AI Skills Hub - Browse 180,000+ Agent Skills

Interactive planning and execution for complex tasks. Use when user asks to use or invoke planner skill.

Analyze disk usage across directories, identify large/old directories, and generate storage reports. Use when you need to find directories consuming disk space, identify candidates for cleanup (directories older than X days AND larger than Y MB), sort results by size, or generate disk usage reports. Supports filtering by age and size, automatic sorting by disk space, and file-based report generation.

Typst technical foundation layer providing syntax reference, toolchain commands, package management, and diagram solution selection (diagraph/D2/oxdraw). Serves as technical reference for slide and report skills.

Process large volumes of local materials with parallel sub-agents. Features task decomposition, context isolation, parallel execution, and narrative synthesis. Use when processing multiple files, batch analysis, building narratives from existing materials, or when user mentions "wide research", "batch analysis", "批量分析", "整理材料", "构建叙事".

Conduct comprehensive research with persistent output. Features: user clarification, supervisor-based dynamic parallelization, source archival, and structured findings. Activate on: "research", "调研", "研究", "深入了解", "investigate", "explore".

Store and transform images with Cloudflare Images API and transformations. Use when: uploading images, implementing direct creator uploads, creating variants, generating signed URLs, optimizing formats (WebP/AVIF), transforming via Workers, or debugging CORS, multipart, or error codes 9401-9413.

Build with OpenAI's stateless APIs - Chat Completions (GPT-5, GPT-4o), Embeddings, Images (DALL-E 3), Audio (Whisper + TTS), and Moderation. Includes Node.js SDK and fetch-based approaches for Cloudflare Workers. Use when: implementing chat completions with GPT-5/GPT-4o, streaming responses with SSE, using function calling/tools, creating structured outputs with JSON schemas, generating embeddings for RAG (text-embedding-3-small/large), generating images with DALL-E 3, editing images with GPT-Image-1, transcribing audio with Whisper, synthesizing speech with TTS (11 voices), moderating content (11 safety categories), or troubleshooting rate limits (429), invalid API keys (401), function calling failures, streaming parse errors, embeddings dimension mismatches, or token limit exceeded.

Build secure WordPress plugins with core patterns for hooks, database interactions, Settings API, custom post types, REST API, and AJAX. Covers three architecture patterns (Simple, OOP, PSR-4) and the Security Trinity. Use when creating plugins, implementing nonces/sanitization/escaping, working with $wpdb prepared statements, or troubleshooting SQL injection, XSS, CSRF vulnerabilities, or plugin activation errors.

Build stateless MCP servers with TypeScript on Cloudflare Workers using @modelcontextprotocol/sdk. Provides patterns for tools, resources, prompts, and authentication (API keys, OAuth, Zero Trust). Use when exposing APIs to LLMs, integrating Cloudflare services (D1, KV, R2, Vectorize), or troubleshooting export syntax errors, unclosed transport leaks, or CORS misconfigurations.

Generate typed TypeScript SDKs for AI agents to interact with MCP servers. Converts verbose JSON-RPC curl commands to clean function calls (docs.createDocument() vs curl). Auto-detects MCP tools from server modules, generates TypeScript types and client methods, creates runnable example scripts. Use when: building MCP-enabled applications, need typed programmatic access to MCP tools, want Claude Code to manage apps via scripts, eliminating manual JSON-RPC curl commands, validating MCP inputs/outputs, or creating reusable agent automation.

Build CLI scripts alongside MCP servers for terminal environments. Scripts provide file I/O, batch processing, caching, and richer output formats that remote MCP servers cannot offer. Includes templates for TypeScript scripts and SCRIPTS.md. Use when: creating MCP server companion scripts, adding batch processing to MCP tools, saving MCP results to files, building CLI wrappers for APIs, or troubleshooting "context too large", "no file access", or batch input handling.

Integrate Redis-compatible Vercel KV for caching, session management, and rate limiting in Next.js applications. Powered by Upstash with strong consistency and TTL support. Use when implementing cache strategies, storing temporary data with expiration, building rate limiters, or troubleshooting missing environment variables, serialization errors, or rate limit issues.

This skill should be used when the user asks to "document directories", "create CLAUDE.md files", "document folder structure", "generate directory documentation", or wants to automatically document subdirectories of a root path. Provides the complete workflow for orchestrating parallel sub-agents to create documentation files.

This skill should be used by subagents when extracting and parsing CLAUDE.md documentation index files. Provides universal extraction rules, output format specification, and source attribution requirements.

Converts Markdown articles to WeChat public account-friendly HTML format with professional typography. Use when formatting articles for WeChat, converting Markdown to WeChat HTML, or when user mentions WeChat formatting or publishing.

Use when configuring or running Python quality tools (ruff, ty, pytest, coverage, CI gates) and when enforcing a pre-merge quality checklist.

Reviews code for bugs, race conditions, missing error handling, type safety issues, and PM UAT readiness. Use when reviewing code written by other agents, checking for bugs, preparing for deployment, or when user mentions code review, bugs, errors, or UAT.

Extract complete content from a single webpage and its direct links only (depth 0 + depth 1). Does NOT recursively follow links beyond the first level. Use when you need focused extraction without deep crawling.

Unified design system for data/ML dashboards. Quick reference for brand vs data color decisions, component patterns, typography, spacing. Auto-invokes on styling, CSS, design, colors, UI, visualization keywords. Tiered loading - core always, philosophy/implementation on-demand.

프레젠테이션 슬라이드 컴포넌트 생성. 새 슬라이드 추가, 슬라이드 디자인, 발표자료 레이아웃 요청 시 사용. React + TailwindCSS 기반 다크모드 UI.

このリポジトリの GitHub Actions CI（.github/workflows/ci.yml）の失敗を切り分け、ローカル再現によって原因を最短で特定する手順を提供する。PR/push の CI run が失敗している、または Build/Test/Lint の失敗ログ解釈が必要な場合に有効。

Detect sample contamination and cross-species reads using FastQ Screen. Screen reads against multiple reference genomes to identify bacterial, viral, adapter, or sample swap contamination. Use when suspecting cross-contamination or working with samples prone to microbial contamination.

keywords: - mcp-builder - automation - biomedical measurable_outcome: execute task with >95% success rate. ---"

keywords: - xlsx - automation - biomedical measurable_outcome: execute task with >95% success rate. ---"

keywords: - docx - automation - biomedical measurable_outcome: execute task with >95% success rate. ---"

Search for places and activities via Google Maps Places API (New). For inventory agent: builds exhaustive activity masterlist across multiple categories.

Workflow orchestrator and dispatcher between inventory subagents. Validates outputs, cross-checks agent claims, updates execution state, and routes to the next phase. Use when accommodation or activities subagent completes to report what happened and relay/enforce what to do next.

Hotel search, rates, and booking API for building travel applications.

End-to-end copy number variant detection workflow from BAM files. Covers CNVkit analysis for exome/targeted sequencing with visualization and annotation. Use when detecting copy number alterations from sequencing data.

End-to-end bisulfite sequencing workflow from FASTQ to differentially methylated regions. Covers Bismark alignment, methylation calling, and DMR detection with methylKit. Use when analyzing bisulfite sequencing data.

Call accessible chromatin regions from ATAC-seq data using MACS3 with ATAC-specific parameters. Use when identifying open chromatin regions from aligned ATAC-seq BAM files, different from ChIP-seq peak calling.

Generate comprehensive WIKI.md documentation for any codebase using LSP for precise code analysis. Use when user asks to document a codebase, generate technical documentation, create architecture diagrams, or analyze code structure and dependencies. Supports TypeScript, JavaScript, Python, Go, Rust, Java, and C/C++ projects.

Generate reverse complements and complements of DNA/RNA sequences using Biopython. Use when working with opposite strands, primer design, or converting between template and coding strands.

Transcribe DNA to RNA and translate to protein using Biopython. Use when converting between DNA, RNA, and protein sequences, finding ORFs, or using alternative codon tables.

Slice, extract, and concatenate biological sequences using Biopython. Use when extracting subsequences, joining sequences, or manipulating sequence regions by position.

Create and use BAI/CSI indices for BAM/CRAM files using samtools and pysam. Use when enabling random access to alignment files or fetching specific genomic regions.

Convert between sequence file formats (FASTA, FASTQ, GenBank, EMBL) using Biopython Bio.SeqIO. Use when changing file formats or preparing data for different tools.

Write biological sequences to files (FASTA, FASTQ, GenBank, EMBL) using Biopython Bio.SeqIO. Use when saving sequences, creating new sequence files, or outputting modified records.

keywords: - probability-statistics - automation - biomedical measurable_outcome: Converge to within 5% of the optimal parameter set within 10 iterations. ---"

Quantify transcript expression using pseudo-alignment with Salmon or kallisto. Use when quantifying transcripts with Salmon or kallisto.

Count reads per gene from aligned BAM files using Subread featureCounts. Use when processing BAM files from STAR/HISAT2 to generate gene-level counts for DESeq2/edgeR.

Quantifies alternative splicing events (PSI/percent spliced in) from RNA-seq using SUPPA2 from transcript TPM or rMATS-turbo from BAM files. Calculates inclusion levels for skipped exons, alternative splice sites, mutually exclusive exons, and retained introns. Use when measuring splice site usage or isoform ratios from RNA-seq data.

Assesses RNA-seq data quality for splicing analysis including junction saturation curves, splice site strength scoring, and junction coverage metrics using RSeQC. Use when evaluating data suitability for splicing analysis or troubleshooting low event detection.

Creates sashimi plots showing RNA-seq read coverage and splice junction counts using ggsashimi or rmats2sashimiplot. Visualizes differential splicing events with grouped samples and junction read support. Use when visualizing specific splicing events or validating differential splicing results.

Automate sgRNA selection, scoring, off-target evaluation, and oligo generation for CRISPR experiments using the documented workflow.

High-quality genome assembly from PacBio HiFi reads using hifiasm with phasing support. Use when building reference-quality diploid assemblies from HiFi data, especially with trio or Hi-C phasing for fully resolved haplotypes.

De novo genome assembly from Oxford Nanopore or PacBio long reads using Flye and Canu. Produces highly contiguous assemblies suitable for complete bacterial genomes and resolving complex regions. Use when assembling genomes from ONT or PacBio reads.

Call SNPs and indels from aligned reads using bcftools mpileup and call. Use when detecting variants from BAM files or generating VCF from alignments.

UI validation with Chrome MCP browser automation. Use when testing UI components, verifying pages render correctly, testing forms and interactions, or validating visual changes.

Use CellTypeAgent to interpret marker genes, annotate scRNA-seq clusters, and coordinate multi-agent workflows for downstream analysis.

Analyzes cfDNA fragment size distributions and fragmentomics features using FinaleToolkit or Griffin. Extracts nucleosome positioning patterns, fragment ratios, and DELFI-style fragmentation profiles for cancer detection. Use when leveraging fragment patterns for tumor detection or tissue-of-origin analysis.

Filter and prioritize variants by pathogenicity, population frequency, and clinical evidence for rare disease analysis. Use when identifying candidate disease-causing variants from exome or genome sequencing.

Structure raw clinical notes into SOAP-format summaries with explicit contradictions, missing data, and ICD-linked assessments using the provided prompt + usage script.

Use when setting up DocC documentation for a Swift package, deploying to GitHub Pages, or encountering "no such module 'UIKit'" during doc generation

> **用途**: 分析 GitHub Agentic Workflows 的方法论和设计模式识别 > **阅读时机**: Phase 2（分析）开始时 > **行数目标**: 骨架文件，详细内容在子目录

> 本地代理配置与网络问题排查

云端开发环境配置 - GitHub Secrets 管理、SSH 连接、服务器访问

Query GitHub issues efficiently with jq argument support for filtering

Query GitHub discussions efficiently with jq argument support for filtering

Best practices for writing JavaScript code for GitHub Actions using github-script

Query GitHub pull requests efficiently with jq argument support for filtering

Error Pattern Safety Guidelines for Agentic Engines

技能深度审计器：对 SKILL.md 执行五维度深度审计（结构、激活、示例、数值、接口），验证逻辑完整性与数值合理性。当用户说'审计技能'、'检查 Skill 质量'、'验证设计'、'审计项目'时激活。输入目标 SKILL.md，输出 @audit-report.md。

Create specialized expert Claude Code sub-agents from Smart Librarian knowledge bases. This skill should be used when users want to create domain-specific expert agents (e.g., claude-code-expert, radar-expert, numpy-expert) that can efficiently answer questions using structured documentation with INDEX.md files.

Copy project-specific .claude configurations to main claude_configuration directory with interactive selection and conflict resolution

ブランチ作成Skill。仕様策定用（spec/*）または実装用（impl/*）のブランチを作成。/spec や spec-workflow から呼び出される。

This skill should be used when the user asks to "read my emails", "send an email", "compose email", "check my calendar", "get calendar events", "create a meeting", "schedule an event", "add calendar event", "search emails", "list mail folders", "show unread messages", "what meetings do I have", "fetch emails from Microsoft", "access Outlook", or mentions Microsoft Graph, Office 365 email, or Outlook calendar integration.

This skill should be used when the user asks to "search Notion", "find in Notion", "search my Notion workspace", "create Notion page", "make a Notion page", "update Notion page", "edit Notion page", "query Notion database", "get Notion database", "read Notion page", "get page content from Notion", "list Notion pages", or mentions Notion integration, Notion workspace, or Notion API access.

Quality review with traceability check

Pre-edit gate enforcing WS scope (INTERNAL)

Import content into local RAG. Triggers: "add to RAG", "scrape docs", "import YouTube", "embed PDF", "build knowledge base", "embedda sito", "importa video", "aggiungi PDF", "crea knowledge base".

Prepare a release including version bump, testing, and PR creation

Run tests, linting, and formatting checks for dotenvage

Bump version in Cargo.toml using cargo-version-info bump command

Create and manage shadcn/ui component registries. Use when building custom component registries, distributing React components via shadcn CLI, creating registry.json or registry-item.json files, or setting up a component distribution system for shadcn/ui compatible projects.

Master end-to-end testing with Cypress and Playwright for complete user journey testing.

Fetches live play-by-play data from Tank01 API

Structured debugging workflow with log server capture and analysis

Manage UnaMentis services via USM API (never via bash kill commands)

Manage tasks in Notion. List, create, update tasks. Use for any Notion task-related operations.

Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When 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

Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When OpenCode needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for: (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modify existing spreadsheets while preserving formulas, (4) Data analysis and visualization in spreadsheets, or (5) Recalculating formulas

Model Context Protocol (MCP) server development and AI/ML integration patterns. Covers MCP server implementation, tool design, resource handling, and LLM integration best practices. Use when developing MCP servers, creating AI tools, integrating with LLMs, or when asking about MCP protocol, prompt engineering, or AI system architecture.

Use when crawling web pages, extracting markdown content, or scraping website data with intelligent chunking and skeleton planning.

SKiDLを使用した回路設計。以下の場合に使用: (1) 「回路を設計」「分圧回路」「フィルタ回路」などの電子回路リクエスト (2) ネットリスト・回路図（SVG）の生成 (3) SPICEシミュレーション 入力: 仕様書または自然言語要望 出力: Pythonスクリプト、ネットリスト、SVG、シミュレーション結果

Implementation planning with Spec-Driven Development (SDD). Use when: Starting new feature development, Breaking down complex requirements, Estimating AI-assisted development tasks, Creating hierarchical project plans.

Git conventions, branching strategies, and commit practices. Use when: Choosing a branching strategy, Writing commit messages, Creating pull requests, Reviewing code.

Code writing best practices for clean, maintainable software. Use when: Writing new code or features, Reviewing code quality, Refactoring existing code, Pair programming with AI.

Expert in testing CI/CD pipelines both locally and remotely. Runs pre-push validation, monitors GitHub Actions, analyzes workflow failures, and provides fix suggestions. Use before pushing code or when investigating CI failures. Specializes in pristine CI/CD setups with zero warnings.

Acceptance criteria expert using BDD Given/When/Then format. Covers testable requirements, edge cases, and definition of done. Use for writing AC or acceptance criteria.

Structured logging, error tracking, and request tracing principles for production systems.

This skill provides guidance for setting up Drizzle ORM with Neon serverless PostgreSQL. Use when the user asks about "Drizzle with Neon", "Neon ORM setup", "drizzle-orm neon", "schema definitions", "database migrations with Neon", "drizzle-kit configuration", or needs help with HTTP vs WebSocket adapters for Neon.

This skill covers the Neon Toolkit (@neondatabase/toolkit) for creating ephemeral databases. Use when the user asks about "ephemeral database", "test database", "CI/CD database testing", "Neon branching for tests", "isolated test environment", "Jest with Neon", or needs to create temporary databases for testing.

Develop Flutter fragment shaders (GLSL) end-to-end. Use when creating, debugging, or integrating custom shaders in Flutter apps. Triggers on shader, GLSL, fragment shader, CustomPainter with shader, ShaderMask, visual effects, procedural graphics, or GPU rendering in Flutter.

Research topics using YouTube video and podcast content. Use when user provides YouTube URLs and wants to (1) bring expert opinions into engineering planning discussions, (2) create structured podcast summaries, or (3) extract specific topics from longer podcasts. Handles transcript fetching, cleaning, and analysis.

Use the bird CLI to access X/Twitter accounts, including reading timelines/mentions and listing unanswered mentions by date. Trigger when asked to use bird for whoami, home/mentions, or to detect replies.

Manage academy enrollments by appending rows to a Google Sheet (used by Zapier/n8n to grant LearnWorlds access).

Investigate a topic with Grok 4.1 via OpenRouter and generate a Markdown report with a timeline, verifiable claims, and sources (web/X). Use it when the user says “investiga…”, “haz research…”, “averigua…”, “búscame fuentes…”, “research…”, “look into…”, or when you need fast, source-backed research (news, rumors, product/policy changes, competitive context).

Manage WhatsApp via Evolution API (v2.x): list chats with unread messages and reply.

List, download, and delete Zoom recordings via the API (OAuth). Use when you need to manage recordings at scale.