AI Skills Hub - Browse 180,000+ Agent Skills

Create and manage Claude Code plugins with proper structure, manifests, and marketplace integration. Use when creating plugins for a marketplace, adding plugin components (commands, agents, hooks), bumping plugin versions, or working with plugin.json/marketplace.json manifests.

Toolkit for generating PowerToys release notes from GitHub milestone PRs or commit ranges. Use when asked to create release notes, summarize milestone PRs, generate changelog, prepare release documentation, request Copilot reviews for PRs, update README for a new release, manage PR milestones, or collect PRs between commits/tags. Supports PR collection by milestone or commit range, milestone assignment, grouping by label, summarization with external contributor attribution, and README version bumping.

此 Skill 用于维护和管理 Discord Claude Bridge 项目，提供系统架构参考、配置管理、故障排查和维护脚本，适用于调试 Bot 问题、修改配置、清理队列等日常维护任务。

Use when the user asks to create, scaffold, or edit Jupyter notebooks (`.ipynb`) for experiments, explorations, or tutorials; prefer the bundled templates and run the helper script `new_notebook.py` to generate a clean starting notebook.

Deploy applications and websites to Vercel. Use when the user requests deployment actions like "deploy my app", "deploy and give me the link", "push this live", or "create a preview deployment".

Guide for using the TxGate secure multi-chain transaction signing CLI. Use when working with txgate commands, transaction signing, key management, policy configuration, or the txgate daemon.

Guides the import of Inn Express distribution data into Supabase. Use when importing monthly sales data, debugging import issues, or managing product mappings.

Convert GSD codebase mapping to AutoBuildr app_spec.txt. This skill should be used when the user has run /gsd:map-codebase and wants to use AutoBuildr on an existing project. Triggers: "convert to autobuildr", "gsd to spec", "create app_spec from codebase", "use autobuildr on existing project", after /gsd:map-codebase completion.

Reproducible Nix-based Python development environment setup with devenv, uv, ruff, and ty.

Formal verification of Rust code using Creusot and the Pearlite specification language. Use when the user wants to (1) add contracts/specifications to Rust functions, (2) prove correctness of Rust code, (3) write loop invariants, (4) use Creusot's Why3-based verification, (5) work with Pearlite syntax (requires, ensures, invariant, logic, predicate), or (6) debug failing Creusot proofs. Triggers include "verify this Rust", "prove", "Creusot", "add contracts", "formal verification", "loop invariant", "precondition", "postcondition", "Pearlite".

Lists all code tasks in the repository with their status, dates, and metadata. Useful for getting an overview of pending work or finding specific tasks.

Screenshot-based regression testing with Playwright. Compares rendered pixels against baseline PNGs. Use when working with stories, *.visual.spec.ts files, or baseline screenshots. Auto-apply when editing files in stories/ or *.visual.spec.ts.

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

Internationalization and localization patterns. Detecting hardcoded strings, managing translations, locale files, RTL support.

This skill should be used when users ask about examples and tutorials in ase; it prioritizes documentation references and then source inspection only for unresolved details.

This skill should be used when users ask about inputs and modeling in ase; it prioritizes documentation references and then source inspection only for unresolved details.

This skill should be used when users ask about calculators in ase; it prioritizes documentation references and then source inspection only for unresolved details.

This skill should be used when users ask about getting started in ase; it prioritizes documentation references and then source inspection only for unresolved details.

This skill should be used when users ask about using Psi4 through ASE (setup, parameters, limitations, threading/scratch behavior, energy/force calculations, reading psi4-calc outputs, or troubleshooting ASE+Psi4 workflows), with answers grounded in ASE documentation, source code, tests, and relevant tutorial patterns.

This skill should be used when users ask about api and scripting in ase; it prioritizes documentation references and then source inspection only for unresolved details.

This skill should be used when users ask about analysis and output in ase; it prioritizes documentation references and then source inspection only for unresolved details.

This skill should be used when users ask about simulation workflows in ase; it prioritizes documentation references and then source inspection only for unresolved details.

This skill should be used when users ask about parallel and hpc in ase; it prioritizes documentation references and then source inspection only for unresolved details.

Posts content and articles to X (Twitter). Supports regular posts with images/videos and X Articles (long-form Markdown). Uses real Chrome with CDP to bypass anti-automation. Use when user asks to "post to X", "tweet", "publish to Twitter", or "share on X".

Fetch any URL and convert to markdown using Chrome CDP. Supports two modes - auto-capture on page load, or wait for user signal (for pages requiring login). Use when user wants to save a webpage as markdown.

Analyzes article structure, identifies positions requiring visual aids, generates illustrations with Type × Style two-dimension approach. Use when user asks to "illustrate article", "add images", "generate images for article", or "为文章配图".

Access Microsoft OneNote notebooks — read, create, and update notes via Microsoft Graph API. Use when the user mentions OneNote, notebooks, notes, Microsoft notes, or wants to read/create/edit OneNote content.

This skill should be used when users ask about getting started in lammps; it prioritizes documentation references and then source inspection only for unresolved details.

This skill should be used when users ask about build and install in lammps; it prioritizes documentation references and then source inspection only for unresolved details.

This skill should be used when users ask about parallel and hpc in lammps; it prioritizes documentation references and then source inspection only for unresolved details.

Schelling point coordination game where players converge on a shared word. Use when someone initiates the "got it" game, when managing active game state in Discord/Telegram channels, or when responding to "got it" messages during gameplay.

This skill should be used when users ask about api and scripting in lammps; it prioritizes documentation references and then source inspection only for unresolved details.

This skill should be used when users ask about inputs and modeling in lammps; it prioritizes documentation references and then source inspection only for unresolved details.

This skill should be used when users ask about analysis and output in lammps; it prioritizes documentation references and then source inspection only for unresolved details.

This skill should be used when users ask about simulation workflows in lammps; it prioritizes documentation references and then source inspection only for unresolved details.

This skill should be used when users ask about troubleshooting in lammps; it prioritizes documentation references and then source inspection only for unresolved details.

No description available

resolution = 20 dpml = 1.0

Find running Jupyter Server kernels and execute custom code via the server API/WebSocket. Use when a user wants to connect to an existing Jupyter kernel, select it with minimal questions, run code, and return results.

Deploy and configure the AKS Model Context Protocol (MCP) server to Azure Kubernetes Service clusters with Workload Identity, connect MCP to VS Code GitHub Copilot and Claude Code for AI-assisted Kubernetes operations, and implement event-driven self-healing automation. Use this skill when deploying AKS-MCP servers, configuring MCP clients, troubleshooting cluster issues with AI assistance, or building automated remediation workflows.

Deploy an AI-powered Kubernetes operations chatbot stack on AKS. This skill sets up LiteLLM (AI gateway), AKS-MCP (kubectl/helm/az tools), MCP Proxy (tool injection), and a simple chat UI. Use this skill when deploying AI Ops infrastructure for cluster triage, debugging, and self-service diagnostics. The stack enables SREs to ask natural language questions about their cluster and get answers based on real kubectl output.

Parses and validates HMETIS hypergraph (.hgr) files. Supports unweighted, edge-weighted, node-weighted, and dually-weighted formats. Use when working with hypergraph partitioning, HMETIS files, or graph partitioning tasks.

YouTube およびその他の yt-dlp 対応サイトから動画、音声、字幕、綺麗な段落形式の文字起こしをダウンロード。「この動画をダウンロードして」「このクリップを保存して」「音声を抽出して」「字幕を取得して」「文字起こしを取得して」などのリクエスト、または yt-dlp/ffmpeg やフォーマット/プレイリストのトラブルシューティング時に使用。

1Password CLI (op) のセットアップと使用。CLI のインストール、デスクトップアプリ連携、サインイン（シングル/マルチアカウント）、シークレットの読み取り/注入/実行に使用。

CLI パラメータと UX 設計：引数、フラグ、サブコマンド、ヘルプテキスト、出力形式、エラーメッセージ、終了コード、プロンプト、設定/環境変数の優先順位、安全/dry-run 動作。CLI 仕様設計（実装前）や既存 CLI のリファクタに使用。

Repair an (often imperfect) Flexible Job Shop Scheduling baseline into a downtime-feasible, precedence-correct schedule while staying within policy budgets and matching the evaluator’s exact metrics and “local minimal right-shift” checks.

Generate a PR description and open a pull request. Use when the user says /openpr, asks to open a PR, create a pull request, or push and open a PR. Triggers: openpr, open pr, pull request, create pr, push and pr.

Migrate codebase from try/catch or Promise-based error handling to better-result. Use when adopting Result types, converting thrown exceptions to typed errors, or refactoring existing error handling to railway-oriented programming.

Read and send email via IMAP/SMTP. Check for new/unread messages, fetch content, search mailboxes, mark as read/unread, and send emails with attachments. Works with any IMAP/SMTP server including Gmail, Outlook, 163.com, vip.163.com, 126.com, vip.126.com, 188.com, and vip.188.com.

Notion API integration with managed OAuth. Query databases, create and update pages, manage blocks. Use when users want to interact with Notion workspaces, databases, or pages. Notion API 集成，支持 OAuth 管理。查询数据库、创建/更新页面、管理 blocks。

Text-to-speech conversion using node-edge-tts npm package for generating audio from text. Supports multiple voices, languages, speed adjustment, pitch control, and subtitle generation. Use when: (1) User requests audio/voice output with the "tts" trigger or keyword. (2) Content needs to be spoken rather than read (multitasking, accessibility, driving, cooking). (3) User wants a specific voice, speed, pitch, or format for TTS output.

从 YouTube 视频链接提取字幕并转换为中文文字稿。支持自动生成字幕和手动字幕。 使用场景：(1) 用户提供 YouTube 链接并要求提取字幕/文字稿，(2) 用户要求将 YouTube 视频内容转为文字， (3) 用户说"帮我把这个 YouTube 视频转成文字"或类似请求。 触发词：YouTube 字幕、视频转文字、提取字幕、YouTube transcript、视频文字稿。

Track parcels via the 17TRACK API with local SQLite database, polling, and optional webhook ingestion.

Diff-aware guardrail checker for Fear-of-Falling (FOF) changes; fails closed on raw data edits, Kxx intro/req_cols mismatches, and output discipline risks.

Modular workflow generator with on-demand context loading. Creates workflows from YAML plans with focused, trigger-specific guidance. Use when user wants to create, build, or generate workflow automation.

Aggregate-only summarizer for K18 QC artifacts; produces summary outputs and appends manifest rows when format is confirmed.

获取基金最新持仓信息，支持查询前1-20条重仓股及其持仓比例，并提供实时股票涨跌数据和基金估值预测。默认查询前20条重仓股，用户可以通过参数指定查询条数（如"前10条"、"top 15"）。仅支持通过基金代码查询，使用天天基金网的公开数据源。适用于用户查询"基金xxxx的最新持仓"、"查看某基金的前N条重仓股"等场景。

Build Python web scrapers with BeautifulSoup and requests. Includes rate limiting, user-agent rotation, retry logic, structured CSV/JSON output, and error handling. Use when creating tools to extract data from websites or building data collection scripts.

Run equipment downtime analysis on Stresscon maintenance data. Calculates Cost of Idleness metrics, generates category breakdowns, monthly trends, and top-offender rankings. Use when analyzing equipment availability, maintenance KPIs, or estimating financial impact of machine downtime.

Generate and debug Microsoft Power Apps formulas (Power Fx) for the Stresscon Operations Suite. Covers delegation warnings, SharePoint connector patterns, gallery filtering, Patch/Collect operations, barcode/QR scanner integration, and tablet-optimized responsive layouts. Use when writing, fixing, or explaining Power Apps formulas, or designing Power Apps screens.

Generate pytest tests matching Stresscon project conventions. Reads existing test files to learn patterns, creates unit and integration tests with typed fixtures, pd.DataFrame construction, direct value assertions, and proper imports from the stresscon package. Use when adding or updating Python tests.

Author deterministic PHOSPHENE domain done-score scripts and evaluators (bash-only), including metric selection, normalization, weighting, gates, and reporting. Use when creating or updating `.github/scripts/*-domain-done-score.sh` or designing new deterministic evaluation rubrics.

Download audio from YouTube and Twitter/X links

Security audit and threat model for OpenClaw gateway hosts. Use to verify OpenClaw configuration, exposure, skills/plugins, filesystem hygiene, and to produce an OK/VULNERABLE report with evidence and fixes.

Generates structured Standard Operating Procedures from process descriptions, verbal walkthroughs, or existing documentation. Produces human-readable and AI-readable SOPs in markdown format. Use when documenting workflows, codifying tribal knowledge, creating onboarding materials, or building process libraries. Supports both organizational SOPs and AI agent SOPs (the Agent SOP format used by AWS Strands and similar systems).

Send and receive Signal messages via signal-cli daemon. Use when sending Signal messages, checking Signal groups, or working with the Signal socket.

Multi-step scheduler for in-depth agent requests. Detects when user needs multiple steps, suggests plan and waits for confirmation, persists state, and runs heartbeat-aware flow. Use when requests have 3+ actions, sequential dependencies, output dependencies, or high scope/risk.

Use when breaking down specifications, when specs/spec.xml exists, or when planning epic and feature structure

Use when implementation is complete on a regular branch (no .arcforge-epic file), all tests pass, and you need to decide how to integrate - guides completion with structured options for merge, PR, keep, or discard

Use when managing worktrees for multi-epic projects, when dag.yaml exists, or when coordinating parallel development

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

Generate a compact single-image “CD card” for IM@S releases by fetching details from a CD event_url (typically Lantis) and composing cover + release date + title + artist line + tracklist with staff + QR code and one-line URL using Pillow. Use when the user asks to turn a CD link into an image, make a shareable CD info picture, include QR code, or wants a compact layout.

A comprehensive toolkit for processing HWP and HWPX files. Use for reading, creating, editing, converting, and analyzing Korean word processor documents. Supports conversion to PDF, Markdown, HTML, and text. Works on Linux and macOS. Ideal for tasks involving HWP/HWPX files where the Hangul office suite is not installed.

argument: $1

Use this skill when the user asks for a Mermaid diagram or when your response includes a Mermaid code block. It validates and automatically fixes Mermaid syntax errors.

Analyzes CircleCI configuration files (config.yml) and provides optimization recommendations based on best practices. Use when (1) User mentions 'optimize config.yml', 'improve CircleCI setup', or 'review CircleCI configuration', (2) User wants to reduce build costs, execution time, or credit consumption, (3) User asks about resource_class settings, caching strategies, parallelization, or Docker Layer Caching, (4) User mentions CircleCI performance issues like 'builds are slow' or 'tests take too long', (5) User requests best practices check or wants to identify anti-patterns. Performs static analysis of resource_class optimization, cache strategy evaluation, parallelization opportunities, Docker Layer Caching configuration, Orbs utilization, workflow structure, and general best practices. DO NOT use for other CI/CD tools (GitHub Actions, Jenkins, GitLab CI), Dockerfile optimization, CircleCI account management, or Orbs development.

Review code for quality and pattern compliance. Validates against checklists. Manages retry loop (max 3 attempts). On rejection, provides structured feedback for re-planning.

Converts EPUB ebooks to Markdown using epub2md CLI. Handles single files or batch wildcards.

Create interactive code walkthroughs in Virgil format. Use when the user asks to "create a walkthrough", "document the code flow", "explain how X works", "create an onboarding guide", "make a code tour", "create a PR walkthrough", or "document this feature".

Standards for mechanical scripts in `tools/`.

Orchestrates the Azure SDK Management Plane Namespace Review process. Use for updating, processing, or checking namespace review status. Invokes GitHub CLI and Microsoft Graph API.

Use the ClawBazaar CLI to register agents, configure API access, mint and list NFTs, browse and buy marketplace listings, and manage editions on the ClawBazaar marketplace. Use when tasks involve ClawBazaar marketplace operations or require running the `clawbazaar` CLI.

Run LiveKit Cloud end-to-end smoke tests (text/audio) against the deployed agent via lk, and debug failures using session reports.

Transform YouTube videos into beautifully formatted ebook articles with transcripts

Generate Agent Skills by writing executable example scenarios first, then deriving implementation and docs from them.

Run a 4D method using tool4d command-line tool. Use this skill when the user wants to execute, test, or run a 4D project method. Automatically finds tool4d.app in standard locations (VS Code extensions, Antigravity). Supports running any project method with --dataless mode for testing without data file.

Vedic astrology (Jyotish) computational tools for birth chart analysis, divisional charts, dasha periods, yogas, doshas, panchang, muhurat selection, and matchmaking. ALWAYS use these tools when asked about horoscope, kundali, astrology, compatibility, muhurat, Hindu calendar, or panchang. Do NOT guess or use training data - these tools perform precise astronomical calculations.

Interact with Moltbook - the social network for AI agents. Discover opportunities, browse feed, create posts, contribute to quadratic funding pools, join pools, comment, vote, and engage with the Moltbook community.

Redis caching strategy para endpoints críticos. Invalidación inteligente y TTL por tipo de dato. FASE 5 COMPLETA con MetricsCollectorService.

Decide where to place TiDB tests and how to write them (basic structure, naming, testdata usage). Use when asked about test locations, writing conventions, shard_count limits, casetest categorization, or when reviewing test changes in code review.

Guide for building applications with the Stellar JS SDK (@stellar/stellar-sdk). Use when working with the Stellar blockchain in JavaScript/TypeScript — including sending payments, creating accounts, issuing assets, managing trustlines, trading on the DEX, querying Horizon, interacting with Stellar RPC, streaming events, building and signing transactions, multisig, claimable balances, sponsored reserves, SEP-10 auth, federation, fee-bump transactions, and interacting with Soroban smart contracts via the JS SDK. Covers all @stellar/stellar-sdk usage patterns (Horizon module, rpc module, contract module, TransactionBuilder, Keypair, Operation, Asset, etc.).

Read .documents/review/AI_REVIEW.md, implement fixes, and log changes into .documents/review/AI_CHANGES.md.

Convert a plan into a concrete specification covering inputs, outputs, errors, data, and boundary cases; write to .documents/plan/SPEC.md.

Identify structural improvement opportunities (not bugs or performance fixes) and log them as a refactor backlog without changing source code.

Perform a security review focusing on auth, secrets, validation, and logging; write findings to .documents/_ops/SECURITY_AUDIT.md without changing code.

Implement tests or a test plan based on .documents/qa/QA_MATRIX.md; log execution results in .documents/qa/TEST_REPORT.md.

Update an existing Confluence page with a 5-phase workflow Supports: content update, section update, status change, move Triggers: "update doc", "edit doc", "update confluence", "move page"

Download videos, audio, and playlists from 1000+ websites using yt-dlp. Use for - downloading videos from YouTube, Vimeo, Twitter, Bilibili, etc. - extracting audio from videos - downloading subtitles or transcripts - downloading entire playlists - saving videos at specific quality/resolution. Supports direct URLs and handles multiple formats, qualities, and metadata extraction.

Remove image backgrounds using CarveKit neural networks. Use for - batch background removal from photos - extracting people/objects from images - creating transparent PNGs - processing product photos - removing backgrounds from portraits with hair. Supports single images or entire folders with high-quality edge detection and hair preservation.

This skill should be used when the user asks to "유튜브 정리", "영상 요약", "transcript 번역", "YouTube digest", "영상 퀴즈", or provides a YouTube URL for analysis. Extracts transcript, generates summary/insights/Korean translation, and tests comprehension with 9 quiz questions across 3 difficulty levels. Optional Deep Research for web-based follow-up.