AI Skills Hub - Browse 180,000+ Agent Skills

Use when analyzing codebases for structure, finding symbols, tracing call paths, checking test coverage, or analyzing dependencies - provides instant AST-based code analysis using tree-sitter for Python, JavaScript, TypeScript, Rust, Java, Go, and C

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.

This skill should be used when working on Godot Engine projects. It provides specialized knowledge of Godot's file formats (.gd, .tscn, .tres), architecture patterns (component-based, signal-driven, resource-based), common pitfalls, validation tools, code templates, and CLI workflows. The `godot` command is available for running the game, validating scripts, importing resources, and exporting builds. Use this skill for tasks involving Godot game development, debugging scene/resource files, implementing game systems, or creating new Godot components.

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

Bayesian modeling with PyMC. Build hierarchical models, MCMC (NUTS), variational inference, LOO/WAIC comparison, posterior checks, for probabilistic programming and inference.

Query NCBI Gene via E-utilities/Datasets API. Search by symbol/ID, retrieve gene info (RefSeqs, GO, locations, phenotypes), batch lookups, for gene annotation and functional analysis.

Create and manage isolated Docker workspaces on your tailnet with Claude Code and OpenCode pre-installed. Use when working with Perry workspaces, connecting to coding agents, or managing remote development environments.

Generate detailed token usage report with threshold analysis and recommendations

Check status of running subagents including token usage and context limits

What it does AND when to use it. Include key terms and triggers.

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.

Deploying, managing, executing, and monitoring dbt projects natively within Snowflake using dbt

Manage and synchronize AI agent skills from local SKILL.md files and remote Git repositories,

Ultra-fast data discovery and loading skill for industrial finance datasets. Handles CSV, JSON, DuckDB, Parquet, and Feather with memory-efficient 2-step discovery and loading.

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 writing or refactoring Ruby code that integrates Claude Code via the claude-agent-sdk gem (ClaudeAgentSDK.query, ClaudeAgentSDK::Client, streaming input, ClaudeAgentOptions configuration, tools/permissions, MCP servers, hooks, structured output, budgets, sandboxing, session resumption/rewind, and Rails patterns like jobs or ActionCable).

Expert API designer for REST, GraphQL, gRPC architectures. Activate on: API design, REST API, GraphQL schema, gRPC service, OpenAPI, Swagger, API versioning, endpoint design, rate limiting, OAuth flow. NOT for: database schema (use data-pipeline-engineer), frontend consumption (use web-design-expert), deployment (use devops-automator).

Expert in 2000s-era music visualization (Milkdrop, AVS, Geiss) and modern WebGL implementations. Specializes in Butterchurn integration, Web Audio API AnalyserNode FFT data, GLSL shaders for audio-reactive visuals, and psychedelic generative art. Activate on "Milkdrop", "music visualization", "WebGL visualizer", "Butterchurn", "audio reactive", "FFT visualization", "spectrum analyzer". NOT for simple bar charts/waveforms (use basic canvas), video editing, or non-audio visuals.

Comprehensive MDX content sanitizer that escapes angle brackets, generics, and other JSX-conflicting patterns to prevent build failures

Manage DAG execution lifecycles including start, stop, pause, resume, and cleanup. Activate on 'execution lifecycle', 'stop execution', 'abort DAG', 'graceful shutdown', 'kill process'. NOT for cost estimation, DAG building, or skill selection.

Strategic analyst that maps competitive landscapes, identifies white space opportunities, and provides positioning recommendations. Use when users need competitive analysis, market positioning strategy, differentiation tactics, or "how do I stand out?" guidance across any domain (portfolios, products, services). NOT for market size estimation or financial forecasting.

Expert bot developer specializing in Discord, Telegram, Slack automation with deep knowledge of rate limiting, state machines, event sourcing, moderation systems, and conversational AI integration. Activate on 'Discord bot', 'Telegram bot', 'Slack bot', 'chat automation', 'moderation system'. NOT for web APIs (use backend-architect), general automation scripts (use python-pro), or frontend chat widgets (use frontend-developer).

Analyze FEC (Federal Election Commission) campaign finance filings. Use when working with FEC filing IDs, campaign finance data, contributions, disbursements, or political committee financial reports.

Create a new GitHub repository with the gh CLI and bootstrap a local project in ~/projects with git init, README, remote setup, and initial push. Use when the user asks to create a repo (public/private) in their account, set up the local folder, add the upstream remote, and push the first commit.

Debug pattern errors systematically

Guide for using the ct (CommonTools) binary to interact with charms,

Microscopy data management platform. Access images via Python, retrieve datasets, analyze pixels, manage ROIs/annotations, batch processing, for high-content screening and microscopy workflows.

Analyze FEC (Federal Election Commission) campaign finance filings. Use when working with FEC filing IDs, campaign finance data, contributions, disbursements, or political committee financial reports. Provides the proper workflow for the fec-api MCP tools (search_committees, get_filings).

Interface for MCP (Model Context Protocol) servers via CLI. Use when you need to interact with external tools, APIs, or data sources through MCP servers.

Real-time bidirectional communication with security focus on CSWSH prevention, authentication, and message validation

Concurrent operations with asyncio and Tokio, focusing on race condition prevention, resource safety, and performance

Manage git worktrees for parallel development. Use when the user wants to work on multiple branches simultaneously, create isolated environments for features/fixes, or clean up completed worktrees.

Expert guidance for creating syntactically correct Mermaid diagrams. Use when creating flowcharts, sequence diagrams, class diagrams, state diagrams, Gantt charts, ER diagrams, or data lineage visualizations.

Capture solved problems as categorized documentation with YAML frontmatter for fast lookup

Use when implementing Hotwire features with Turbo Drive, Turbo Frames, and Turbo Streams. Applies Rails 8 conventions, morphing, broadcasts, lazy loading, and real-time update patterns.

Validate skills against agentskills.io specification. Use when adding new skills to the marketplace, reviewing skill PRs, checking skill compliance, or running quality gates on skills. Validates frontmatter fields (name, description, license, compatibility, metadata, allowed-tools), directory naming, line limits, and structure.

Comprehensive Git push operations including basic push, force push safety protocols, tag pushing, remote management, and troubleshooting. Use when pushing commits, managing remotes, pushing tags, resolving push conflicts, handling rejected pushes, or dealing with force push scenarios. Covers push strategies, branch protection, upstream configuration, and push --force-with-lease best practices.

This skill should be used when reading any tabular data file (Excel, CSV, Parquet, ODS). It automatically detects and fixes common data issues including multi-level headers, encoding problems, empty rows/columns, and data type mismatches. Returns a clean DataFrame ready for analysis with zero user intervention.

Comprehensive guide for building full-stack applications with Convex and TanStack Start. This skill should be used when working on projects that use Convex as the backend database with TanStack Start (React meta-framework). Covers schema design, queries, mutations, actions, authentication with Better Auth, routing, data fetching patterns, SSR, file storage, scheduling, AI agents, and frontend patterns. Use this when implementing features, debugging issues, or needing guidance on Convex + TanStack Start best practices.

Generates Figma Code Connect mappings for React or Angular repos, validates them with pre-checks and the Figma CLI, and can publish via figma connect. Use when a user provides a Figma file URL and a component repo and asks for Code Connect files, figma.config.json, or validation.

Reviews Go code for idiomatic patterns, error handling, concurrency safety, and common mistakes. Use when reviewing .go files, checking error handling, goroutine usage, or interface design.

Reviews CloudKit code for container setup, record handling, subscriptions, and sharing patterns. Use when reviewing code with import CloudKit, CKContainer, CKRecord, CKShare, or CKSubscription.

Reviews BubbleTea TUI code for proper Elm architecture, model/update/view patterns, and Lipgloss styling. Use when reviewing terminal UI code using charmbracelet/bubbletea.

Write Architectural Decision Records following MADR template. Applies Definition of Done criteria, marks gaps for later completion. Use when generating ADR documents from extracted decisions.

SvelteKit data flow guidance. Use for load functions, form actions, server/client data, and invalidation. Covers +page.server.ts vs +page.ts, serialization, fail(), redirect(), error(), invalidateAll().

Use this when updating the codex submodule or when patch files in codex-patches/ need to be added, regenerated, or repaired.

Setup and use text-to-SQL capabilities for SQL databases (SQLite, PostgreSQL, MySQL, MariaDB, etc.). Use when: (1) User wants to query databases using natural language, (2) User asks to setup text-to-sql project, (3) User mentions extracting data from database, (4) User has .sqlite/.db file or database credentials and wants to work with data. This skill sets up project structure, extracts database schema, and enables natural language to SQL conversion.

Search 76M+ patents using BigQuery (fast, zero setup) or PatentsView API (US patents with rich metadata).

Guides through installation, configuration, and first-time setup of the Claude Patent Creator system.

Background HTTP server rendering markdown files with calm, book-like reading experience.

Plans dashboard server with progress tracking and timeline visualization.

Use when you have implemented an equivariant model and need to verify it correctly respects the intended symmetries. Invoke when user mentions testing model equivariance, debugging symmetry bugs, verifying implementation correctness, checking if model is actually equivariant, or diagnosing why equivariant model isn't working. Provides verification tests and debugging guidance.

串联赛题解析、数据计算与微单元脚本，一键从赛题文件夹到完整论文。Invoke when用户已放好赛题与附件，希望自动跑完全流程。

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.

Token-efficient library documentation fetcher using Context7 MCP with 86.8% token savings through intelligent shell pipeline filtering. Fetches code examples, API references, and best practices for JavaScript, Python, Go, Rust, and other libraries. Use when users ask about library documentation, need code examples, want API usage patterns, are learning a new framework, need syntax reference, or troubleshooting with library-specific information. Triggers include questions like "Show me React hooks", "How do I use Prisma", "What's the Next.js routing syntax", or any request for library/framework documentation.

Cross-platform messaging aggregator. Use as DEFAULT when user does NOT specify a platform (telegram/imessage). Provides unified inbox, search, and triage across both platforms. Triggers: "check messages" (no platform), "inbox", "who messaged me", "all my messages", "triage". NOT for platform- specific requests - use tg-ingest for "telegram X" or imsg-ingest for "imessage X".

CLI tools for Are.na: export blocks, enrich with vision AI, generate views. Use when: (1) exporting Are.na blocks incrementally, (2) enriching images with AI-generated titles/tags/patterns, (3) generating browsable HTML views, (4) searching blocks by UI patterns or tags, (5) visual search results when terminal output is insufficient. Triggers: "export arena", "enrich arena", "sync arena", "arena view", "search arena for [pattern]", "show me [pattern]".

Set up webhook-to-desktop notification systems using Cloudflare Workers and ntfy.sh. Use when users want to receive desktop notifications for webhooks from services like Stripe payments, GitHub events, custom app alerts, error monitoring, or any webhook source. Handles the full setup including worker deployment, local listener, and background service installation. Supports custom sounds, click actions, rich content, and event filtering.

Primary iMessage interface. Full-featured CLI for message export, conversation management, contact resolution, and thread state. Use when user mentions "imessage", "imsg", "text message", "iphone messages", or phone numbers. Triggers: "imessage messages", "export imessage", "text from john", "imessage contacts", "sync imessage". This is STANDALONE - do not defer to unified-messages for iMessage operations.

Converts a Refound/Lenny Skill into a high-density, agent-executable Skill Pack (Agent Skills standard). Output must be in English.

Expert guidance for using JJ (Jujutsu) version control system. Use when working with JJ, whatever the subject. Operations, revsets, templates, debugging change evolution, etc. Covers JJ commands, template system, evolog, operations log, and interoperability with git remotes.

Expert guidance for agents to manage local Nix profiles for installing tools and dependencies. Covers flakes, profile management, package searching, and registry configuration.

Launch Baldur's Gate 3 through Steam on macOS and load saved games using macos-automator and peekaboo MCP servers. Designed for testing bg3se-macos (Script Extender) development. Use when: (1) launching BG3 from Steam, (2) loading a BG3 saved game, (3) testing SE mod injection, (4) user asks to "start BG3", "load my BG3 save", "play Baldur's Gate", "test the script extender". Requires macos-automator and peekaboo MCP servers installed with accessibility permissions.

This skill should be used when designing, implementing, or reviewing CLI tools, or when flags, subcommands, help text, exit codes, or `--cli-dev` are mentioned.

Skill with validation hooks

使用此技能自动启动Godot MCP服务器，确保在Godot项目启动时MCP工具可用。当需要确保MCP连接就绪或在项目启动时自动初始化MCP工具时触发。

first heading or first line — max 40 chars, truncate with `…`

Load vtable information from a pre-generated YAML file. Use this skill when you need to get vtable address and size for a class before analyzing virtual functions. This skill checks for existing vtable YAML files and errors out if not found, ensuring the vtable analysis has been done first.

Scaffold iOS apps with Tuist and layered architecture (Domain, Infrastructure, App). Use when: (1) Creating a new iOS app project, (2) Setting up Tuist project structure, (3) User asks to "create an iOS app", "scaffold an app", or "set up a new Swift project", (4) User wants layered/clean architecture for iOS, (5) User mentions Tuist setup.

Optimize and manage AILANG teaching prompts for maximum conciseness and accuracy. Use when user asks to create/update prompts, optimize prompt length, or verify prompt accuracy.

Find AILANG vs Python eval gaps and improve prompts/language. Use when user says 'find eval gaps', 'analyze benchmark failures', 'close Python-AILANG gap', or after running evals.

Create new AILANG releases with version bumps, changelog updates, git tags, and CI/CD verification. Use when user says "ready to release", "create release", mentions version numbers, or wants to publish a new version.

Develop and modify the AILANG Collaboration Hub UI. Use when user asks to add features to the monitoring dashboard, modify the approval queue, update the message center, or make changes to the React frontend.

Write and run AILANG code with correct syntax. Use when user asks to write AILANG programs, fix AILANG syntax errors, run AILANG code, or needs help with AILANG syntax. Includes version checking, syntax validation, and common patterns.

Guides AILANG parser development with conventions and patterns. Use when user wants to modify parser, understand parser architecture, or debug parser issues. Saves 30% of development time by preventing token position bugs.

Ensure AILANG CLI help system (`ailang --help`) remains the authoritative, accurate, and complete source of truth for all CLI features. Critical for AI discoverability in external repositories where CLAUDE.md isn't available.

Authoritative templates and scaffolding for creating agent system prompts (primary agents and subagents). This skill should be used when creating new agents, reviewing existing agent prompts for template compliance, verifying agent structure, or extracting knowledge into agent prompts. Contains YAML templates with section-by-section instructions and scaffolding scripts for generating skeleton files.

Authoritative templates and scaffolding for creating slash commands. This skill should be used when creating new commands, reviewing existing commands for template compliance, or understanding command structure. Contains YAML templates with section instructions and scaffolding scripts for generating command skeleton files.

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.

Manage PR review feedback loops with Gemini Code Assist. Use when pushing changes to a PR, iterating on review feedback, or monitoring CI/review status. Automatically falls back to Claude when Gemini is rate-limited.

HarmonyOS build and deploy automation. Compile HarmonyOS apps and install to real devices with one command. Supports Windows (PowerShell), macOS, and Linux. Use when user needs to: (1) Build HarmonyOS project to generate HAP/APP package, (2) Install app to real device, (3) One-click build + install, (4) View connected HarmonyOS devices, or mentions hvigor, hdc, HAP installation.

Use when a user asks to review, interpret, or audit an AI agent skill (SKILL.md plus bundled scripts/references/assets) for capabilities, triggering behavior, tool/command usage, safety & privacy risk, supply-chain provenance, quality gaps, and improvement recommendations; also use when validating a skill before installing or deploying it.

Render and view webpages using a headless browser (Playwright) to fetch JS-rendered HTML, extract visible text, and optionally save full-page screenshots. Use when a user asks to “无头浏览器打开/查看网页”, needs the rendered DOM instead of raw curl HTML, or wants a screenshot of a page.

Generate Chinese official document (公文) Word files from controlled Markdown or JSON. Use when producing or updating .docx 公文 that must follow fixed fonts, line spacing, title/recipient layout, attachments, and footer page numbers, especially when the input is a controlled Markdown protocol.

Use when user wants to extract text from ebooks (EPUB, MOBI, PDF). Use for converting ebooks to plain text for analysis, processing, or reading. Handles all common ebook formats.

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.

Guides pytest test writing for LangGraph casts with mocking patterns for LLM/API/Store calls. Use when writing tests, need mock strategies, setting up fixtures, testing nodes/graphs, or ask "write tests", "mock LLM", "test coverage".

Guide for using Apollo MCP Server to connect AI agents with GraphQL APIs. Use this skill when: (1) setting up or configuring Apollo MCP Server, (2) defining MCP tools from GraphQL operations, (3) using introspection tools (introspect, search, validate, execute), (4) troubleshooting MCP server connectivity or tool execution issues.

Quality assurance and CodeRabbit learning system for Zammad MCP development. Use when creating PRs, implementing MCP tools, adding pagination, handling errors, or addressing CodeRabbit feedback. Provides checklists, pattern guides, and accumulated project learnings to prevent recurring issues.

Run GDUnit4 tests for Godot projects. Use after implementing features, fixing bugs, or modifying GDScript files to verify correctness.

This skill provides guidance for implementing Go Embedded SPA architecture - embedding React/Vue/TSX frontend static resources into Go binary using go:embed directive. Use this skill when building self-contained single-binary applications, implementing SPA with Go backend, setting up cross-platform deployable full-stack projects, or configuring static file serving with Go standard library net/http.

百度语音识别 - 将语音消息转换为文本。支持中文普通话、英语、粤语、四川话。专为国内服务器环境优化，自动绕过代理访问百度 API。

Generate 3D historical gourmet diorama images for Chinese cities using Google Gemini API. Creates artistic miniature food worlds with four-quadrant layouts featuring iconic dishes, Pop Mart style figures, and cultural elements. Use when the user asks to create food diorama, 美食盲盒, gourmet blind box, city food scene, or mentions generating 3D food artwork for cities like 西安, 重庆, 成都, 北京, 广州.

Systematic methodology for constructing compact (<150 lines), expressive, Claude Code-integrated subagent prompts using lambda contracts and symbolic logic. Use when creating new specialized subagents for Claude Code with agent composition, MCP tool integration, or skill references. Validated with phase-planner-executor (V_instance=0.895).

Generate comprehensive test coverage reports when reviewing code. Identifies untested code paths and low-coverage areas. Supports Python (pytest-cov), JavaScript (jest), Go (go test -cover), Java (JaCoCo). Use when reviewing tests or before approving code changes.

Seed JSON configuration files into database. Use ONCE at BAZINGA session initialization, BEFORE spawning PM.

Unified project health dashboard aggregating all quality metrics

Determine next agent based on state machine rules. Use AFTER receiving any BAZINGA agent response to decide what to do next.

Run code quality linters when reviewing code. Checks style, complexity, and best practices. Supports Python (ruff), JavaScript (eslint), Go (golangci-lint), Ruby (rubocop), Java (Checkstyle/PMD). Use when reviewing any code changes for quality issues.

Detect dangerous operations in database migrations before deployment