AI Skills Hub - Browse 180,000+ Agent Skills

OpenDocument Text (.odt) creation, editing, and analysis. Supports tracked changes, styles, annotations, and language/locale handling. Use for: creating new ODT documents, editing existing ODT content, working with tracked changes (redlining), adding comments/annotations, or extracting/analyzing ODT content.

Svelte 5 runes, snippets, SvelteKit patterns, and modern best practices for TypeScript and component development. Use when writing, reviewing, or refactoring Svelte 5 components and SvelteKit applications. Triggers on: Svelte components, runes ($state, $derived, $effect, $props, $bindable, $inspect), snippets ({#snippet}, {@render}), event handling, SvelteKit data loading, form actions, Svelte 4 to Svelte 5 migration, store to rune migration, slots to snippets migration, TypeScript props typing, generic components, SSR state isolation, performance optimization, or component testing.

Comprehensive developer workflow guide for PikaCSS monorepo maintenance, including package architecture, implementation patterns, testing strategies, and release procedures.

This skill should be used when the user asks to "fetch JIRA issue", "get ticket", "show DEV-123", "retrieve issue details", "get comments for ticket", "show attachments", or pastes a JIRA URL like "https://yoursite.atlassian.net/browse/KEY-123". Also triggers when the user asks to "understand the requirements", "what does the ticket say", or needs context from a JIRA issue.

This skill should be used when the user asks to "list schemes", "show available schemes", "find Xcode schemes", "get project schemes", "check workspace schemes", or needs to know which build schemes are available in an Xcode project (.xcodeproj) or workspace (.xcworkspace).

Security scanning and triage for local Agent Skills. Use this skill to audit SKILL packages, detect prompt-injection/data-exfiltration/tool-abuse risks, and produce concise risk conclusions with reasons.

This skill should be used when the user asks to "run tests", "execute tests", "run unit tests", "run UI tests", "test the app", "xcodebuild test", or needs to run Xcode tests for an iOS, watchOS, tvOS, or visionOS app.

This skill should be used when the user asks to "build the app", "build iOS app", "compile the project", "run xcodebuild", "build for simulator", "build for device", or needs to build an Xcode project or workspace.

This skill should be used when the user asks to "run SwiftLint", "lint Swift code", "fix Swift lint errors", "format Swift code with SwiftLint", "check Swift code style", "auto-fix lint issues", or needs to run SwiftLint with --fix or --format options. Requires swiftlint_path and config_path to be provided by the caller.

Manages Infisical configuration. Use when user says "Infisical에 업데이트해줘", "환경변수 동기화해줘", "이 config Infisical에 저장해줘", "strategy config 업데이트", "YAML을 Infisical로", "JSON config 저장", or wants to sync environment variables to Infisical.

3. **If ESLint config is found:** - Proceed with the validation workflow

A macOS command-line tool for recording audio, screen, and camera output. Designed for both human users and AI agents operating in a terminal.

Coordinate with interactive async agents in separate contexts. Run another Claude in separate pane for second opinion, objective review, pair programming, or parallel tasks. Also for background process management.

name: notification-alert description: Claude Codeの入力待ち・許可要求時に通知（音声+ダイアログ+最前面化）を行う設定の管理とテスト。「通知テスト」「通知設定」「アラート確認」などのリクエストで発動。

Turborepo monorepo build system guidance for task pipelines, caching, filtering, CI optimization, and monorepo structure.

Extract brand identity and download assets from existing client websites. Use this skill BEFORE building any website, landing page, or marketing page that needs to match an existing brand. Handles logo extraction, color palette identification, font detection, and local asset downloading. Pair with landing-pages skill for the actual build.

Generate a Jekyll blog post in kkamji98.github.io from a study directory (README.md + manifests + images) in kkamji-lab. Use when the user asks to write a blog post based on a study topic directory or wants README content converted into a post with WebP images, raw GitHub links for kubectl apply, and references.

Run ComfyUI workflows from the command line using comine-san (npx). Use when the user has a ComfyUI-exported workflow_api.json and wants to (1) discover generated CLI options via --help, (2) execute against a ComfyUI server via --server, (3) save aggregated results via --output-json, or (4) script runs with --quiet and troubleshoot common failures (missing file, invalid JSON, cannot connect to server).

Debug MicroClaw issues. Use when things aren't working, container fails, authentication problems, or to understand how the system works. Covers logs, environment variables, mounts, and common issues.

Use when starting new Home Assistant feature work or before making configuration changes - ensures latest config backed up with smart retention

Search PaperBLAST for literature about proteins, find characterized proteins by function via Curated BLAST, and check metabolic pathway gaps with GapMind. Use when: (1) user asks about papers or literature for a protein or gene, (2) user wants to find characterized proteins matching a functional description, (3) user asks about amino acid biosynthesis or carbon source utilization capability of an organism, (4) user mentions PaperBLAST, GapMind, or Curated BLAST, (5) user wants to annotate hypothetical proteins using literature evidence. Wraps papers.genomics.lbl.gov CGI tools via MCP server.

Publish markdown content to Google Docs via n8n webhook. Maintains local registry to prevent duplicate document creation.

Transform Substack frameworks (3-10 step processes, pillars, layers) into visually compelling single-page HTML infographics with creative excellence

Provides expert guidance on Swift Concurrency patterns, implementation, and issue remediation. This skill should be used when working with async/await, actors, tasks, Sendable conformance, fixing concurrency compiler errors, or migrating to Swift 6. Triggers on "Swift Concurrency", "async/await", "actor", "@MainActor", "Sendable", "data race", "concurrency", "Swift 6", "并发", "线程安全", "异步", "Swift 并发".

Provides iOS WidgetKit development expertise with best practices for Timeline Providers, Widget Configuration, Live Activities, and App Intents. This skill should be used when user asks to create widgets, implement widget features, debug widget issues, or optimize widget performance. Triggers on "widget", "WidgetKit", "Timeline", "Live Activity", "小组件", "桌面组件", "widget 开发".

Comprehensively analyze Excel workbooks by combining factual extraction (via `xls-extract`) with AI-powered insights.

Provides tools to verify connectivity and route health for the MES system. Use this skill when troubleshooting connection issues, verifying deployment status, or checking if services (Postgres, Redis, MQTT, APIs) are reachable.

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.

Error handling and input validation for Todo AI Chatbot task operations. Use when implementing: (1) Input validation for task title, position, and description (2) User-friendly error messages for MCP tool operations (3) Edge case handling (empty lists, non-existent tasks, duplicates) (4) Graceful degradation for API and database failures

Provision, configure, and manage OpenClaw AI agent instances running inside Firecracker microVMs. Use when creating new VM instances, controlling VM lifecycle (start/stop/restart/destroy), debugging guest services, checking instance health, or modifying VM provisioning scripts.

Audit and debug agentic cross-project runs using a deterministic Debug/ sweep. Use when you want to verify agent concatenation (planned vs executed), tier/dispatch/enforcement health, and actionable fixes based on real run evidence copied into a Debug folder.

Build with Aurora DSQL - manage schemas, execute queries, and handle migrations with DSQL-specific requirements. Use when developing a scalable or distributed database/application or user requests DSQL.

Give your Claude Code sessions memory across /clear and /compact boundaries. Save/resume workstream state to named session files without clobbering shared MEMORY.md. Triggers on "save session", "continue session", "clear session".

Generate actionable task breakdown from plan and specification

Search collected papers by keyword or natural language query. This skill should be used when users want to find papers in their collection matching specific topics or questions.

Generate digest of recently collected papers grouped by topic. This skill should be used when users want to review all papers collected in a time period.

Generate structured summaries for collected papers using Claude. This skill should be used when users want to summarize a specific paper or when papers need batch summarization after collection.

Generate images via Nano Banana with 129 curated prompts. 3 modes: search (best match), creative (remix), wild (experimental). Actions: generate for banners, portraits, infographics, products. Styles: Ukiyo-e, Bento grid, cyberpunk, cinematic, vintage patent.

Improve semiconductor failure analysis (FA) reports based on professional 8D evaluation criteria. Supports both .ppt and .pptx formats with automatic conversion. Features dynamic content injection from LLM evaluations, multi-format JSON compatibility, and closed-loop execution manifests.

Trigger when: (1) User mentions "manim" or "Manim Community" or "ManimCE", (2) Code contains `from manim import *`, (3) User runs `manim` CLI commands, (4) Working with Scene, MathTex, Create(), or ManimCE-specific classes. Best practices for Manim Community Edition - the community-maintained Python animation engine. Covers Scene structure, animations, LaTeX/MathTex, 3D with ThreeDScene, camera control, styling, and CLI usage. NOT for ManimGL/3b1b version (which uses `manimlib` imports and `manimgl` CLI).

Download videos, audio, subtitles, and clean paragraph-style transcripts from YouTube and any other yt-dlp supported site. Use when asked to “download this video”, “save this clip”, “rip audio”, “get subtitles”, “get transcript”, or to troubleshoot yt-dlp/ffmpeg and formats/playlists.

Design command-line interface parameters and UX: arguments, flags, subcommands, help text, output formats, error messages, exit codes, prompts, config/env precedence, and safe/dry-run behavior. Use when you’re designing a CLI spec (before implementation) or refactoring an existing CLI’s surface area for consistency, composability, and discoverability.

スライド画像とナレーション音声から動画を自動生成するパイプラインです。

データ駆動の“図解・モーション素材”を自動生成するためのスキルです。

Write one or more matchup guides for a battlebox deck; use when asked to create or update matchup guide .md files.

Initialize or upgrade software repositories with reliable engineering defaults. Use when creating a new repo, scaffolding a project, or improving delivery discipline so Codex must keep docs current, add risk-based tests, detect major changes, create missing gate commands, run full gate after major changes, generate missing GitHub Actions gate workflow, and hand off failures with a structured blocker report.

Automate Adobe After Effects via ExtendScript. Use when the user asks to create, modify, or query anything in an After Effects project — layers, keyframes, expressions, effects, compositions, assets, rendering, batch operations. Generates and executes JSX ExtendScript via osascript on macOS.

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. Use when user: configures tasks/workflows/pipelines, creates packages, sets up monorepo, shares code between apps, runs changed/affected packages, debugs cache, or has apps/packages directories.

Syncs skill metadata to AGENTS.md Auto-invoke sections. Trigger: When updating skill metadata (metadata.scope/metadata.auto_invoke), regenerating Auto-invoke tables, or running ./skills/ops/skill-sync/assets/sync.sh (including --dry-run/--scope).

Control Philips Hue lights locally via the bridge HTTP API. Use for turning lights on/off, dimming, changing colors, and setting scenes. No cloud required.

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

Generate high-quality synthetic datasets using statistical samplers and Claude's native LLM capabilities. Use when users ask to create synthetic data, generate datasets, create fake/mock data, generate test data, training data, or any data generation task. Supports CSV, JSON, JSONL, Parquet output. Adapted from NVIDIA NeMo DataDesigner (Apache 2.0).

Find and switch to macOS Spaces/Desktops by application name. Use when asked to find which Space an app is on, switch to a Space containing a specific app (like GoLand, IntelliJ, VS Code), navigate between Mission Control Spaces, or detect full-screen application windows across desktops.

プロジェクト関連データ（project_master, stakeholder_master等）のINSERT/UPDATE/DELETE操作を実行するスキル。

Export all tables from the SSOT database (ssot.db) to pipe-delimited CSV files sorted by primary key. Use this skill when backing up database contents for version tracking, comparing database state across different points in time, or generating human-readable snapshots of all table data for documentation or diff analysis.

プロジェクト知識検索スキル。SSOTデータベースからプロジェクト情報を効率的に取得し、 AIエージェントがプロジェクトに関するあらゆる質問に回答できるようにする。 Use when: - ユーザーが「〜について教えて」「〜とは？」と質問したとき - ユーザーが特定の要件・機能・API・画面について尋ねたとき - 「影響範囲は？」「関連する〜は？」というトレーサビリティ質問 - 「〜の背景は？」「なぜ〜？」という理由・経緯の質問 - 「〜の進捗は？」「〜の状況は？」という状況確認 - プロジェクト全体像の把握が必要なとき

Query table schema information from the SSOT database (ssot.db). Use this skill to get detailed column definitions, data types, primary keys, unique constraints, indexes, and foreign key relationships for specific tables. Replaces reading init/配下 directly.

Step 11-03: バッチエラー定義（外部オーケストレーター方式）

Initialize SSOT SQLite database from init/配下 and sequential step files. This skill should be used when the user requests database initialization, reinitialization, or reset. The skill automates backup, table creation, sequential data loading (step01_01.sql, step01_10.sql, ...), and integrity validation.

Step 08-05: 機能詳細ステップ → エンティティ・CRUDマッピング（外部オーケストレーター方式・トークン最適化版）

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

Search arXiv preprint repository for papers in physics, mathematics, computer science, quantitative biology, and related fields

Check meta title and description pixel widths against Google SERP limits (580px title, 990px description). Use when validating SEO metadata, checking SERP pixel lengths, or auditing meta tags — whether single strings, small batches, or full spreadsheets.

Generates and reviews Salesforce Apex code with 2025 best practices and 150-point scoring. Use when writing Apex classes, triggers, test classes, batch jobs, or reviewing existing Apex code for bulkification, security, and SOLID principles.

Operational workflows, command recipes, and troubleshooting for the doc-control repository. Use when running audits, collecting Mattermost/Redmine data, starting/stopping Django UI/API and workers, managing configs and env, running quality gates, or diagnosing common failures in doc-control.

Generate YARA rules from malware samples using yarGen-Go. Manage goodware databases, use CLI or API for rule generation, and integrate with yarGen web server. Use when generating YARA rules, managing goodware databases, creating custom string/opcode databases, or interacting with yarGen web API.

High-performance temporary storage using Redis. Use to save context, cache expensive API results, or share state between agent sessions. Follows strict key naming conventions.

Interact with VirusTotal API v3 for threat intelligence, file/URL/IP/domain analysis, and malware hunting. Use when looking up hashes, scanning files/URLs, investigating IOCs (IPs, domains), searching VT Intelligence, retrieving analysis reports, checking file reputations, or working with threat intelligence data from VirusTotal.

Interact with VirusTotal API v3 for threat intelligence, file/URL/IP/domain analysis, and malware hunting. Use when looking up hashes, scanning files/URLs, investigating IOCs (IPs, domains), searching VT Intelligence, retrieving analysis reports, checking file reputations, or working with threat intelligence data from VirusTotal.

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.

This skill should be used when docs-researcher agent needs guidance on "how to search documentation", "WebSearch query patterns", "filtering search results", "documentation research strategy", or "creating knowledge files". Provides systematic methodology for effective technical documentation research.

Design and deploy Model Context Protocol servers with deep knowledge of the JSON-RPC 2.0 spec, transport mechanisms, and protocol lifecycle. Covers FastMCP framework patterns, production hardening, and diagnostic techniques for connectivity failures. Engage when architecting MCP integrations, building custom servers, or debugging protocol-level issues.

Check, send, and auto-reply to emails using standard IMAP/SMTP protocols. Works with Gmail, Outlook, Yahoo, and any IMAP/SMTP compatible email provider.

Take screenshots of web pages at various viewport sizes for visual debugging. Use when building or debugging frontend UI, especially mobile-responsive layouts.

Use the bundled Python scripts to call Kagi’s API from the OpenClaw host.

LinkedIn automation — post, comment (with @mentions), edit/delete comments, repost, read feed, analytics, like monitoring, and engagement tracking. Uses Playwright with persistent browser profile. Use for any LinkedIn task including content strategy, engagement analysis, and audience growth.

Create and develop Obsidian plugins from scratch. Use when building a new Obsidian plugin, scaffolding from the sample-plugin-plus template, or developing plugin features. Covers project setup, manifest configuration, TypeScript development, settings UI, commands, ribbons, modals, and Obsidian API patterns.

Control Apple HomeKit smart home devices. Supports listing, discovering, pairing devices, and controlling lights, switches, outlets, thermostats. Use when the user needs to manage HomeKit accessories programmatically. Requires homekit library and paired devices.

Generate AI-powered podcast-style audio narratives using Azure OpenAI's GPT Realtime Mini model via WebSocket. Use when building text-to-speech features, audio narrative generation, podcast creation from content, or integrating with Azure OpenAI Realtime API for real audio output. Covers full-stack implementation from React frontend to Python FastAPI backend with WebSocket streaming.

Security audit and threat model for OpenClaw gateway hosts. Use to verify OpenClaw configuration, exposure, skills/plugins, filesystem hygiene, and to produce an OK/VULNERABLE report with evidence and fixes.

[English] Control Xiaomi Home devices via local LAN using miiocli. Supports status checks, toggling power, and MIOT property manipulation for devices like smart plugs, humidifiers, and rice cookers. | [中文] 通过局域网利用 miiocli 控制米家智能设备。支持查看状态、开关控制以及对智能插座、加湿器、电饭煲等 MIOT 设备的属性调优。

Scan networks to discover devices, gather MAC addresses, vendors, and hostnames. Includes safety checks to prevent accidental scanning of public networks.

Fetch live exchange rates between any currency pairs from XE.com. Use when user asks about currency conversion, exchange rates, forex rates, or converting amounts between currencies (e.g., "USD to INR", "100 EUR in GBP", "what's the dollar rate").

Send emails via Mailgun API. Use when the user needs to send emails programmatically, such as newsletters, notifications, alerts, or automated reports. Requires MAILGUN_API_KEY and MAILGUN_DOMAIN environment variables to be configured.

Advanced Home Assistant control using the official hass-cli tool. Features auto-completion, event monitoring, history queries, and rich output formatting. Alternative to the curl-based homeassistant skill - choose this if you want a more interactive CLI experience with better discovery and formatting.

Trade and monitor Hyperliquid perpetual futures. Check balances, view positions with P&L, place/cancel orders, execute market trades. Use when the user asks about Hyperliquid trading, portfolio status, crypto positions, or wants to execute trades on Hyperliquid.

Implements Manus-style file-based planning for complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when starting complex multi-step tasks, research projects, or any task requiring >5 tool calls. Now with automatic session recovery after /clear.

Access Spotify listening history, top artists/tracks, and get personalized recommendations via the Spotify Web API. Use when fetching a user's recent plays, analyzing music taste, or generating recommendations. Requires one-time OAuth setup.

Verify workspace file integrity and scan for prompt injection patterns in agent identity and memory files. Detects unauthorized modifications to SOUL.md, AGENTS.md, IDENTITY.md, memory files, and installed skills. Free detection layer — upgrade to openclaw-warden-pro for automated countermeasures.

Scan binaries and scripts for malicious patterns before trusting them. Use when installing skills, evaluating unknown binaries, or auditing tool dependencies.

Generate videos using Flyworks (a.k.a HiFly) Digital Humans. Create talking photo videos from images, use public avatars with TTS, or clone voices for custom audio.

Email inbox for AI agents. Check messages, send emails, and communicate via your own @agentmail.to address.

Transcribe audio to text using ElevenLabs Scribe. Supports batch transcription, realtime streaming from URLs, microphone input, and local files.

Find and compare products online (Google Shopping) and locally (stores near you). Auto-selects best products based on price, ratings, availability, and preferences. Generates shopping list with buy links and store locations. Use when asked to shop for products, find best deals, compare prices, or locate items locally. Supports budget constraints (low/medium/high or "$X"), preference filtering (brand, features, color), and dual-mode search (online + local stores).

Secure sync for OpenClaw memory and workspace. Use /sync to push, /restore to pull, /sync-status to check. Supports versioned snapshots and disaster recovery.

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.

Set timers and alarms. When a background timer completes, you receive a System notification - respond with the reminder message (NOT HEARTBEAT_OK) to notify the user.

Social media campaign analysis and performance tracking. Calculates engagement rates, ROI, and benchmarks across platforms. Use for analyzing social media performance, calculating engagement rate, measuring campaign ROI, comparing platform metrics, or benchmarking against industry standards.

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.

Generate, edit, and manage PowerPoint presentations via the SlideSpeak API. Use this skill when users want to create presentations from text or documents, edit existing presentations, or work with presentation templates.