AI Skills Hub - Browse 180,000+ Agent Skills

Generate a verifiable GitHub Wrapped year-in-review as a single-file HTML (raw gh API JSON saved, Python-built dataset embedded), with a Bilibili-style narrative, smooth transitions, and mobile-friendly paged mode. Requires gh CLI to be authenticated.

Create publication-quality scientific diagrams using AI with smart iterative refinement. Uses AI quality review. Only regenerates if quality is below threshold for your document type. Specialized in neural network architectures, system diagrams, flowcharts, biological pathways, and complex scientific visualizations.

Run knip to find and remove unused files, dependencies, and exports. Use for cleaning up dead code and unused dependencies.

Hot-reloadable Flecs modules as Rust dylibs. Covers module architecture, component vs system modules, and inter-module dependencies.

将素材转换为戏言系列葵井巫女子的说话风格。触发场景：(1) 用户提供素材并要求「用巫女子风格改写」「巫女子会怎么说」；(2) 用户说「戏言风格」「巫女子口吻」；(3) 需要将普通文字转换为荒诞比喻 + 活泼语气的风格。

Generate and validate Python clients from OpenAPI specs. Use for generation, validation, or troubleshooting.

This skill should be used when looking up Kyverno Helm chart versions, release dates, and corresponding app versions from Artifact Hub. Use for version planning, upgrade decisions, and release timeline analysis.

This skill should be used when checking for naming conflicts between local skills (~/.claude/skills) and plugin-provided skills (~/.claude/plugins). Use to identify duplicate or similarly named skills that may cause inconsistent agent behavior.

Analyzes experimental results comparing code-execution vs direct-MCP approaches for any task. Extracts performance metrics, execution logs, and workspace outputs from zip archives to generate detailed comparison reports. Use when you have a results zip file and need to compare code-execution vs direct-MCP performance, cost, and output quality for any task.

Fetches issues from any GitHub repository with recent activity and generates a prioritized report by analyzing issue state, labels, and comment counts to identify high-priority bugs, enhancements, and good first issues for contributors.

Fetch and analyze GitHub issue details including comments, metadata, and discussion context. Use when user mentions issue numbers, URLs, or you need to understand implementation requirements from a GitHub issue.

Use for WordPress Playground workflows: fast disposable WP instances in browser or locally via @wp-playground/cli, auto-mounting plugins/themes, switching WP/PHP versions, blueprints, and debugging with Xdebug.

Use when you need to quickly understand a WordPress repository: detect project type (plugin/theme/block theme/WP core/full site), available tooling (Composer, npm, @wordpress/scripts), test frameworks (PHPUnit, Playwright, wp-env), and version hints.

Use when developing WordPress block themes: theme.json (global settings/styles), templates and template parts, patterns, style variations, and Site Editor troubleshooting (style hierarchy, overrides, caching).

Fetch raw ADF JSON data from a Confluence page URL. Use this skill when you need to see real-world ADF examples, understand how Confluence represents specific elements, debug ADF parsing, or create test samples.

Create a GitHub pull request (PR) with proper formatting and content guidelines. Invoke this skill whenever the user wants to create, open, or submit a PR (or GitLab MR, Gerrit CR).

Use when planning, scaffolding, validating, or packaging Claude skills inside Advanced Memory MCP.

Use when animation runs slow, janky, or causes frame drops

Use when animation is limited by browser support, platform capabilities, or technical requirements

Use when wrong elements get attention, important content is missed, or visual hierarchy is broken by animation

Use when animation causes user confusion, delays task completion, or creates frustration

Use when motion needs to read clearly and powerfully—broad comedy, action highlights, important story beats, or any moment that must unmistakably communicate to the audience.

Start, stop, and manage the Orchestra application and its services.

This skill should be used when working with Python projects that use uv for package and project management. Use this skill for running Python scripts and CLI tools with `uv run`, managing dependencies, creating projects, handling virtual environments, and executing commands within isolated project environments. Essential for projects with pyproject.toml files.

Save current config before making changes

Use when storing decision traces, querying past precedents, or implementing learning loops. Load in COMPLETE state or when needing to learn from history. Covers semantic search with Voyage AI embeddings, ChromaDB for cross-platform vector storage, and pattern extraction from history.

Use when testing web applications, debugging browser console errors, automating form interactions, or verifying UI implementations. Load for localhost testing, authenticated app testing (Gmail, Notion), or recording demo GIFs. Requires Chrome extension 1.0.36+, Claude Code 2.0.73+, paid plan.

Use when managing agent state transitions (START/INIT/IMPLEMENT/TEST/COMPLETE), triggering context compression at 80% capacity, or handling session lifecycle. Load at session start, on state change, or when context exceeds threshold. Core skill for single-orchestrator architecture.

Use when setting up MCP servers for the first time or verifying MCP configuration. Ensures token-efficient and context-graph MCP servers are properly installed and configured with API keys.

Generate comprehensive multi-tenant security and operational reports from LimaCharlie. Provides billing summaries, usage roll-ups, detection trends, sensor health monitoring, and configuration audits across multiple organizations. Supports both per-tenant detailed breakdowns and cross-tenant aggregated roll-ups. Built with strict data accuracy guardrails to prevent fabricated metrics. Supports partial report generation when some organizations fail, with transparent error documentation. Time windows always displayed, detection limits clearly flagged, zero cost calculations.

ZSH completion system patterns and conventions. Use when implementing custom completion handling, writing completion files, or working with zsh autocomplete. Do not use when installing packages from homebrew, since that typically installs completions automatically.

Automate browser actions using Puppeteer with a simple DSL for web testing and automation

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

Generate a plan for how an agent should accomplish a complex coding task. Use when a user asks for a plan, and optionally when they want to save, find, read, update, or delete plan files in $CODEX_HOME/plans (default ~/.codex/plans).

Complete spec workflow - generates Run ID, creates isolated worktree, brainstorms requirements, writes lean spec documents that reference constitutions, validates architecture quality, and reports completion

Comprehensive vitest testing patterns covering test structure, AAA pattern, parameterized tests, assertions, mocking, test doubles, error handling, async testing, and performance optimization. Use when writing, reviewing, or refactoring vitest tests, or when user mentions vitest, testing, TDD, test coverage, mocking, assertions, or test files (*.test.ts, *.spec.ts).

Guide for creating Claude Code commands with skill integration. Use when users want to create a new Claude Code command specification, whether skill-based or standalone. Assists with command definition, skill discovery, argument specification, and command generation.

专注于构建高性能、可扩展且架构清晰的 Flutter 应用。涵盖整洁架构、高级状态管理和深度性能优化。

Maintains and updates existing skills with new patterns, standards, and fixes. Mass rollout of changes across multiple skills.

Troubleshoot ADK errors and issues. Use when encountering API errors, model overloaded errors, state issues, tool failures, authentication problems, or unexpected agent behavior.

Generates images and videos using MuleRouter or MuleRun multimodal APIs. Text-to-Image, Image-to-Image, Text-to-Video, Image-to-Video, video editing (VACE, keyframe interpolation). Use when the user wants to generate, edit, or transform images and videos using AI models like Wan2.6 or Nano Banana.

Build AI agents with SpoonReactMCP. Use when creating custom agents, configuring tool chains, designing system prompts, or implementing concurrent agent patterns.

Diagnose and fix oh-my-droid installation issues

Practical test/CI playbook for Home Assistant custom components (config flow, coordinator, entities, diagnostics)

How this integration talks to Marstek devices via the local Open API over UDP (JSON messages) and how to handle errors safely

React hooks for NEAR Protocol wallet integration using @hot-labs/near-connect. Use when building React/Next.js apps that need NEAR wallet connection, smart contract calls (view and change methods), token transfers, access key management, or NEP-413 message signing. Triggers on queries about NEAR wallet hooks, NearProvider setup, useNearWallet hook, or NEAR dApp React integration.

Use when user asks YouTube video extraction, get, fetch, transcripts, subtitles, or captions. Writes video details and transcription into structured markdown file.

Help users install and configure the mirrord operator for team environments. Use when users ask about operator setup, Helm installation, licensing, or multi-user mirrord deployments.

Guide users from zero to their first working mirrord session. Use when a user is new to mirrord, wants to install it, or needs help running their first session connecting to a Kubernetes cluster.

Diagnose cardano-cli: version, era-prefixed vs legacy syntax, network flags. Produces compatibility report.

Plutus script guidance: datums, redeemers, collateral, reference scripts. Templates only—use operator to execute.

MeshJS patterns: tx building, wallet connectors, script interactions. TypeScript/JavaScript Cardano development.

Hydra troubleshooting: decision tree for common issues. Maps symptoms to fixes with verification steps.

Protocol parameters: fetch pparams, understand fees, min-UTxO, execution budgets. Read-only diagnostics.

Execute Plutus script transactions: script spends, datum/redeemer submission. Manual invoke only.

Core concepts for Fullstory's User Anonymization API. Platform-agnostic guide covering session management, privacy compliance, and best practices for logout handling and user switching. See SKILL-WEB.md and SKILL-MOBILE.md for implementation examples.

Core concepts for Fullstory's Asynchronous API methods. Covers the Async suffix pattern, Promise handling, error handling, and when to use async vs fire-and-forget. Note - this pattern is web-only; mobile platforms use different mechanisms.

// 2. Define expected file paths const files = { odn: `public/${deptName}_odn.csv`, odd: `public/${deptName}_odd.csv`, map: `public/${deptName}_map.json` };

Doodlestein Self-Releaser - Fallback release infrastructure for building and releasing tools locally when GitHub Actions is throttled. Cross-platform builds via SSH, supply chain security (SLSA/SBOM/signing), quality gates, and offline capability.

validate workspace, update workspace map, check workspace.

If the log doesn't exist, inform the user they should run `just maintenance` or `claude --maintenance` first.

share skill, upload skill, publish skill.

continue [build], resume, work on, check progress, execute build, build [ID/name].

airtable, connect airtable, query [base], add to [table].

Search companies in HubSpot CRM by name or domain. Load when user says 'search companies', 'find company', 'lookup company', 'search for [company]'.

List email engagements from HubSpot CRM. Load when user says 'list emails', 'show emails', 'email history', 'hubspot emails'. Returns logged email records.

Create a new contact in HubSpot CRM. Load when user says 'create contact', 'add contact', 'new contact'. Requires email, optional firstname, lastname, phone, company.

hubspot, crm, contacts, companies, deals.

Create a meeting engagement in HubSpot CRM. Load when user says 'create meeting', 'add meeting', 'schedule meeting', 'new meeting'. Requires title, start and end times.

List contacts from HubSpot CRM. Load when user says 'list contacts', 'show contacts', 'get contacts', 'hubspot contacts'. Returns paginated contact list with email, name, phone, company.

Create a new company in HubSpot CRM. Load when user says 'create company', 'add company', 'new company'. Requires name, optional domain, industry, city.

Create a note engagement in HubSpot CRM. Load when user says 'create note', 'add note', 'new note', 'record note'. Requires body content.

List note engagements from HubSpot CRM. Load when user says 'list notes', 'show notes', 'note history', 'hubspot notes'. Returns logged note records.

Create a new deal in HubSpot CRM. Load when user says 'create deal', 'add deal', 'new deal', 'new opportunity'. Requires name, optional amount, stage, closedate.

notebooklm, create notebook, audio overview, podcast.

Reprend le pipeline depuis la dernière phase/task

Phase ACT (planning) - Génère epics/US/tasks

Retrieves a film's box office revenue (and optionally budget) by resolving the correct movie entity and reading the revenue field from movie metadata. Use when asked 'how much did [movie] make at the box office', 'box office gross', 'revenue', or similar performance questions about a specific film title.

Use when need to create specialized subagent for recurring tasks, domain-specific work, or pipeline automation

Use when need to create reusable technique, pattern, or reference guide for AI agents

Retrieve ratings snapshot with overall rating and key metric scores including DCF, ROE, ROA, Debt-to-Equity, P/E, and P/B for public companies. Use when screening stocks, comparing quality metrics, or quick fundamental assessment.

Retrieve year-over-year growth in income statement items including Revenue, Gross Profit, Operating Income, Net Income, and EPS Diluted. Use when analyzing company financial growth trends, comparing fiscal year performance, or identifying profitability inflection points.

Analyze year-over-year growth in income statement items and financial metrics using Octagon MCP. Use when retrieving YoY Revenue Growth, Cost of Revenue Growth, Gross Profit Growth, Operating Income Growth, Net Income Growth, or comparing financial performance across fiscal periods for any public company.

Retrieve real-time or historical cash flow statement data including Net Income, Operating Cash Flow, Investing Cash Flow, Financing Cash Flow, Free Cash Flow, and Cash Position for public companies. Use when analyzing cash generation, capital allocation, or liquidity trends.

Retrieve year-over-year growth in cash flow metrics including Operating Cash Flow, Free Cash Flow, and Net Cash Flow. Use when analyzing company cash generation trends, capital allocation efficiency, or liquidity trajectory.

Retrieve detailed revenue breakdown by geographic segment for public companies. Use when analyzing regional exposure, geographic concentration, international expansion, or currency risk assessment.

Retrieve comprehensive year-over-year growth in key financial metrics including Revenue, Gross Profit, Operating Income, Net Income, EPS, and Free Cash Flow. Use when analyzing overall company financial performance trends across income statement and cash flow.

Retrieve detailed balance sheet statement data including Total Assets, Current Assets, Non-Current Assets, Liabilities, Equity, and Net Debt for public companies. Use when analyzing financial position, capital structure, or leverage metrics.

Retrieve analyst financial estimates including Revenue and EPS projections with low/high ranges and analyst coverage. Use when analyzing forward expectations, consensus estimates, valuation inputs, or comparing projections to historical performance.

Retrieve year-over-year growth in balance sheet items including Total Assets, Total Liabilities, Shareholders Equity, Cash, and Inventories. Use when analyzing company financial position trends, capital structure changes, or liquidity management.

Strict skill for reproducing ML models. Use for: (1) Reproducing paper algorithms, (2) Porting open-source models, (3) Integrating multiple algorithms into one agent, (4) Adapting a model to downstream tasks. Core rule: engineering code may change (adapters, I/O, logging, config), but the algorithm must stay untouched. Keywords: reproduce, reimplement, port, migrate, adapt, integration.

Engineering-grade code development with modular architecture, clear interfaces, and professional project structure. Use this skill when: (1) Starting any new coding project, (2) Building features that may grow in complexity, (3) User requests maintainable/scalable/professional code, (4) Projects expected to span multiple conversation turns, (5) Code that needs to be readable, testable, or reusable. This skill ensures code is modular (small focused files), consistent (predictable patterns), and navigable (clear project structure) - enabling efficient long-context development.

Engineering patterns for ML/DL research and LLM training infrastructure. Use this skill when: (1) Building training pipelines (SFT, RLHF, DPO, etc.), (2) Creating ML experiment infrastructure, (3) Designing distributed training systems, (4) Research projects requiring reproducibility, (5) Any deep learning project beyond simple scripts. Complements engineering-code skill with ML-specific patterns: config-driven architecture, component registry, experiment management, and stable/experimental layer separation.

Q&A platform where AI agents ask and answer questions for each other

Use when starting new Xiaohongshu accounts, struggling with unclear content direction, receiving inconsistent engagement, or needing to define target audience and vertical domain

账号合并 - 多账号整合策略，集中资源打造主账号

This skill applies Edward Tufte's data visualization principles from "The Visual Display of Quantitative Information" to create high-impact slides. Use when designing presentations, creating charts/graphs, reviewing slides for clarity, or transforming data into visual displays. Triggers on phrases like "make a slide", "create presentation", "design chart", "visualize data", "review my slides", or "make this more impactful".

Compare options using gestalt impression + structured evaluation. Impression first, then criteria, then check for divergence.

Three core metacognitive questions. What am I trying to achieve? Is this the best way? Am I making progress?

Produce diverse candidate solutions. Given constraints and purpose, generate N candidates ranging from conventional to extreme. The creative primitive that other skills call.