订单拆分。

Analyze market conditions, geographic opportunities, pricing, consumer behavior, and product validation across Google Maps, Facebook, Instagram, Booking.com, and TripAdvisor.

Render Remotion video compositions to MP4/WebM. Use for: rendering videos, exporting compositions, batch renders, previewing.

Autonomous development loop with fresh context per iteration. Uses an external bash loop that spawns fresh Codex sessions, storing state in files to prevent context drift. Based on the original Ralph Wiggum technique by Geoffrey Huntley.

Wraps AWS CLI v2 commands for EC2, EIP, and spot instance operations. Use when: writing or modifying aws_cmd calls, building AWS CLI queries with --query/--filter, parsing AWS JSON output with jq, or adding new AWS API interactions to lib/*.sh

Manages Bash 4+ scripting, shell functions, error handling, and CLI patterns. Use when: writing or modifying .sh files, adding CLI commands, building shell functions, fixing shellcheck warnings, implementing error handling, or working with bash arrays/strings.

Manages Elastic IP allocation, association, and lifecycle operations in the EC2 Ops Kit. Use when: working on EIP commands (alloc/assoc/disassoc/release), cleanup of orphaned EIPs, or modifying the `cmd_eip` function family in `lib/cmd_network.sh`.

Connect bank accounts via Plaid and analyze financial transactions. Provides a web dashboard for account management, plus CLI tools for balances, transactions, and spending analysis. Complements the community plaid skill (jverdi/plaid) with a visual account manager and AI-ready data formatting.

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

Comprehensive Bitwarden integration supporting both personal CLI (bw) and Secrets Manager CLI (bws). Use for password management, secure storage of API keys, secrets injection into commands, team secrets management, and automated credential retrieval. Supports login, vault access, item creation/update, secrets management, and environment variable injection.

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.

Create professional research posters in LaTeX. ON-REQUEST ONLY - do not use alongside thesis chapter requests unless explicitly asked for a poster.

Intelligent web search routing with automatic fallback handling and memory caching. Selects between Exa web search, deepWiki repository Q&A, DuckDuckGo, and webfetch based on query type and tool availability. Use for all web searches, code questions, documentation lookups, and research tasks.

Fetch PR data from GitHub with token-efficient output. Use when reviewing PRs, checking PR status, or preparing PR summaries.

Process and generate multimedia content using Google Gemini API for better vision capabilities. Capabilities include analyze audio files (transcription with timestamps, summarization, speech understanding, music/sound analysis up to 9.5 hours), understand images (better image analysis than Claude models, captioning, reasoning, object detection, design extraction, OCR, visual Q&A, segmentation, handle multiple images), process videos (scene detection, Q&A, temporal analysis, YouTube URLs, up to 6 hours), extract from documents (PDF tables, forms, charts, diagrams, multi-page), generate images (text-to-image with Imagen 4, editing, composition, refinement), generate videos (text-to-video with Veo 3, 8-second clips with native audio). Use when working with audio/video files, analyzing images or screenshots (instead of default vision capabilities of Claude, only fallback to Claude's vision capabilities if needed), processing PDF documents, extracting structured data from media, creating images/videos from text prompts, or implementing multimodal AI features. Supports Gemini 3/2.5, Imagen 4, and Veo 3 models with context windows up to 2M tokens.

Plans dashboard server with progress tracking and timeline visualization.

使用 iztro 生成紫微斗数排盘并输出分层解读。适用于用户要求基于出生日期、出生时辰、出生地与性别进行本命盘分析，或要求流年/流月/流日/未来时间段推演时。支持先确认出生日期是公历或农历，再生成对应盘面并按“本命→流年→流月→流日”层级解读。

Query pre-processed Ghidra firmware analysis databases for embedded firmware reverse engineering. Use when the user asks about firmware binaries, function lookups, cross-references, call graphs, symbol resolution, disassembly, or binary patching tasks. Supports queries like "find function at address", "show callers of X", "get disassembly for function Y", "what references this address", or "help me patch this firmware". Each firmware project has a corresponding SQLite database in /mnt/user-data/uploads/firmware-dbs/.

Optimize and compress images for web use. Reduces file sizes of JPEG, PNG, GIF images using lossy/lossless compression. Can resize images to maximum dimensions, convert to WebP format, and process entire directories recursively. Use when images are too large for web, need compression, or need format conversion.

Batch log analysis using Groq's fast inference. Handles 10K-100K+ line files from Teleport, journalctl, syslog, ESP32.

Generate changelogs from git history. Use when the user asks to create a changelog, release notes, or summarize changes between tags, branches, or date ranges. Triggers on 'changelog', 'release notes', 'what changed', 'diff summary'.

Use when user requests managing Azure DevOps work item comments - listing, deleting, updating, or cleaning up AI-generated comments.

Creates Claude Code skills, hooks, MCP configs, and custom agents. Use when user wants to create a skill, needs help with SKILL.md, asks about hooks, MCP servers, sub-agents, or autonomous workflows like Ralph loop.

系统化复现论文的技能与提示词模板，输出复现方案、模块拆解、风险与验证清单。

Verifies and auto-fixes Rust code by compiling it and analyzing errors. Trigger this skill when the user provides Rust code that needs validation, or when previously generated Rust code fails to compile.

Extract YouTube video transcripts with metadata and save as Markdown to Obsidian vault. Use this skill when the user requests downloading YouTube transcripts, converting YouTube videos to text, or extracting video subtitles. Does not download video/audio files, only metadata and subtitles.

Use this skill when adding a new NodeBridge handler to src/nodeBridge.ts, including updating types in src/nodeBridge.types.ts and optionally testing with scripts/test-nodebridge.ts

Package and deploy applications to Kubernetes with Dockerfiles, Helm charts, and local Minikube deployment. Use when containerizing applications, creating Kubernetes manifests, setting up Helm charts, deploying to Minikube, or preparing cloud-ready configurations. Focuses on local-first deployment with stateless services.

Token-efficient library API documentation fetcher using Context7 MCP with 77% token savings. Fetches code examples, API references, and usage patterns for published libraries (React, Next.js, Prisma, etc). Use when users ask "how do I use X library", need code examples, want API syntax, or are learning a framework's official API. Triggers: "Show me React hooks", "Prisma query syntax", "Next.js routing API". NOT for exploring repo internals/source code (use researching-with-deepwiki) or local files.

Creates and edits Excel spreadsheets with formulas, formatting, and financial modeling standards. Use when working with .xlsx files, financial models, data analysis, or formula-heavy spreadsheets. Covers formula recalculation, color coding standards, and common pitfalls.

유튜브 채널에서 수집한 컨텐츠를 기반으로 블로그 글을 생성하는 워크플로우. 사용자가 (1) 블로그 주제 찾기/글 쓰기를 요청하거나, (2) 수집된 영상에서 인사이트를 추출하거나, (3) 블로그 워크플로우를 진행할 때 사용. "블로그 글 쓸 주제 찾아줘", "블로그 글 작성해줘", "인사이트 추출해줘" 등의 요청에 트리거됨.

Orchestrator skill for RHDH plugin development. Provides CLI tooling, activity tracking, and routes to specialized skills (overlay, etc.).

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.

Convert HTML to PDF with pixel-perfect rendering and excellent Hebrew/RTL support. Use when the user asks to 'convert HTML to PDF', 'generate PDF from HTML', 'create PDF from webpage', 'export to PDF', or needs PDF generation with Hebrew text support.

Publish posts to WordPress. Use for: publish blog post, upload to WordPress, פרסם בבלוג.

Migrate codebase from try/catch or Promise-based error handling to better-result. Use when adopting Result types, converting thrown exceptions to typed errors, or refactoring existing error handling to railway-oriented programming.

Use when automating Unreal Engine editor tasks via REST API, manipulating actors/materials/blueprints, working with the UnrealBridgeREST plugin, or executing Python in UE.

Bypass API rate limits by rotating VPN servers. Works with any OpenVPN-compatible VPN (ProtonVPN, NordVPN, Mullvad, etc.). Automatically rotates to new server every N requests for fresh IPs. Use for high-volume scraping, government APIs, geo-restricted data.

Manage Blinko notes via its REST API (create/list/delete notes, manage tags/taxonomy). Use when the user says “blinko …”, wants to capture a note to Blinko, list/search recent notes, retag notes, or do cleanup/organization. Requires BLINKO_API_KEY.

Guides the creation of Hytale mods using Java (Server), NoesisGUI (UI), HyUI (HTML UI), and World Gen V2. Acts as a hub for detailed server, asset, and generation guides.

Documentation and codemap specialist. Use PROACTIVELY for updating codemaps and documentation. Generates docs/CODEMAPS/*, updates READMEs and guides.

TDD workflow guide. Use PROACTIVELY when writing new features or fixing bugs. Enforces Red-Green-Refactor cycle and prevents testing anti-patterns.

Weekly engineering research radar for a set of active repos. Use when asked to run the Friday/weekly research digest or "Engineering Radar" that searches (Exa first, then SearXNG fallback), filters out anything previously included, ranks items by novelty/relevance/authority/impact, and produces a concise per-repo report with links. Also persists history/policy for future runs.

Detecta anomalías biológicas graves (ej. pulso en reposo alto, VFC desplomada) y activa protocolos de alerta.

Export Google Documents to local markdown files, keeping them in sync with the source document. Supports single doc export, batch folder export, and splitting by sections.

Convert markdown files to Google Docs with rich formatting. Use when user asks to upload markdown to Google Docs, convert markdown to gdocs, or sync markdown with Google Drive. Supports in-place updates preserving URLs, text styling (bold, italic, links), tables with borders and headers, and Proxima Nova font for headings.

Review Claude/Cursor Skills for security issues (prompt injection, agentic/tool injection, data exfiltration, unsafe automation). Use when evaluating a Skill package/folder or SKILL.md + bundled scripts for risks like hidden instructions, tool misuse, credential theft, network exfil, destructive commands, and policy bypass. Automatically suggest running the scanner when user opens/modifies Skill folders, before installing Skills, or when reviewing Skills for security.

Upload large video files and other assets to Dropbox cloud storage. Use when Claude needs to upload files to Dropbox, especially when files exceed GitHub's size limits (50-100MB), when sharing files via cloud storage, or when backing up project assets to Dropbox.

Helps users remove bloated Logitech official applications (G HUB, Logi Options+), clean up residual files, and then install the lightweight Logi Options+ Mini tool. Suitable when users complain about Logitech software consuming resources or want a cleaner system.

Diagnoses common Linux service issues using logs, systemd/PM2, file permissions, Nginx reverse proxy checks, and DNS sanity checks. Use when a server app is failing, unreachable, or misconfigured.

Fetch and triage the latest unread RSS/news entries from a Miniflux instance via its REST API using an API token. Use when the user asks to get the latest Miniflux unread items, list recent entries with titles/links, or generate short summaries of specific Miniflux entries. Includes a bundled script to query Miniflux (/v1/entries and /v1/entries/{id}) using credentials from ~/.config/clawdbot/miniflux-news.json (or MINIFLUX_URL and MINIFLUX_TOKEN overrides).

Use this skill to add planned work discovered during execution to the end of the current milestone in the roadmap. This skill appends sequential phases to the current milestone's phase list, automatically calculating the next phase number. Triggers include "add phase", "append phase", "new phase", and "create phase". This skill updates ROADMAP.md and STATE.md accordingly.

Use this skill when reviewing pending todos, selecting a todo to work on, filtering todos by area, or deciding what to work on next. Triggers include "check todos", "list todos", "what todos", "pending todos", "show todos", "view todos", and "select todo to work on".

Use this skill when inserting urgent work as a decimal phase between existing phases, adding mid-milestone work, or creating intermediate phases. Triggers include "insert phase", "add urgent phase", "create decimal phase", "insert between phases", and "urgent work".

Build PRISMA 2020-compliant systematic literature review systems with RAG-powered analysis in VS Code. Use when researcher needs automated paper retrieval (Semantic Scholar, OpenAlex, arXiv), AI-assisted PRISMA screening (50% or 90% threshold), vector database creation (ChromaDB), or research conversation interface. Supports knowledge_repository (comprehensive, 15K+ papers, teaching/exploration) and systematic_review (publication-quality, 50-300 papers, meta-analysis) modes. Conversation-first workflow with 7 stages.

Use when creating, editing, or analyzing PowerPoint (.pptx) presentations, including layout manipulation, text extraction, and design customization.

Run all linting, type checking, tests, and documentation builds for the rms-cloud-tasks project. Check for errors and warnings, then fix any problems found. Use when the user asks to run checks, verify the build, run CI locally, or fix lint/type/test errors.

Use when tracking the impact of content on revenue across multiple touchpoints (First-Touch, Last-Touch, Multi-Touch). Trigger when needing to prove content marketing ROI, identifying which blog posts start customer journeys, or calculating influence scores to justify content budget allocation.

Use when designing high-value downloadable offers to build an email list. Trigger when needing to convert markdown checklists into professional PDFs (scripts/checklist_formatter.py), creating actionable guides or templates, or establishing automated email delivery sequences for new opt-ins.

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.

Base skill for JITX hardware design workflow. Use when working with JITX Python projects for PCB design, circuit creation, or component modeling. Provides environment setup verification, build commands, project structure guidance, documentation lookup, and navigation to specialized subskills (component-modeler, etc.). Triggers on any JITX-related task or when user mentions JITX, circuits, PCB design, or hardware. Also triggers when user asks about JITX APIs, landpattern generators, protocols, or needs to look up JITX documentation. IMPORTANT - When user provides a datasheet or asks to create/model a component, ALWAYS invoke the jitx-component-modeler subskill.

Generate or modify interactive HTML computation graphs with a consistent visual style and structure.

Token-efficient library API documentation fetcher using Context7 MCP with 77% token savings. Fetches code examples, API references, and usage patterns for published libraries (React, Next.js, Prisma, etc). Use when users ask "how do I use X library", need code examples, want API syntax, or are learning a framework's official API. Triggers: "Show me React hooks", "Prisma query syntax", "Next.js routing API". NOT for exploring repo internals/source code (use researching-with-deepwiki) or local files.

| Necesidad | Endpoint/Recurso | | ---------------- | ---------------------------------------------------------------------------- | | Autenticar OAuth | [oauth-guide.md](references/oauth-guide.md) | | Buscar productos | `GET /sites/{SITE}/search?q={query}` | | Publicar item | `POST /items` | | Órdenes | `GET /orders/search?seller={ID}` | | Preguntas | `GET /questions/search?item={ID}` | | Webhooks | [code-examples.md#webhooks](references/code-examples.md#configurar-webhooks) |

Create new Azure Database for PostgreSQL Flexible Server instances and configure passwordless authentication with Microsoft Entra ID. Set up developer access, managed identities for apps, group-based permissions, and migrate from password-based to Entra ID authentication. Trigger phrases include "passwordless for postgres", "entra id postgres", "azure ad postgres authentication", "postgres managed identity", "migrate postgres to passwordless".

This skill provides the architecture and code patterns for building production-grade Retrieval-Augmented Generation systems. It enforces "Garbage In, Garbage Out" discipline.

Use when building AI agents, designing tool APIs, implementing permission systems, creating autonomous coding assistants, or working with ReAct/Plan-Execute patterns. Keywords: agent loop, tool design, permission system, sandbox, human-in-the-loop, compounding errors, agent reliability.

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.

Manage business accounting via Odoo ERP using XML-RPC API. Use when creating invoices, recording expenses, querying financial data, or managing customers and products. NOT when using QuickBooks or Xero (different systems).

Manage Google Calendar events via MCP server. Use when scheduling meetings, checking availability, listing events, or processing meeting requests from emails. NOT when managing Outlook calendars (different API).

Send emails via Gmail API using FastMCP server with approval workflows. Use when configuring email sending, troubleshooting email delivery, setting up email templates, or managing email rate limits. NOT when reading emails (use watching-gmail skill). NOT when categorizing emails (use watching-gmail skill).

Systematic debugging techniques including error classification, root cause analysis (5 Whys), reproduction strategies, and error documentation. Use when debugging errors, investigating failures, analyzing stack traces, fixing bugs, or documenting errors in error-log.md. (project)

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.

Post tweets to X (Twitter) via a local proxy server.