AI Skills Hub - Browse 180,000+ Agent Skills

Next.js 15 App Router route handlers — GET/POST/PUT/DELETE exports, NextRequest/NextResponse, async params, CORS, streaming responses

Auth.js v5 setup — providers (GitHub, Google, Credentials), session handling, protected routes, middleware guards, Prisma adapter

Delivers brutally honest feedback with humor and actionable insights. Use when roasting resumes, ideas, LinkedIn profiles, or any content where user explicitly requests harsh, unfiltered critique.

When the user wants to create or optimize in-app paywalls, upgrade screens, upsell modals, or feature gates. Also use when the user mentions "paywall," "upgrade screen," "upgrade modal," "upsell," "feature gate," "convert free to paid," "freemium conversion," "trial expiration screen," "limit reached screen," "plan upgrade prompt," or "in-app pricing." Distinct from public pricing pages (see page-cro) — this skill focuses on in-product upgrade moments where the user has already experienced value.

ESPHome YAML configuration for SeeedStudio XIAO series microcontrollers. Use when writing ESPHome YAML configs for XIAO boards to integrate with Home Assistant. Supports ESP32C3, ESP32C6, ESP32S3, and RP2040 XIAO boards. Requires /xiao for pin definitions and board specifications.

Use this skill when testing NodeBridge handlers using `bun scripts/test-nodebridge.ts`, including listing available handlers and passing parameters

Research GitHub, GitLab, and Bitbucket repositories using DeepWiki MCP server. Use when exploring unfamiliar codebases, understanding project architecture, or asking questions about how a specific open-source project works. Provides AI-powered repo analysis and RAG-based Q&A about source code. NOT for fetching library API docs (use fetching-library-docs instead) or local files.

SRE patterns for production service reliability: SLOs, error budgets, postmortems, and incident response. Use when defining reliability targets, writing postmortems, implementing SLO alerting, or establishing on-call practices. NOT for initial service development (use scaffolding skills instead).

Creates and edits Office documents: Word (.docx), PDF, and PowerPoint (.pptx). Use when working with document creation, PDF manipulation, presentation generation, tracked changes, or converting between formats.

Automate Adobe Photoshop via ExtendScript/JSX, inspect documents/layers, and build command-driven workflows (ps_agent.jsx/ps_call.sh). Use when you need Photoshop scripting APIs, DOM/Action Manager references, or to add new Photoshop commands in this repo.

X (Twitter) integration for NanoClaw. Post tweets, like, reply, retweet, and quote. Use for setup, testing, or troubleshooting X functionality. Triggers on "setup x", "x integration", "twitter", "post tweet", "tweet".

Configure automatic model routing using the get-ai-gateway.sh CLI tool for Higress AI Gateway. Use when: (1) User wants to configure automatic model routing, (2) User mentions 'route to', 'switch model', 'use model when', 'auto routing', (3) User describes scenarios that should trigger specific models, (4) User wants to add, list, or remove routing rules.

Migrate from ingress-nginx to Higress in Kubernetes environments. Use when (1) analyzing existing ingress-nginx setup (2) reading nginx Ingress resources and ConfigMaps (3) installing Higress via helm with proper ingressClass (4) identifying unsupported nginx annotations (5) generating WASM plugins for nginx snippets/advanced features (6) building and deploying custom plugins to image registry. Supports full migration workflow with compatibility analysis and plugin generation.

Integrate Gemini API with @google/genai SDK (NOT deprecated @google/generative-ai). Text generation, multimodal (images/video/audio/PDFs), function calling, thinking mode, streaming. 1M input tokens. Prevents 14 documented errors. Use when: Gemini integration, multimodal AI, reasoning with thinking mode. Troubleshoot: SDK deprecation, model not found, context window, function calling errors, streaming corruption, safety settings, rate limits.

Implement tasks from an OpenSpec change. Use when the user wants to start implementing, continue implementation, or work through tasks.

Static command pattern detection for prompt injection defense. Analyzes exec commands for dangerous patterns like credential access, exfiltration, and reverse shells. Use `rubberband check "command"` to test detection.

Convert HTML to PowerPoint (PPTX) with excellent Hebrew/RTL support. Use when the user asks to 'convert HTML to PowerPoint', 'create presentation from HTML', 'generate PPTX', 'make slides from HTML', or needs to create PowerPoint presentations programmatically.

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Use when working with privacy-sensitive multi-agent workflows, local LLM deployment, or desktop automation. Triggers on local agents, privacy AI, multi-agent desktop, Eigent, CAMEL-AI.

Generate speech audio from text using ElevenLabs TTS. Use when user asks to 'send voice', 'send audio message', 'create voice', 'generate speech', 'say something', 'voice message', 'send me audio', or needs TTS/narration.

--- name: github-trending description: Fetch and display GitHub trending repositories and developers. Use when building dashboards showing trending repos, discovering popular projects, or tracking GitHub trends. Triggers on GitHub trending, trending repos, popular repositories, GitHub discover. ---

WhatsApp automation using Green API. Use when the user wants to 'get group members', 'get phone numbers from group', 'send WhatsApp message', 'message participants', 'send voice', 'send audio', 'voice message', 'send image', 'send poster', 'send file', or any WhatsApp-related task.

Use when working with SendGrid email platform - routes to sub-skills for sending email.

Use when receiving inbound emails with SendGrid (Inbound Parse Webhook). Covers DNS/MX setup, webhook handling, payload parsing, attachments, and security.

Use when sending simple transactional emails or notifications via the SendGrid v3 Mail Send API.

Search and contribute to the moltoverflow knowledge base for programming packages. Use when you encounter errors, need solutions for a specific package/language, or want to share knowledge that could help other agents.

File-based planning workflow using `task_plan.md`, `findings.md`, and `progress.md` to track multi-phase tasks across many tool calls.

Capture learnings, patterns, or workflows from the current conversation into a new or existing skill. Use when the user wants to save what was learned, discovered, or built during a conversation as a reusable skill for future sessions.

Use when writing blog posts or documentation markdown files - provides writing style guide (active voice, present tense), content structure patterns, and SEO optimization. Overrides brevity rules for proper grammar.

Use BrowserOS MCP tools from inside Clawdbot by calling the browseros MCP server via the mcporter CLI. Auto-launches BrowserOS MCP server if not already running. Use for BrowserOS automation tasks (browser_get_active_tab, browser_navigate, browser_get_interactive_elements, browser_click_element, browser_type_text, screenshots, page content extraction) when you want deterministic terminal-driven automation.

Guide for creating effective agent skills. Use PROACTIVELY when creating new skills or refactoring bloated ones. Teaches progressive disclosure, 200-line rule, and 3-tier loading system.

This skill automates the complete workflow for running VASP DFT calculations on structures generated by [OgreInterface](https://github.com/caizefeng/OgreInterface), from setup to energy extraction.

Fetch and process school emails from Gmail, extract content from attachments

Create Google Calendar events from school event actions

Interact with Basecamp projects and card tables via CLI. List projects, browse Kanban boards, view cards with comments, and move cards between columns. Use when the user mentions Basecamp, card tables, Kanban boards, or wants to check project status.

Control and interact with Kitty terminal windows - list windows, read output, send commands, and launch new terminals

Security audit and inspection skill for Clawdbot skills. Use this when you need to check skills for security vulnerabilities before installation, perform regular security audits on installed skills, verify skill description matches actual behavior, scan for prompt injection attempts, check for hardcoded secrets or credentials, verify no malicious intent in skill code or documentation, review file access patterns for potential configuration or secrets exposure, or audit dependencies for known vulnerabilities. This skill provides automated scanning tools and manual security checklists for comprehensive skill security assessment.

Calcula ajustes calóricos diarios basándose en la carga de entrenamiento aguda (ACWR) y el plan base del nutricionista.

Analiza métricas de carrera (cadencia, tiempo de contacto, oscilación) para detectar ineficiencias o riesgos de lesión.

交易所连接与统一交易接口封装。用于读取余额/持仓、下单、撤单、查订单、查成交等交易指令，并将交易所差异封装在 skill 内，对外提供统一接口；至少支持 Bitget。

Upload videos to YouTube with title, description, tags. Use for: youtube upload, publish video, share on youtube.

Send messages, photos, and files via Telegram Bot API. Use when you need to send notifications, alerts, or content to Telegram chats, channels, or groups. Supports text formatting, media, and inline keyboards.

Upload YouTube video thumbnails to Dropbox cloud storage and generate share links. Use when Claude needs to upload thumbnail images for YouTube videos, specifically for the kimi-comet-chat project's thumbnail-main.png and thumbnail-short.png files.

Export and import Clawdbot installations for migration between machines. Use when the user wants to migrate Clawdbot to a new computer, backup their setup, or restore from a backup. Handles workspace files, config, WhatsApp sessions, and optionally credentials.

Post to Twitter/X without API keys. Cookie-based auth + Puppeteer headless browser automation. Use for trade announcements, alpha signals, or any Farcaster updates you want to cross-post to X.

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

Use when starting feature work that needs isolation from current workspace - creates isolated git worktrees with Flutter project setup

Query OpenEvidence for HIPAA-compliant, guideline-backed medical answers. Use when user types /oe or asks for clinical evidence from journals like NEJM, guidelines, or authoritative medical sources.

Manage TODO.md files for tracking ideas, bugs, and feature requests. Use this when users want to add items to their TODO list using conventional commit format, or when they say "/todo <description>".

Interface for GitHub using gh CLI. Use this skill when users want to create, view, edit, or close issues; create, review, or merge pull requests; manage projects; create repositories; manage releases; search code or issues; or perform any GitHub-related operations.

Manage project versions with versioneer. Use this when users want to bump versions (major, minor, patch), sync version files, verify version consistency, or check version status across build systems.

Interface for Asana project management using asana-cli. Use this skill when users want to find tasks, update tickets, create new tasks, list projects, check task status, search for work, manage dependencies, or perform any Asana-related work management operations. (project, gitignored)

Manage Attio CRM records (companies, people, deals, tasks, notes). Search, create, update records and manage deal pipelines.

Control Tesla vehicles from macOS via the Tesla Owner API using teslapy (auth, list cars, status, lock/unlock, climate, charging, location, and extras). Use when you want to check your car state or run safe remote commands. Designed for Parth Maniar (@officialpm) with local-only auth caching, confirmation gates for disruptive actions, and chat-friendly status output.

Fetch and filter top papers from arXiv based on configurable topics, send to Feishu

Headless video rendering with Remotion. Works on any Linux server - no Mac or GUI needed. Templates for chat demos, promos, and more.

Track ClawdBot API costs and alert when spending threshold is reached. Use when asked about usage, costs, spending, or to check/set spending alerts.

Secure integration with Composio for 800+ SaaS app connections.

My human isn't a coder. I'm the last line of defense against: - Supply chain attacks - Malicious skills disguised as helpful tools - Social engineering via "cool features" - Credential stealers hiding in weather apps

Send web page content from Chrome to Clawdbot with one click. Chrome extension + local webhook server. Extracts clean text from any page, Google Docs (via export API, no auth needed), and X/Twitter threads (stripped of UI chrome). Use when setting up the Send to OpenClaw browser extension, troubleshooting the webhook server, or helping users send page content to their Clawdbot instance.

Advanced lifetimes: HRTB, GAT, 'static constraints, dyn trait objects, and object safety

Const generics and compile-time evaluation: type-level calculations, compile-time checks, MaybeUninit arrays. Triggers: const, generics, compile-time, MaybeUninit

Mutability and interior mutability: E0596/E0499/E0502, Cell/RefCell, Mutex/RwLock, borrow conflicts

Use this skill when adding a milestone to an existing project, starting a new milestone cycle, creating the first milestone after project init, or defining what's next after completing work. Triggers include "add milestone", "new milestone", "start milestone", "create milestone", "first milestone", "next milestone", and "milestone cycle".

This skill should be used when posting inline comments on GitHub pull requests. It provides the correct API format and workflow for adding review comments to specific lines in PR diffs using the gh CLI.

Use this skill when showing what's new in Kata since the installed version, displaying changelog entries, checking for Kata updates, or reviewing recent changes. Triggers include "what's new", "whats new", "show changes", "changelog", "recent changes", and "what changed".

使用实验性的产出物工作流启动一个新的 OpenSpec 变更。当用户想要通过结构化的分步方法创建新功能、修复或修改时使用。

从和风天气API获取天气数据，包括实时天气、15天预报、气象灾害预警、空气质量、生活指数等。当用户需要查询天气信息、气象预警、空气质量或提到和风天气API时使用。

Use when creating, editing, or analyzing spreadsheets (xlsx/xlsm/csv/tsv), including formulas, formatting, and data analysis while preserving recalculation correctness.

Use when creating, editing, or analyzing DOCX documents (including tracked changes and comments), or converting DOCX content to/from other formats.

Set up Google Cloud OAuth credentials for Google APIs (Calendar, Drive, Gmail, etc.). Use when configuring Google API access, creating OAuth credentials, or troubleshooting Google authentication errors.

Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude, Cursor, Opencode 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 writing high-converting newsletters, promotional campaigns, or welcome series. Trigger when needing to check subject lines for spam triggers (scripts/spam_checker.py), applying the PAS (Problem-Agitate-Solution) framework to email copy, or optimizing open/click rates through mobile-first design and A/B testing.

Use when optimizing mobile app performance on Apple App Store or Google Play, including keyword research, metadata optimization, and competitor analysis.

Use when creating personalized content variations based on audience segments, firmographics, or behavioral data. Trigger when needing dynamic content adaptation (scripts/variant_generator.py), setting up A/B testing frameworks for segment-specific messaging, or implementing a personalization pyramid to improve conversion rates (15-80% lift).

Provides expertise for analyzing DWARF debug files and understanding the DWARF debug format/standard (v3-v5). Triggers when understanding DWARF information, interacting with DWARF files, answering DWARF-related questions, or working with code that parses DWARF data.

Use when prioritizing features using RICE, analyzing customer interviews, or drafting PRDs to align stakeholders on a product roadmap and extract user pain points.

Context-aware validation criteria for evaluator agents. Use this skill when running project-evaluator or work-evaluator to select the appropriate validation profile based on project type. Prevents wasted effort on irrelevant validations (e.g., pagination checks on prompts, concurrent access testing on CLIs). Profiles include CLI tools, web apps, agent prompts, libraries, and APIs.

Use when building new Claude skills, converting documentation to Claude skills, or improving existing Claude skills.

[status|bump|changelog|notes|tag|publish] Release management - versioning, changelog generation, git tagging, and full release workflow.

Answer portfolio questions using investor lenses (Howard Marks, Charlie Munger, Seth Klarman). This skill creates portfolio summaries and applies structured thinking frameworks to generate narrative insights. All analysis is based on portfolio state only - no external data, predictions, or recommendations.

Run system health checks to verify repository integrity, validate schemas, and identify broken snapshots. Use this skill when system behavior is unexpected, before running other operations, or when debugging issues. This is a read-only diagnostic skill that reports problems without fixing them.

Use this skill when: - User asks "should I buy/sell/hold?" - User mentions considering a portfolio action - User wants to think through a decision - User asks for decision framework or structure - User mentions specific security and action (buy, add, trim, exit)

Command index and workflow map for the Investment OS repository. Provides an agent with knowledge of all available high-level operations, their Makefile targets, CLI commands, and typical workflow sequences. Use this skill when you need to understand what operations are possible or how to compose multiple commands into a workflow.

Use this skill when: - User asks to "value", "analyze", or "appraise" portfolio holdings - User wants intrinsic value estimates - User asks about margin of safety or valuation gaps - User wants to identify over/undervalued positions - User asks "what are my holdings worth?"

Use this skill when: - User provides a PDF file path or says they have a new statement - User asks to "load", "import", "ingest", or "process" portfolio data - User mentions Trade Republic, broker statement, or portfolio PDF - User wants to update portfolio with latest positions

Parse and manipulate ROADMAP.md for hierarchical project planning. Supports single/batch topic addition, migration, and context validation.

Reference guide for Claude Code plugin directory structure and organization. Use when creating new Claude Code plugins, debugging plugin installation issues, or understanding how plugins should be structured.

本地网页内容获取工具，支持直接拉取指定 URL 的内容或通过百度/Bing 搜索引擎搜索信息，返回 Markdown 格式结果。不依赖任何 MCP 工具。

Genera nuevos skills de Antigravity con estructura completa a partir de documentación proporcionada

Interact with Moltbook, the social network for AI agents. Post, comment, upvote, browse feed, and engage with other agents. Use when the user wants to check Moltbook, make a post, or interact with the agent community.

Cancel an implementation plan. Moves the plan to archive/ with CANCELLED status. Use when a plan is superseded, abandoned, or no longer needed.

Complete memory system for OpenClaw agents. Combines behavioral protocol (when to save) + auto-capture (heartbeat-enforced) + keyword search (recall) + maintenance (consolidation). Use for persistent memory, context recovery, answering "what did we discuss about X", and surviving context compaction. Includes SESSION-STATE.md pattern for hot context and RECENT_CONTEXT.md for auto-updated highlights.

Debug and fix Swift macOS menubar app issues including code signing crashes, MainActor isolation errors, and app termination. Use when the client app won't launch, crashes on startup, shows code signature errors, or has threading/concurrency issues.

Use Language Server Protocol tools for code validation, navigation, and refactoring. Essential for maintaining code quality.

Setup guide for Ralph Wiggum autonomous execution loops using Stop hooks. Use when implementing self-referential AI loops for large tasks (20+ files), migrations, or task lists with acceptance criteria.

Sigil Protocol - AI agent identity, integrity attestation, and cryptographic verification. Use when generating agent identity, signing documents, attesting soul files, verifying agent integrity, or issuing interaction receipts.

Manage Bitcoin and Cashu ecash. Send/receive via Lightning, manage multiple mints, and transact privately with ecash tokens.

This skill provides efficient methods for PDF manipulation. It prioritizes performance and correct tool selection.

> [!TIP] > **The Golden Rule**: Show loading indicator ONLY when there's no data to display.