AI Skills Hub - Browse 180,000+ Agent Skills

GitHub MCP 伺服器管理技能。用於設定 GitHub MCP、管理 repositories、issues、pull requests、搜尋程式碼等 GitHub 操作。

Run Rust tests, analyze failures, and fix issues. Use after making code changes.

This skill should be used when the GM needs to roll dice or when the user asks to "roll dice", "make a dice roll", "roll for initiative", "roll a skill check", "roll damage", or needs to resolve RPG mechanics with random dice outcomes. Provides deterministic dice rolling for tabletop RPG adventures.

This skill should be used when the GM needs to look up rules, reference what the SRD says, find official rules, get exact wording, check RAW (rules as written), verify rules references, or understand how mechanics work in d20 5E. Provides authoritative rule clarification from the System Reference Document 5.2.

This skill should be used when the GM needs to handle Daggerheart combat, including action roll resolution, Hope/Fear token economy, spotlight flow, damage tracking, reaction rolls, and managing combat encounters. Provides action outcome tables, encounter tracking templates, and condition references.

This skill should be used when the GM needs to look up Daggerheart rules, reference what the SRD says, find official rules, get exact wording, check RAW (rules as written), verify rules references, or understand how mechanics work in Daggerheart. Provides authoritative rule clarification from the Daggerheart System Reference Document 1.0.

This skill should be used when handling domain cards and magical abilities in Daggerheart, including looking up domain card effects, understanding Recall costs, making Spellcast Rolls, selecting domain cards during character creation or advancement, or when players want to use domain-based abilities. Covers all 9 SRD domains (Arcana, Blade, Bone, Codex, Grace, Midnight, Sage, Splendor, Valor) and their associated cards.

Guide for using pagent - a PRD-to-code orchestration tool. Use when users ask how to use pagent, run agents, create PRDs, or transform requirements into code.

Configuration loader and manager for Obsidian vault settings. Use when the user wants to (1) load vault configuration, (2) customize note type definitions, (3) manage frontmatter defaults, (4) merge configuration files, (5) validate configuration structure, or (6) save custom vault settings. Triggers on keywords like load config, vault settings, note type config, frontmatter defaults, merge configs, validate configuration.

Assign Dewey Decimal categories to books and determine correct shelf location in __BOOKS_DIR__/. Handles directory leafing rules for when to create subcategories. Use when cataloging books or reorganizing library structure.

Extract author, title, year, and contributor metadata from ebook files (EPUB, PDF). Use when you need to identify a book's bibliographic information from its embedded metadata or filename.

Release a merged PR by tagging and creating a GitHub release. Use when asked to "release", "tag", or "create a release".

フロントエンド（TypeScript/Svelte 5/Vitest）のテスト実装とデバッグを行います。テストの作成、テストの実行、テストエラーの修正、Svelte 5 コンポーネントのテスト、国際化対応のモックなどのテスト関連タスクに使用します。

Search the web using NinjaExa (Exa AI) for real-time information, current events, and technical documentation. Use this skill when you need up-to-date information beyond your knowledge cutoff, researching libraries/frameworks/APIs, finding recent news, or getting code examples. Triggers on queries about recent events, library docs, API references, or when user explicitly asks to search the web.

This skill should be used when the user asks to "create a Jira issue", "search Jira", "get issue details", "manage sprints", "list boards", "transition issue status", "add Jira comment", "convert to subtasks", or performs any Jira Cloud operations. Provides comprehensive Jira API integration with issue tracking, sprint management, Agile/Scrum workflows, and bulk operations.

Emergency recovery patterns for when vibecoding goes wrong. Use when user mentions things like "everything broke", "nothing works", "it was working before", "I messed something up", "how do I undo", "project won't start", "dependencies broken", "git is messed up", errors after updates, blank screens, infinite loops, or any situation where a project that was working is now broken.

PowerShell build automation tool for creating task-based build scripts. Use when Claude needs to create, modify, or troubleshoot psake build scripts (psakefile.ps1), automate builds for .NET/Node.js/Docker projects, set up CI/CD pipelines with psake (GitHub Actions, Azure Pipelines, GitLab CI), or work with PowerShell-based build automation. Triggers include mentions of psake, psakefile, PowerShell build scripts, Invoke-psake, or build task dependencies.

Provides team GitHub activity insights including merged PRs, contributor leaderboards, merge velocity, review participation, and PR size analysis. Use when users ask about team productivity, who merged PRs, code contribution stats, review patterns, or developer activity.

Analyze WordPress theme PHP files to extract testable elements for E2E test generation.

Audit and optimize existing skills for token efficiency and progressive disclosure compliance. Use when analyzing skill token footprint, reformatting verbose skills into hierarchical structures, or ensuring skills follow the 3-level disclosure model.

pnpm+turbo 모노레포에서 Node 버전(.nvmrc)과 터보 task 의존성을 고려해 lint/typecheck/build를 안전하게 실행하고, 실패 시 패키지 단위로 범위를 좁혀 원인을 찾습니다.

packages/ui의 shadcn/ui + Tailwind v4 컴포넌트를 추가/수정할 때 기존 컴포넌트 재사용, cn()/cva 패턴, exports 영향, lint/typecheck 절차를 따릅니다.

CI/CD integration and automation frameworks for continuous AI security testing

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.

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup

Use when you've developed a broadly useful skill and want to contribute it upstream via pull request - guides process of branching, committing, pushing, and creating PR to contribute skills back to upstream repository

Use when tests have race conditions, timing dependencies, or inconsistent pass/fail behavior - replaces arbitrary timeouts with condition polling to wait for actual state changes, eliminating flaky tests from timing guesses

Navigate and query Memory Bank files using MBEL 6.0 syntax. Use when user asks about features, files, dependencies, entry points, hotspots, anchors, or wants to understand codebase structure from Memory Bank. Also use when user mentions "MB", "Memory Bank", "MBEL", or asks "where is X implemented".

Analyzes iron butterfly credit spreads with ATM short straddle and OTM long strangle protection. Requires numpy>=1.24.0, pandas>=2.0.0, matplotlib>=3.7.0, scipy>=1.10.0. Use when expecting stock to pin at specific strike, want maximum credit collection in high IV, analyzing tight-range opportunities, or implementing high-premium neutral strategies on stocks with strong technical pivot levels.

簡報創建、編輯和分析。當 Claude 需要處理簡報（.pptx 檔案）時使用：(1) 創建新簡報、(2) 修改或編輯內容、(3) 處理版面、(4) 添加註解或講者備註，或任何其他簡報任務

全面的文件創建、編輯和分析，支援追蹤修訂、註解、格式保留和文字擷取。當 Claude 需要處理專業文件（.docx 檔案）時使用：(1) 創建新文件、(2) 修改或編輯內容、(3) 處理追蹤修訂、(4) 添加註解，或任何其他文件任務

Execute SQL queries and explore PostgreSQL database structures. Use when Claude needs to connect to PostgreSQL databases, list tables, or run read-only queries. Supports parameterized queries to prevent SQL injection and environment variable configuration.

Comprehensive Cloudflare account management for deploying Workers, KV Storage, R2, Pages, DNS, and Routes. Use when deploying cloudflare services, managing worker containers, configuring KV/R2 storage, or setting up DNS/routing. Requires CLOUDFLARE_API_KEY in .env and Bun runtime with dependencies installed.

Master Vue Testing - Vitest, Vue Test Utils, Component Testing, E2E with Playwright

Master Vue Router - Navigation, Guards, Lazy Loading, Meta Fields, History Modes

This skill should be used when the user asks to "convert CLAUDE.md", "create AGENTS.md", "sync instruction files", "generate copilot instructions", "create GEMINI.md", "split instructions into platforms", or needs guidance on AI coding assistant instruction file formats (AGENTS.md, CLAUDE.md, copilot-instructions.md, GEMINI.md).

Enforce architectural boundaries and coding standards via static analysis. Validates layer dependencies, module boundaries, naming conventions, and structural rules. Use when checking architecture compliance, during code review, or when asked about architecture violations.

Unified linting scripts for all services in the monorepo. Use when the user wants to lint code, check formatting, or run type checks.

Build mithril-dedup for ML dataset deduplication. Use when implementing MinHash, LSH, clustering, or document I/O.

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

This skill should be used when analyzing errors, stack traces, and logs to identify root causes and implement fixes.

Discover and consolidate Claude Code and Cursor AI history/session data from local and remote machines. Use when the user wants to find, backup, or aggregate their AI coding assistant histories, extract conversation data from multiple development machines, or create a unified view of Claude Code sessions and Cursor chats across hosts.

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

Loads Conductor project context automatically. Use when user asks about the project, starts tracks, implements features, or needs project info. Auto-loads conductor/ files as needed.

Before building on assumptions, validates them first. Activates when making claims about how code works, what exists, or why something happens. Prevents assumption cascades where one wrong guess leads to a completely wrong solution.

When a user uploads or references a data file (CSV, JSON, XLSX, TXT, LOG) or any file larger than 100KB, immediately estimate token cost using scripts/estimate_size.py. If >30k tokens, chunk the file and summarize each chunk. If smaller, run quick inspection. Return a safe preview and summary without asking the user what to do.

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

Cryptographically verified dice rolling for play-by-post TTRPGs on Moltbook.

Identify and resolve duplicate skills across the neoskills bank and agent targets (Claude Code, OpenCode). Use when the user mentions duplicate skills, wants to deduplicate their skill bank, asks about redundant or overlapping skills, wants to clean up skills, or needs to audit skill inventory for duplicates. Also use when importing skills that may already exist in the bank.

Transform exploration findings, bugs, or feature requests into well-structured Linear issues.

Deploy and query Databricks Model Serving endpoints. Use when (1) deploying MLflow models or AI agents to endpoints, (2) creating ChatAgent/ResponsesAgent agents, (3) integrating UC Functions or Vector Search tools, (4) querying deployed endpoints, (5) checking endpoint status. Covers classical ML models, custom pyfunc, and GenAI agents.

MLflow 3 GenAI evaluation for agent development. Use when (1) writing mlflow.genai.evaluate() code, (2) creating @scorer functions, (3) building evaluation datasets from traces, (4) using built-in scorers (Guidelines, Correctness, Safety, RetrievalGroundedness), (5) analyzing traces for latency/errors/architecture, (6) optimizing agent context/prompts/token usage, (7) debugging evaluation failures. Covers the full eval workflow: trace analysis -> dataset building -> scorer creation -> evaluation execution.

Standard patterns for Databricks Asset Bundles configuration files for serverless jobs, DLT pipelines, dashboards, alerts, apps, and workflows. Use when creating, configuring, or deploying DABs for infrastructure-as-code deployments. Covers mandatory serverless environment configuration, hierarchical job architecture (atomic/composite/orchestrator), DLT pipeline patterns, dashboard resources with dataset_catalog/dataset_schema, SQL Alerts v2 API schema, Apps lifecycle, Python notebook parameter passing (dbutils.widgets.get vs argparse), deployment error prevention, and pre-deployment validation.

End-to-end Bronze layer creation for testing and demos. Creates table DDLs, generates fake data with Faker, copies from existing sources, and configures Asset Bundle jobs. Covers Unity Catalog compliance, Change Data Feed, automatic liquid clustering, and governance metadata. Use when setting up Bronze layer tables, creating test/demo data, rapid prototyping Medallion Architecture, or bootstrapping a new Databricks project. For Faker-specific patterns (corruption rates, function signatures, provider examples), load the faker-data-generation skill.

Generate synthetic data with Faker for Bronze layer testing with configurable data corruption. Use when creating test data for data quality validation, testing DLT expectations, or simulating production-like datasets. Supports realistic data generation with intentional corruption patterns mapped to specific DQ expectations.

Databricks DQX framework patterns for advanced data quality validation with detailed failure insights and flexible quarantine strategies. Use when implementing Silver/Gold layer validation, needing richer diagnostics than DLT expectations, or requiring pre-merge validation with detailed failure tracking. Supports YAML configuration, Delta table storage, and serverless compute compatibility.

Create dual-format ad-hoc exploration notebooks for Databricks workspace (.py) and local Jupyter (.ipynb) with Databricks Connect. Use when building data exploration tools, debugging data quality issues, or creating interactive analysis notebooks. Supports widget fallback patterns, helper functions for table discovery, and proper Spark session initialization for both environments.

Patterns for setting up Databricks Genie Spaces with comprehensive agent instructions, data assets, and benchmark questions. Use when creating Genie Spaces, configuring agent behavior, selecting data assets, or validating benchmark questions. Includes mandatory 7-section deliverable structure, General Instructions (≤20 lines), data asset organization (Metric Views → TVFs → Tables), benchmark questions with exact SQL, Serverless warehouse mandate, table/column comment requirements for Genie SQL quality, pre-creation table inspection, Conversation API programmatic validation, follow-up vs new conversation patterns, and deployment checklists.

End-to-end guide for planning, creating, deploying, and validating Table-Valued Functions (TVFs) in Databricks optimized for Genie Space natural language queries. Use when creating TVFs for Genie Spaces, planning TVF requirements from business questions, troubleshooting TVF compilation errors, or ensuring Genie compatibility. Includes requirements gathering templates, schema validation patterns, SQL requirements (STRING parameters, parameter ordering, LIMIT workarounds), v3.0 bullet-point comment format, null safety, SCD2 handling, cartesian product prevention, 5 complete domain-adaptable examples, Asset Bundle deployment patterns, and post-deployment validation queries.

Comprehensive guide for Databricks Lakehouse Monitoring with quick-start workflow (2 hours), fill-in-the-blank requirements template, concrete fact/dimension monitor examples, and complete deployment patterns. Use when setting up Lakehouse Monitoring for Gold layer tables, creating custom business metrics, designing monitoring strategy, querying monitoring tables for dashboards, or troubleshooting monitor initialization failures. Includes setup patterns with graceful degradation, custom metric syntax (AGGREGATE, DERIVED, DRIFT), table-level business KPIs with input_columns=[":table"], query patterns for dashboards, async operations handling, monitor cleanup, Genie documentation integration, and production deployment workflow.

Production-grade patterns for Databricks AI/BI (Lakeview) dashboards. Prevents visualization errors, deployment failures, and maintenance issues through widget-query alignment, number formatting, parameter configuration, monitoring table patterns, chart scale properties, and automated deployment workflows. Includes complete JSON templates, validation scripts, and step-by-step implementation guide.

Converts Cursor rules (.mdc files) into properly structured Agent Skills following the AgentSkills.io specification. Handles frontmatter conversion, content restructuring, and generates complete skill directory structures with references and scripts when appropriate. Use when transforming cursor rules into skills, migrating .cursor/rules to skills format, or creating a SKILL.md from existing rule files. Triggers on "convert rule", "mdc to skill", "cursor rule to skill", "transform rule", "migrate rules", "create skill from rule", "agent skill from cursor rule".

Run criterion benchmarks and compare against performance budgets. Use to validate spike criteria or after performance-sensitive changes.

华安保险车险周报自动生成器（麦肯锡风格）。将周度车险数据（支持Excel/CSV/JSON/DuckDB）转化为12-13页董事会级经营分析报告。采用问题导向标题、16:9宽屏、四象限/气泡图可视化、深红#a02724配色。报告结构：经营概览、保费进度、变动成本、损失暴露、费用支出，每个章节分机构和分客户类别双维度分析。支持自定义阈值配置和保费计划。触发场景：用户上传车险周报数据文件（.xlsx/.csv/.json/.db），要求生成董事会汇报PPT。

AI-powered code review using CodeRabbit. Default code-review skill. Trigger for any explicit review request AND autonomously when the agent thinks a review is needed (code/PR/quality/security).

Control smart home devices via USB camera + Nature Remo on WSL2. Capture room photos with ffmpeg, analyze with vision, operate lights/AC/TV via Nature Remo Cloud API. Use when asked to check the room, turn lights on/off, adjust AC temperature, or manage home appliances. Also handles the capture→analyze→operate→verify loop.

Checks TypeScript syntax errors, linting issues, and type problems across files or directories. Use when you need to identify code quality issues, verify compilation, or catch errors before committing.

Generate test PDF fixtures with known, extractable content. Creates PDFs with sections, tables, figures, requirements, equations, and annotations. Use when user needs "create test PDF", "generate PDF fixture", "make sample PDF for testing".

Sync .agents/skills with the canonical agent-skills repo. Use when asked to "sync skills", "publish skills", or "pull skills" between projects.

Free web and local search via Brave Search API. Use when user says "brave search", "search with brave", "brave web search", "brave local search", "local search", "find businesses near", or "near me".

Connect to a self-hosted Plane.so instance via API. Use this skill when the user wants to interact with Plane for project management tasks including managing workspaces, projects, work items (issues), cycles, modules, states, and labels.

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

Create Remotion videos using the Geist design system aesthetic. Use when asked to create videos, animations, or motion graphics that should follow Vercel's visual style - dark theme, spring animations, Geist typography, and the Geist color palette.

Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude 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

Run Qodana code inspection and get parsed results. Use when you need to analyze code quality, find unused code, detect potential bugs, or check for JetBrains IDE inspections. Supports all major programming languages (Java, Kotlin, Python, JavaScript, TypeScript, C#, C++, Go, Ruby, PHP). Returns structured list of problems grouped by file with severity, location, and code snippets.

Guide for building production-ready LiveKit voice AI agents with multi-agent workflows and intelligent handoffs. Use when creating real-time voice agents that need to transfer control between specialized agents, implement supervisor escalation, or build complex conversational systems.

Guide for creating effective prompts and instructions for LiveKit voice agents. Use when building conversational AI agents with the LiveKit Agents framework, including (1) Creating new voice agent prompts from scratch, (2) Improving existing agent instructions, (3) Optimizing prompts for text-to-speech output, (4) Integrating tool/function calling capabilities, (5) Building multi-agent systems with handoffs, (6) Ensuring voice-friendly formatting and brevity for natural conversations, (7) Iteratively improving prompts based on testing and feedback, (8) Building industry-specific agents (debt collection, healthcare, banking, customer service, front desk).

Enhanced architecture guidance for voice-first Brazilian fintech applications. Use when designing voice interfaces, implementing PIX/Boletos, optimizing financial systems, or making technology stack decisions for Brazilian market applications. Integrates with docs/ content, MCP tools for Brazilian market research, enhanced validation scripts, and comprehensive Brazilian compliance patterns.

Generate or edit images using Google Gemini API via nanobanana. Use when the user asks to create, generate, edit images with nanobanana, or mentions image generation/editing tasks.

Create PRD, HANDOFF, PROMPT, RESULT, CONTEXT, INTENT, and AUDIT documents using canonical templates with Mentu evidence capture. Use when writing documentation for agents, creating task specifications, documenting completed work, recording design decisions, or processing Architect intents.

Auto-updates documentation (README, implementation plans) based on recent code changes.

Standard error response taxonomy and envelope for services, including error codes, categories, retryability, correlation IDs, safe messaging, and validation error details

Strategies for managing data structures, versioning, and evolutions across databases and event streams.

Standardized local development environment setup ensuring consistency across team members and reducing "works on my machine" issues.

Manage Trello boards, lists, and cards using the `trello-cli` command.

Use when fixing bugs, errors, or user mentions "debug", "erro", "não funciona", "bug", "quebrou", "failing". Four-phase root cause analysis.

Smart routing wizard for creating skills, agents, commands with complexity-based skill loading

Design patterns for automatic skill activation at plugin or project level. Use when implementing keyword-based skill suggestions.

Patterns for configuring agent tools correctly

Language, style, and comment quality guidelines for plugin content

MCP Gateway design patterns for Agent Gateway, Subprocess, and Daemon isolation. Use when designing MCP integrations.

Best practices for skill structure and types. Use when creating skills.

Progressive MCP integration for Claude Code. Discover tools incrementally, hydrate schemas on demand, and run procedural workflows that call MCP tools outside the LLM loop.

Dreemz GA4 analytics via Dream Tools (GA4 API + BigQuery). Use this skill when: (1) Analyzing user behavior with GA4 events/screens (2) Building funnels or user journeys (3) Using topScreens, topEvents, userJourney, funnel, etc. (4) Tracking screen flows or event patterns Triggers: "GA4", "BigQuery", "funnel", "user journey", "screen flow", "events", "analytics", "topScreens", "topEvents"

Manage tasks in Todoist - create, update, search, and organize tasks and projects. Use when the user wants to manage their Todoist tasks, add todos, check their task list, update task status, or work with Todoist projects. Requires TODOIST_API_TOKEN environment variable.

How to use the FlowStorm debugger to analyze Clojure/ClojureScript program executions. This skill teaches timeline exploration, value inspection, and debugging patterns using FlowStorm's recording API for runtime analysis.

Merge multiple documentation sources (docs, GitHub, PDF) with conflict detection. Use when combining docs + code for complete skill coverage.

Buy domains on Namecheap and set up Cloudflare DNS programmatically.