AI Skills Hub - Browse 180,000+ Agent Skills

Rust concurrency and parallelism patterns: threads, message passing with channels, shared state with Mutex and Arc, Send and Sync marker traits, data races vs race conditions, and atomics with memory orderings. Use when writing, reviewing, or refactoring Rust concurrent code: (1) Spawning threads with std::thread and JoinHandle, (2) Using move closures with threads, (3) Message passing with mpsc channels (single and multiple producers), (4) Shared-state concurrency with Mutex and Arc, (5) Understanding or implementing Send and Sync traits, (6) Fixing "cannot be sent between threads safely" errors, (7) Choosing between message passing and shared state, (8) Working with atomics and memory orderings (SeqCst, Acquire, Release, Relaxed), (9) Preventing data races and understanding race conditions, (10) Building thread-safe types with raw pointers.

Fetch real-time stock market data including prices, fundamentals (P/E, market cap, dividend yield), technical analysis (RSI, MACD, signals), and TADAWUL screeners. Use when user asks about stock prices, market data, top gainers/losers, or wants to compare/screen stocks. Covers all 400+ Saudi Tadawul stocks, US markets, and 100+ global exchanges.

빌드 후 CP(콕핏) ↔ AC(항공기) 프로젝트 동기화 및 에디터 실행

SSOT 스크립트 실행 후 언리얼 프로젝트에 복사하고 변경사항을 diff로 검증합니다

Generates secure and type-safe Next.js 15 Server Actions. Use this when implementing backend logic, form submissions, or data mutations.

Standards for JSDoc comments and README updates. Use this immediately after coding a complex function or finishing a feature.

Create and validate new skills or agents following project conventions

Locate and list Outlook for Mac profile/cache directories on macOS, including Classic Outlook profile folders such as `Outlook 15 Profiles/Main Profile`, so that downstream tools can copy or process the cached data.

Drive Classic Outlook for Mac (not "New Outlook") via AppleScript to export an `.olm` archive from the local profile cache, enabling offline processing without live account credentials.

Extract clean article content from URLs (blog posts, articles, tutorials) and save as readable text. Use when user wants to download, extract, or save an article/blog post from a URL without ads, navigation, or clutter.

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

Guide for creating effective skills that extend Claude's capabilities with specialized knowledge, workflows, or tool integrations. Use when creating a new skill or updating an existing skill.

Guides the discovery interview at the start of any new agent system design. Use when a human describes what they want to build and you need to capture all requirements.

> Help users discover answers, don't just deliver them.

> Debug non-functional M365 Copilot declarative agents.

| Character | Emoji | Notes | |-----------|-------|-------| | **Alex** | 🧑‍🍳 | Chef - AI author | | **Claudia** | 👩‍� | Woman with curly hair - wife, IBS (brunette) | | **Douglas** | 🧒 | Child - picky eater son | | **Freddy** | 🐕 | Dog (generic) - male | | **Jolly** | 🐩 | Poodle - female |

CLI code review patterns. Use when reviewing CLI applications built with Commander.js, @clack/prompts, picocolors. Covers exit codes, signal handling, error messages, user experience, testing adequacy.

PostHog feature flags, rollouts, A/B testing. Use when implementing gradual rollouts, A/B tests, kill switches, remote configuration, beta features, or user targeting with PostHog.

Resend + React Email templates

Automatically captures LLM API call usage from OpenClaw sessions and logs them to LockN Logger for cost tracking and attribution.

Create a new person folder for tracking tasks and relationships. Use when adding someone to track.

Connect a Feishu (Lark) bot to Clawdbot via WebSocket long-connection. No public server, domain, or ngrok required. Use when setting up Feishu/Lark as a messaging channel, troubleshooting the Feishu bridge, or managing the bridge service (start/stop/logs). Covers bot creation on Feishu Open Platform, credential setup, bridge startup, macOS launchd auto-restart, and group chat behavior tuning.

Interact with Moltbook social network for AI agents. Post, reply, browse, and analyze engagement. Use when the user wants to engage with Moltbook, check their feed, reply to posts, or track their activity on the agent social network.

Implements a Clawdbot extension tool that downloads Feishu files by message_id and file_key, streams to disk with sha256, size limits, and path traversal protection. Use when the user asks to build or update the feishu_file_fetch tool, Feishu file download workflow, or Clawdbot extension handling message_id/file_key inputs.

Supabase patterns for Next.js: SSR auth, RLS, and data access. Trigger: Use when working with Supabase (auth, database, RLS policies).

Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.

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

Free local speech-to-text using MLX Whisper on Apple Silicon. Free, private, no API costs.

Display HTML content on connected Hex nodes (Mac app, iOS, Android).

Manage Things 3 via the `things` CLI on macOS (add/update projects+todos via URL scheme; read/search/list from the local Things database). Use when a user asks Hex to add a task to Things, list inbox/today/upcoming, search tasks, or inspect projects/areas/tags.

Manage Apple Reminders via the `remindctl` CLI on macOS (list, add, edit, complete, delete). Supports lists, date filters, and JSON/plain output.

CLI to manage emails via IMAP/SMTP. Use `himalaya` to list, read, write, reply, forward, search, and organize emails from the terminal. Supports multiple accounts and message composition with MML (MIME Meta Language).

Set up and use 1Password CLI (op). Use when installing the CLI, enabling desktop app integration, signing in (single or multi-account), or reading/injecting/running secrets via op.

Context and coordination for the eval agent pair. Injected when a session starts working on eval.

Create user-facing App Store release notes by collecting and summarizing all user-impacting changes since the last git tag (or a specified ref). Use when asked to generate a comprehensive release changelog, App Store "What's New" text, or release notes based on git history or tags.

Scaffold, build, and package SwiftPM-based macOS apps without an Xcode project. Use when you need a from-scratch macOS app layout, SwiftPM targets/resources, a custom .app bundle assembly script, or signing/notarization/appcast steps outside Xcode.

Refactor and review SwiftUI view files for consistent structure, dependency injection, and Observation usage. Use when asked to clean up a SwiftUI view’s layout/ordering, handle view models safely (non-optional when possible), or standardize how dependencies and @Observable state are initialized and passed.

Control how trading fees are distributed with treasury managers. This is the power feature that sets Flaunch apart from other launchpads.

Use when user asks about Huawei USG firewall configuration, network protocols (OSPF, BGP, IPsec, VPN, NAT, ACL, security-policy), or needs CLI commands for Huawei devices. Triggers on keywords like '华为', 'USG', 'firewall', 'OSPF', 'BGP', 'NAT', 'VPN', 'ACL', '防火墙', '安全策略'.

Use this skill when performing calibrated code or plan reviews. Provides the severity classification system and anti-hate-loop rules that prevent infinite review cycles. Trigger phrases: "review calibration", "severity levels", "review rules"

Practical Python scripts for debugging awf - parse logs, diagnose issues, inspect containers, test domains

This skill should be used when the user wants to publish their Claude Code /insights report to GitHub Pages. It automates creating a git repo, setting up GitHub, enabling Pages, and monitoring the deployment. Triggers on "publish insights", "share my insights report", "put insights on GitHub Pages", or after generating an /insights report.

Interact with X (Twitter) API v2. Post tweets, search, engage, moderate, and analyze — all from your AI agent. Full 31-command skill for Twitter/X automation.

Autonomous task orchestration with coordinator decisions, optional sub-agents, verification pass, and history compaction. Use when a user asks to run a long task end-to-end, keep iterating until a goal is verified complete, or coordinate multiple agent attempts with a final completion check.

Use when creating handoff document for transferring work to another session

Send messages to Google Chat spaces and users via webhooks or OAuth. Use when you need to send notifications, alerts, or messages to Google Chat channels (spaces) or direct messages to specific users. Supports both incoming webhooks (for predefined channels) and OAuth 2.0 (for dynamic messaging to any space or user).

Create, update, and manage GitHub issues using MCP tools. Use this skill when users want to create bug reports, feature requests, or task issues, update existing issues, add assignees/milestones, or manage issue workflows. Triggers on requests like "create an issue", "file a bug", "request a feature", "update issue X", or any GitHub issue management task. Note: For labeling issues, the github-labels skill provides the canonical label taxonomy.

Pre-built, conversion-optimized HTML section patterns for Mindvalley landing pages and sales pages. Use this skill when building landing pages, sales pages, program pages, or any marketing page that needs Hero sections, Benefits grids, Testimonial sections, FAQ accordions, Pricing tables, or CTA sections. Triggers on "landing page", "sales page", "hero section", "benefits section", "testimonials", "FAQ section", "pricing section", "CTA section", or requests to build complete marketing pages. This skill MUST invoke the mindvalley-design skill for brand compliance.

Generate ASCII art diagrams using PlantUML text mode. Use when user asks to create ASCII diagrams, text-based diagrams, terminal-friendly diagrams, or mentions plantuml ascii, text diagram, ascii art diagram. Supports: Converting PlantUML diagrams to ASCII art, Creating sequence diagrams, class diagrams, flowcharts in ASCII format, Generating Unicode-enhanced ASCII art with -utxt flag

Debug flaky Playwright E2E test failures from CI

Run Pareto analysis to visualize error vs time trade-offs for solvers

Run multi-agent method improvement cycle to identify bottlenecks and generate proposals

Prevent unwanted sample rate upsampling when using ffmpeg loudnorm filter. Use when: (1) ffmpeg loudnorm increases file size 10x, (2) audio upsampled from 24kHz to 192kHz, (3) want to normalize audio while preserving original sample rate. The loudnorm filter defaults to input stream's sample rate which can cause unexpected upsampling if streams have different rates.

Fix for Web Audio API streaming audio players getting stuck or not playing. Use when: (1) Building chunked audio streaming with decodeAudioData, (2) Player shows "playing" but no audio outputs, (3) Audio chunks queue but never play, (4) Source node references are null on first chunk. Critical: AudioBufferSourceNode objects are single-use - must create new source for each chunk, never reuse.

Fix "NotSupportedError: The element has no supported sources" when using HTMLAudioElement or HTMLVideoElement with Base64 data URLs. Use when: (1) audio/video from localStorage or APIs fails to play, (2) data: URLs as src cause browser compatibility issues, (3) mobile Safari refuses to load media. Covers fetch + URL.createObjectURL pattern for better browser support, especially for localStorage persistence and file uploads.

Generate large training datasets (1000+ items) using parallel subagents with rate limit handling. Use when: (1) need to generate >1000 phrases/questions/examples, (2) Task tool hits 429 errors with concurrent agents, (3) need topic-specific variety in generated content, (4) working with multilingual datasets. Covers batch sizing (6 agents per batch), topic distribution strategy, and verification patterns.

Access nested fields in HuggingFace datasets when a field appears to not exist or always returns default values. Use when: (1) iterating a dataset shows all values as False/None/empty for a field you expect to have data, (2) the field exists in raw data but not in dataset objects, (3) working with conversation datasets where metadata like 'features', 'emotion', 'metadata' contain the actual data you need. Covers nested dict access patterns in HuggingFace datasets library.

Fix API 500 errors when frontend sends display names instead of IDs. Use when: (1) Backend API returns 500 Internal Server Error, (2) You're sending speaker_name/user_name/display_name but backend expects file path or ID, (3) Backend constructs file paths like os.path.join(DIR, speaker_name), (4) Error mentions "file not found" or "invalid speaker". Common pattern in file upload, TTS, and media processing apps.

Manage GitOps workflows with Flux and ArgoCD. Use for sync status, reconciliation, app management, source management, and GitOps troubleshooting.

Fix for "module 'torch' has no attribute 'io'" when encoding audio/video. Use when: (1) Using torchaudio.save() or torchvision.save(), (2) Need to encode tensors to in-memory bytes, (3) Getting AttributeError: module 'torch' has no attribute 'io'. Solution: Use Python's built-in io.BytesIO, not torch.io.BytesIO.

Fix "SyntaxError: unterminated string literal" in Python phrase/training data files. Use when: (1) Importing phrase lists fails with syntax error, (2) Large Python files with string lists have dangling quotes like `',`, (3) TTS/training data files with thousands of entries need cleanup. Automates detection and removal of malformed list items that break Python imports.

Manage Istio service mesh for traffic management, security, and observability. Use for traffic shifting, canary releases, mTLS, and service mesh troubleshooting.

Manage vCluster (virtual Kubernetes clusters) instances using vind. Use when creating, managing, or operating lightweight virtual clusters for development, testing, or multi-tenancy.

Configure Kubernetes autoscaling with HPA, VPA, and KEDA. Use for horizontal/vertical pod autoscaling, event-driven scaling, and capacity management.

Generate macOS/iOS Shortcuts by creating plist files. Use when asked to create shortcuts, automate workflows, build .shortcut files, or generate Shortcuts plists. Covers 1,155 actions (427 WF*Actions + 728 AppIntents), variable references, and control flow.

Control smart home devices via Homebridge Config UI X REST API. Use to list, turn on/off, adjust brightness, color, or temperature of HomeKit-compatible accessories. Supports lights, switches, thermostats, fans, and other Homebridge-managed devices.

Enable and configure Moltbot/Clawdbot memory search for persistent context. Use when setting up memory, fixing "goldfish brain," or helping users configure memorySearch in their config. Covers MEMORY.md, daily logs, and vector search setup.

Queries TzKT for Tezos blockchain data and incrementally builds a local gitignored database of immutable records. Supports exporting selected subsets to live project folders for published work. Use when the user says "study", "study TzKT", "build a database of Tezos data", or when preparing TzKT-derived data for export into a project.

Install, list, or remove skills for IronBot via natural language statements and helper scripts.

Synchronize DEV_SPEC.md and split it into chapter-specific files under specs/ directory. Run sync_spec.py to update, then read SPEC_INDEX.md for navigation. Foundation for all spec-based operations. Use when user says "同步规范", "sync spec", or before any spec-dependent task.

This document helps AI agents understand and use phonectl effectively.

This skill should be used when the user asks "what's the config", "show me the configuration", "what variables are set", "environment config", "service config", "railway config", or wants to add/set/delete variables, change build/deploy settings, scale replicas, connect repos, or delete services.

This skill should be used when the user wants to add a database (Postgres, Redis, MySQL, MongoDB), says "add postgres", "add redis", "add database", "connect to database", or "wire up the database". For other templates (Ghost, Strapi, n8n, etc.), use the templates skill.

This skill should be used when the user asks "railway status", "is it running", "what's deployed", "deployment status", or about uptime. NOT for variables ("what variables", "env vars", "add variable") or configuration queries - use environment skill for those.

This skill should be used when the user wants to push code to Railway, says "railway up", "deploy", "deploy to railway", "ship", or "push". For initial setup or creating services, use new skill. For Docker images, use environment skill.

V1.0 - Creates well-structured GitHub Issues that serve as implementation specs with proper labels and escape-safe formatting. Use when creating issues via CLI.

Load and parse checker YAML configuration, detect checker type (1-4)

Read input files and extract sample lines for LLM analysis

This skill parses an ItemSpec JSON file and extracts all information needed for code generation. It transforms the complex ItemSpec structure into a `CodeGenContext` object that can be used by the LLM prompt.

This skill validates Python code using AST (Abstract Syntax Tree) parsing. It checks for syntax errors without executing the code, providing detailed error information for the Evaluator-Optimizer feedback loop.

Browser automation for Squarespace website editing. Performs design changes, content edits, and SEO optimization directly in the Squarespace admin panel.

基于 Django 风格约定的 FastAPI 框架，用于构建生产级 API。使用此 Skill 当用户需要：(1) 创建或开发 FastAPI Web API 项目，(2) 使用 ViewSet（类似 Django REST Framework）实现 CRUD 操作，(3) 配置路由/模型/命令的自动发现系统，(4) 设置中间件、认证、权限、限流、缓存，(5) 定义 Tortoise ORM 模型和数据库关系，(6) 管理应用配置和多环境部署，(7) 从其他框架（FastAPI/DRF）迁移到 Faster APP，(8) 排查 Faster APP 相关错误，(9) 需要遵循约定优于配置原则的标准化项目结构。

Create and validate Claude Code skills following this repository's existing conventions. Use when: (1) adding a new skill to this repo, (2) turning concrete learnings into a reusable skill, (3) validating an existing skill for quality and correctness. This skill focuses on correct structure, minimal scope, and adherence to repo standards.

Enforces dogfooding for tool projects and prevents manual workarounds. Use when building CLIs, libraries, or automation that you should use yourself. Triggers on: feature completion, session end, tool failures.

Adds or updates skill templates in the skills-master library. Invoke when user wants to contribute a new skill to the master library.

Pull the latest skills-master directory from a remote GitHub repository and replace the local skills-master directory. Uses Git sparse checkout to fetch only the skills-master folder without cloning the entire repository. Invoke when user wants to update, sync, or pull the latest skills from the master repository.

Control the Canvas display on paired nodes (iOS, Android, macOS). Show web content, run JS, capture screenshots, and display real-time UI.

Create and maintain packages for the Terra package repository (Fedora-based). Use when: creating new packages, writing RPM spec files, creating AndaX update scripts, packaging applications, or setting up auto-updates

Query Rollbar error tracking to investigate errors, list recent issues, resolve items, and get context for bug fixes. Use when the user asks about production errors, wants to investigate an error, asks "what errors happened overnight", wants to mark issues as resolved, or needs context to fix a bug from Rollbar.

OpenClaw Agent Infrastructure Guardian — keep your agent's infrastructure alive. Process lifecycle management with detached execution, auto-restart on failure. Cron scheduler health monitoring (per-job detection, auto-recovery). Direct Telegram/messaging alerts independent of OpenClaw. System-level watchdog that runs from crontab, not OpenClaw cron. Use when launching background processes, monitoring cron job health, or when things keep dying silently.

Slack Web APIを操作するスキル。メッセージの投稿・取得、スレッドの取得、投稿の検索、ユーザー情報の取得を実行。 使用タイミング: (1) Slackにメッセージを投稿したい (2) チャンネルのメッセージ履歴を取得したい (3) スレッドの返信を取得したい (4) 自分の投稿を検索したい (5) ユーザー情報を取得したい トリガーキーワード: Slack、メッセージ送信、スレッド取得、チャンネル履歴、ユーザー取得

Expert agent for React Native mobile application development across iOS and Android

Change or validate daily recurring logic (template+log, dateKey, reset rules). Produces spec delta, invariants, migration needs, and a concrete test plan aligned with testing.md.

Parse YAML frontmatter from markdown notes into structured data. Use when searching, filtering, or querying notes by their metadata properties (created, tags, author, summary, TOPIC, PRIOR, NEXT, RELATED_TO, etc.). Enables quick property-based searches across the vault.

Validate and sync bidirectional semantic links in YAML frontmatter. Ensures RELATED_TO links are mutual between notes, and PRIOR/NEXT links are properly reversed. Use when checking link consistency, fixing broken bidirectional relationships, or maintaining Zettelkasten semantic properties.

Perform BFS (breadth-first search) graph traversal on notes connected via wikilinks. Use when exploring note relationships, discovering connected knowledge within N hops, mapping knowledge graphs, finding related notes from a starting point, or understanding the link structure around a concept.

Find and replace standalone alias wikilinks [[alias]] with their full format [[actual note name|alias]]. Use when normalizing wikilink syntax, cleaning up alias references, or ensuring links display with custom text while pointing to the correct note.

Deduplicate wikilinks in any YAML frontmatter property that contains multi-line wikilink arrays. Removes case-insensitive duplicates like [[ml]] and [[ML]], keeping the version with more capital letters. Use when cleaning up frontmatter, fixing duplicate links, or normalizing link casing.

Comprehensive conventional commit message specification and guidance. Use when creating git commits, writing commit messages, reviewing commit history, or setting up commit message validation. Includes commit types, scopes, breaking change indicators, body/footer format, and versioning rules for automated changelog generation.

Analyze daily token consumption from OpenClaw session transcripts. Use when the user asks about token usage, API costs, token breakdown, usage report, or wants to optimize token spending. Triggers on phrases like "token usage", "how many tokens", "API cost", "usage report", "token breakdown".