AI Skills Hub - Browse 180,000+ Agent Skills

Technical architecture for Astro lead generation websites. Use when setting up new projects, configuring build tools, or establishing project foundations. For images use astro-images skill. For SEO use astro-seo skill.

Transactional email templates for lead generation forms. Lead notification + customer confirmation. Resend compatible.

Analyzes YouTube video comments to extract audience insights: - **Top Questions** people are asking (with urgency ratings) - **Top Myths** and misconceptions (with danger ratings) - **Pain Points** and frustrations - **Content Recommendations** (must address, gaps, viral potential) - **Sentiment Analysis** (positive/negative/neutral breakdown) - **Recurring Themes** in discussions

Sequential thinking CLI for multi-step problem solving. Use when breaking down complex problems into steps, planning implementations, debugging multi-layered issues, or when explicit step-by-step reasoning with confidence tracking and assumption management is beneficial.

Use when interpreting Culture Index surveys, CI profiles, behavioral assessments, or personality data. Supports individual interpretation, team composition (gas/brake/glue), burnout detection, profile comparison, hiring profiles, manager coaching, interview transcript analysis for trait prediction, candidate debrief, onboarding planning, and conflict mediation. Handles PDF vision or JSON input.

Guide for using gtr (git-worktree-runner), a CLI tool for managing git worktrees with editor and AI tool integration. Use this skill when the user asks about: (1) creating, managing, or removing git worktrees, (2) setting up gtr / git-gtr for a project, (3) configuring editors (Cursor, VS Code, Zed) or AI tools (Claude Code, Aider, Codex, Gemini) with worktrees, (4) running parallel development workflows across multiple branches, (5) copying config/env files to new worktrees, (6) setting up hooks for worktree creation/removal, (7) troubleshooting git worktree issues, (8) any mention of "gtr", "git gtr", "git worktree runner", or "worktree" in context of parallel dev. Triggers on keywords: gtr, git-gtr, worktree, parallel branches, multi-branch workflow.

Query past conversations from the agent-memory system. Use when asked to "recall what we discussed", "search conversation history", "find previous session", "what did we talk about last week", or "get context from earlier". Provides hierarchical TOC navigation for topic search, recent summaries, and excerpt expansion.

Use when creating releases - analyzes commits, determines version, writes release notes, then runs release script

Develop and maintain the Chris Achinga Hugo site built on PaperMod—use when adding/editing posts, adjusting PaperMod params/menus in hugo.yaml, tweaking styling/partials/assets, enabling features (search, archives, profile/home modes), or debugging Hugo builds.

Split large Python files into multiple files organized as a package. Use when user says "split this file", "this file is too big", "break this into multiple files", or similar requests for Python (.py) files.

Obsidian vault validation and auto-fix tool using settings.yaml as single source of truth. Detects missing frontmatter, validates required properties, and auto-fixes common issues. Use when the user wants to (1) validate vault frontmatter against standards, (2) check for missing required properties, (3) fix common issues like unquoted wikilinks or wrong date formats, (4) audit vault compliance with type-specific rules, (5) run maintenance checks on their Obsidian vault, or (6) log validation results for audit trails. Triggers on keywords like validate vault, check frontmatter, fix vault issues, vault audit, maintenance check, note-type validation, audit log.

Research pipeline for topology-aware GNN representation learning on power grids using the PowerGraph benchmark. Use when (1) building physics-guided GNNs for power flow (PF), optimal power flow (OPF), or cascading failure prediction, (2) implementing self-supervised pretraining for power systems, (3) evaluating cascade explanation fidelity against ground-truth masks, or (4) conducting reproducible ML-for-power-systems research. Triggers include "PowerGraph", "power flow GNN", "OPF surrogate", "cascade prediction", "physics-guided GNN", "grid analytics ML", "power system representation learning".

Meta-capability toolkit for programmatic agent/command creation with validation, versioning, registry management, and Skill Seekers integration. Features interactive wizard, LLM-assisted validation, and auto-discovery hooks.

Fetch boatrace data from Boatrace Open API. Retrieve program schedules, race results, and preview information by specifying year and date. Use when you need to access boatrace race information, programs (出走表), results, or preview data (直前情報) for a specific date.

使用 Playwright 與本地網頁應用程式互動和測試的工具包。支援驗證前端功能、除錯 UI 行為、擷取瀏覽器截圖和查看瀏覽器日誌。

Predict tabular business data using SAP RPT-1-OSS model. Use for customer churn prediction, payment default detection, delivery delay forecasting, and other tabular prediction tasks on SAP business data.

Build mithril-checkpoint compression for PyTorch models. Use when implementing byte grouping, compression pipeline, or checkpoint I/O.

Create new Claude Code skills with proper structure and conventions. Use when the user wants to create a new skill, scaffold skill templates, or understand skill anatomy.

Run security scans locally (Semgrep, Trivy, Gitleaks) to detect vulnerabilities, secrets, and code issues before pushing. Use when the user wants to check for security issues, scan dependencies, or validate code security.

Deploy IndicConformer Speech-to-Text model on Modal with GPU. Use when deploying Indian language ASR (22 languages) as a web API on serverless GPU infrastructure.

Deploy IndicTrans2 translation model on Modal with GPU. Use when deploying Indian language to English translation (22 languages) as a web API on serverless GPU infrastructure.

Syncs Granola meeting notes to Obsidian vault. Reads from Granola's local cache to extract meeting metadata and notes, then creates properly formatted markdown files with frontmatter. Also handles manual transcript formatting when cache doesn't have content.

Create and query Databricks Genie Spaces for natural language SQL exploration. Use when building Genie Spaces or asking questions via the Genie Conversation API.

Standard patterns for creating Databricks Metric Views with semantic metadata for Genie and AI/BI. Use when creating metric views, troubleshooting metric view creation errors, validating schema references before deployment, implementing joins (including snowflake schema patterns), or optimizing metric views for Genie natural language queries.

Create new Azure Database for PostgreSQL Flexible Server instances and configure passwordless authentication with Microsoft Entra ID. Set up developer access, managed identities for apps, group-based permissions, and migrate from password-based to Entra ID authentication. Trigger phrases include "passwordless for postgres", "entra id postgres", "azure ad postgres authentication", "postgres managed identity", "migrate postgres to passwordless".

Guidelines for writing Agent Skills. TRIGGERS: create a skill, new skill, write a skill, skill template, skill structure, review skill, skill PR, skill compliance, agentskills spec, SKILL.md format, skill frontmatter, skill best practices

Extract transcripts from YouTube videos. Use when user says "get transcript", "transcribe this video", "what does this YouTube video say", "extract captions", "youtube transcript", or provides a YouTube URL and wants the text content.

Control Chrome browser via CLI - navigate, click, type, screenshot, read pages. Use when user says "open browser", "click on", "fill form", "take screenshot", "navigate to", "automate browser", or needs any browser automation task.

Fetch web pages, PDFs, and documents with automatic fallbacks and content extraction. Use when user says "fetch this URL", "download this page", "crawl this website", "extract content from", "get the PDF", or provides URLs needing retrieval.

Find and remove dead code in TypeScript/JavaScript projects. Detects unused exports (functions, types, constants never imported elsewhere), unused npm dependencies (packages in package.json never imported), and unreachable code patterns (code after returns, always-false conditions, stale TODOs). Use when: "find dead code", "check for unused exports", "clean up unused code", "find unused dependencies", "audit codebase for dead code", "what code can I delete", or before major refactors.

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.

Generate AI videos using varg SDK React engine. Use when creating videos, animations, talking characters, slideshows, or social media content. Always run onboarding first to check API keys.

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.

Build self-hosted speech-to-text APIs using Hugging Face models (Whisper, Wav2Vec2) and create LiveKit voice agent plugins. Use when building STT infrastructure, creating custom LiveKit plugins, deploying self-hosted transcription services, or integrating Whisper/HF models with LiveKit agents. Includes FastAPI server templates, LiveKit plugin implementation, model selection guides, and production deployment patterns.

Creates production-ready MCP servers using FastMCP v2. Use when building MCP servers, optimizing tool descriptions for context efficiency, implementing progressive disclosure for multiple capabilities, or packaging servers for distribution.

Publish documentation, evidence, artifacts, and assets to the Mentu publication layer. Use when creating docs with Mermaid diagrams, publishing evidence, deploying architecture documentation, or serving content locally. Supports markdown with syntax highlighting, tables, and flowcharts.

Advanced codebase exploration and manipulation toolkit for searching code, navigating project structure, and making precise file edits.

Flight booking assistant that helps users search for flights, compare options, and complete bookings. Guides users through the standard operating procedure for booking flights.

Launch and coordinate Factory Droid operations with full lifecycle management.

Build Claude skills from extracted documentation. Use after doc-scraper/pdf-extractor to generate uploadable skill packages. Use when relevant to the task.

Master LLM-as-a-Judge evaluation techniques including direct scoring, pairwise comparison, rubric generation, and bias mitigation. Use when building evaluation systems, comparing model outputs, or establishing quality standards for AI-generated content.

Create professional financial charts and visualizations using Python/Plotly. Use when building Sankey diagrams (income statement flows, revenue breakdowns), waterfall charts (profit walkdowns, revenue bridges), bar charts (margin comparisons, segment breakdowns), or line charts (trend analysis, multi-company comparisons). Triggers on chart creation requests, financial visualization needs, or data presentation tasks.

Industrial-strength NLP with spaCy 3.x for text processing and custom classifier training. Use when "installing spaCy", "selecting model for nlp" (en_core_web_sm/md/lg/trf), "tokenization", "POS tagging", "named entity recognition" (NER), "dependency parsing", "training TextCategorizer models", "troubleshooting spaCy errors" (E050/E941 model errors, E927 version mismatch, memory issues), "batch processing with nlp.pipe", or "deploying nlp models to production". Includes data preparation scripts, config templates, and FastAPI serving examples.

Enforces project server actions coding conventions when creating or modifying server actions using next-safe-action, and ensures consistent client-side consumption patterns using the project's useServerAction hook. This skill covers both server-side action implementation and frontend integration patterns.

Enforces project Resend email conventions when implementing email sending, templates, batch operations, and newsletter broadcasts. This skill ensures consistent patterns for email service methods, error handling, retry logic, and Sentry integration.

Personal time analyzer for Timing.app data. Use when user asks about time tracking, productivity stats, app usage, daily/weekly summaries, rule configuration, unassigned activities, or wants to explore how they spend time.

Earn trust through verification. Invoke at session start to establish verifiable checkpoints (environment, baseline, completion). Trust comes from gates, not claims.

Extract landing page metadata (title tags, meta descriptions, H1 headings, and content) from URLs to prepare data for Google Ads RSA and sitelinks generation. Use when asked to scrape pages, fetch landing page data, extract page metadata, or prepare URLs for ad copy generation.

Verifies Google Sheets Web App URLs are accessible and explores available data tabs. Use when Mike provides a Web App URL and needs to check what tabs/sheets are available, verify data structure, or inspect headers and sample data before building integrations.

Jira 이슈 조회, 생성, 편집, 상태 변경, 댓글 관리 등 Atlassian CLI를 활용한 Jira 작업 수행. 사용자가 Jira, 이슈, 티켓, SF-, PROJ- 같은 이슈 키, JQL, 스프린트, 보드를 언급할 때 사용.

Generate Android adaptive icons from Iconify's 200k+ open source icons

Use when extracting specific HTML elements (h1, h2, links, images, etc.), scraping page content, or inspecting DOM structure. Also preferred for JavaScript-rendered content or when WebFetch returns incomplete results.

Use when needing to extract CSS styles from a DOM element, inspect computed styles, check font-size/color/margin of elements, or analyze visual styling of a web page. Requires a CSS selector to target the element.

Comprehensive Agent Design, Creation and modification using Vercel AI SDK generateObject with Zod schemas. used when claude needs to create, prompt, modify, fix, refactor or improve any agent code, and any time a Zod Schema is modified that is used by an agent. Covers: agent architecture, Zod schema patterns, .describe() usage, prompting for structured output, error handling.

Crawl documentation websites and save as clean Markdown files. Use when users need to download docs for offline use, create local documentation mirrors, or prepare docs for AI/LLM consumption. Supports recursive crawling, language filtering, and LLM-powered index generation.

CLI power tools for AI-assisted development. Use when (1) needing recommendations for CLI tools to install, (2) processing JSON/YAML data with jq/yq, (3) searching code with ripgrep or ast-grep, (4) documenting a CLI tool or multi-tool recipe you've discovered, (5) wanting to learn CLI patterns for data pipelines, or (6) setting up a new project and want CLI recommendations. Supports three modes - init (project scan), document (capture new recipes), and recommend (codebase analysis).

PR quality patterns, description generation, and review preparation. Auto-activate when creating PRs, generating descriptions, or analyzing branch changes for review.

End-to-end workflow for designing, implementing, and standardizing card skills in BreakTCG.

Generate images and media using fal.ai API (Flux, Gemini image, etc.). Use when asked to generate images, run AI image models, create visuals, or anything involving fal.ai. Handles queue-based requests with automatic polling.

Guide for creating Agent SOPs (Standard Operating Procedures). Use this skill when the user wants to create a new SOP workflow for AI agents, write an agent procedure, or needs help with SOP format and best practices. Triggers on requests like "create an SOP", "new agent workflow", "help me write an SOP", "create a procedure for agents", or "SOP template".

Comprehensive toolkit for fetching, searching, analyzing, and monitoring Hacker News content. Use when Claude needs to interact with Hacker News for (1) Fetching top/new/best/ask/show/job stories, (2) Searching for specific topics or keywords, (3) Monitoring specific users or tracking their activity, (4) Analyzing trending topics and patterns, (5) Getting story details, comments, or user profiles, or (6) Any other task involving Hacker News data retrieval or analysis.

顧客ペルソナの設計と分析を行うスキル。ターゲット顧客のペルソナを詳細に作り上げ、そのペルソナに対するボトルネック（購入・利用の障壁）と訴求ポイント（刺さるメッセージ）を特定する。「ペルソナを作りたい」「ターゲット顧客を定義したい」「顧客分析」「訴求ポイントを知りたい」などと言及した時に使用。

Scan .ai/ directories and generate compact workspace overview

Migrate workspace from old dot-ai convention version to current

Validate BACKLOG.md structure and check orphan task slugs

Use this skill to discover all available SynthesisFlow skills and their capabilities. Provides a bootstrap context for AI agents by listing all skills, their descriptions, and script paths from the .claude/skills/ directory.

Use this skill to create or update the root AGENTS.md file to register SynthesisFlow skills for AI agent discovery. Triggers include "register SynthesisFlow", "update AGENTS.md", "setup agent guide", or initializing a new project.

Use this skill at the beginning of any session or when needing to understand available project documentation. Provides just-in-time context by scanning YAML frontmatter from all markdown files in the docs/ directory without loading full content.

Use this skill to validate that Markdown files are in standard locations. Scans for .md files outside of predefined allowed directories and outputs warnings to prevent documentation sprawl. Triggers include "validate docs", "check markdown locations", or as part of quality checks.

Use this skill to start work on an assigned GitHub issue. This is the core implementation loop of the SynthesisFlow methodology. Guides the AI to load full context (specs, plans, retrospective), create a feature branch, and begin implementation. Triggers include "start work on issue", "implement issue

Use this skill to migrate existing (brownfield) projects with established documentation to the SynthesisFlow structure. Intelligently discovers, categorizes, and migrates documentation while preserving content, adding frontmatter, and maintaining git history.

Track progress with timestamps, git status, and todo list updates in current session

Begin documented development session using Claude Code CLI's memory system

Deploy applications and websites to Vercel. Use this skill when the user requests deployment actions such as "Deploy my app", "Deploy this to production", "Create a preview deployment", "Deploy and give me the link", or "Push this live". No authentication required - returns preview URL and claimable deployment link.

Customize or personalize a Claude Code plugin for a specific organization's tools and workflows by replacing placeholders and configuring MCP servers.

Evaluate all workspace-hub skills for structural validity, content quality, cross-reference integrity, and registry consistency. Runs 18 checks across critical, warning, and info severity levels with actionable fix suggestions.

Implement features, write code, and build functionality following best practices and language conventions. Use when the user asks to implement, code, build, create a function, add a feature, or write code.

Run nf-core bioinformatics pipelines (rnaseq, sarek, atacseq) on sequencing data for gene expression, variant calling, and chromatin accessibility analyses.

Upload Markdown and source files to a reMarkable device as PDFs using the remarquee CLI (rmapi-backed). Use when the user asks to upload/send/export docs/examples to reMarkable, bundle multiple files into one PDF with a ToC, choose an /ai/YYYY/MM/DD destination, avoid or force overwrites, or troubleshoot pandoc/xelatex/rmapi auth.

Scaffold or retrofit a go-go-golems Go repository with standard project plumbing: Makefile targets, golangci-lint config, lefthook hooks, GitHub Actions (unit/smoke/lint/security), and GoReleaser release setup (GitHub releases + Homebrew tap). Use when creating a new go-go-golems Go CLI/library repo, renaming an existing module/binary to go-go-golems conventions, or making a repo “release-ready” with CI and GoReleaser.

Use plz-confirm to gate long-running or human-in-the-loop steps in scripts and coding workflows (confirm, select, form, table, upload, image), including JSON parsing patterns and failure-proof runbook sequencing.

Run code quality checks including PHPCS, PHPStan, and PHPUnit tests. Use before committing, pushing, or when CI fails. Includes auto-fix commands and troubleshooting.

Create new releases for the WordPress plugin. Use when creating tags, bumping versions, or preparing releases. Includes version script usage, immutable tag rules, and CHANGELOG updates.

Effect-TS best practices for services, errors, layers, schemas, and testing. Use when writing/reviewing Effect code, implementing services, handling errors, or composing layers.

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.

Guide for implementing Google Gemini API image understanding - analyze images with captioning, classification, visual QA, object detection, segmentation, and multi-image comparison. Use when analyzing images, answering visual questions, detecting objects, or processing documents with vision.

Automated multi-agent orchestrator that spawns CLI subagents in parallel, coordinates via Serena Memory, and monitors progress

Diagnose and fix issues within the MIMIC extension project. Use this skill when the user reports 'stuttering', build failures, or when you need to self-diagnose extension errors.

Expert guide for implementing Zstandard (zstd) compression and decompression. Use when working with zstd library for data compression tasks including simple compression, streaming operations, dictionary-based compression, or when users need help with compression performance optimization, error handling, or choosing the right API for their use case.

Use at start of spec creation to initialize folder structure with dated naming and save raw feature idea - creates planning, implementation, and verification folders ready for subsequent phases

帮助用户创建飞书文档

Generate performance review summaries from git repositories by analyzing commits, code changes, and contribution patterns over a specified time range. Use when the user needs to create work reports, performance reviews, or contribution summaries from git history.

Hera log detail query toolkit for querying log details by spaceId, storeId, tailName and time range. Use this when you need to query Hera log information programmatically.

Gateway API query toolkit for querying and managing API information. Use this when you need to query Gateway API details, list APIs, or search for specific APIs programmatically.

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser l

Deploy applications and websites to Vercel. Use this skill when the user requests deployment actions such as 'Deploy my app', 'Deploy this to production', 'Create a preview deployment', 'Deploy and gi

Use this skill for operational diagnostics: message delivery investigation, webhook delivery debugging, error triage, and WhatsApp health checks.

Expert guide for using n8n-mcp MCP tools effectively. Use when searching for nodes, validating configurations, accessing templates, managing workflows, or using any n8n-mcp tool. Provides tool selecti

Create professional research posters in LaTeX using beamerposter, tikzposter, or baposter. Support for conference presentations, academic posters, and scientific communication. Includes layout design, color schemes, multi-column formats, figure integration, and poster-specific best practices for visual communication.

Create, edit, and analyze Excel spreadsheets with formulas, formatting, data analysis, and visualization. Use when working with .xlsx files for professional documents, financial models, data analysis, or reporting.