AI Skills Hub - Browse 180,000+ Agent Skills

Create, search, and list notes in a self-hosted (or hosted) Rote instance via its OpenKey (API Key) HTTP API. Use when the user wants you to save chat content as notes, default to a Rote “inbox”, tag notes, or retrieve notes by keyword/tag.

A user may ask you to create, edit, or analyze the contents of a .docx file. A .docx file is essentially a ZIP archive containing XML files and other resources that you can read or edit. You have different tools and workflows available for different tasks.

Show overview of project's Blueprint structure including specs, ADRs, and patterns. Use when the user asks about documented decisions, project status, or wants to see what's been captured.

List all Architecture Decision Records with their status and summaries. Use when the user wants to see all decisions, review ADR history, or find a specific decision.

Validate and fix markdown formatting in files and folders. Use when the user wants to check formatting, validate markdown, fix lint errors, revisar formato, validar notas, comprobar markdown, arreglar markdown, limpiar markdown, or clean up files.

Remove the NotebookLM watermark from PDFs (presentations) and images (infographics) automatically. Use when the user wants to remove the NotebookLM watermark, eliminar el watermark, quitar la marca de agua.

Prisma-to-Zod schema generator with composable Query Engine. Use when user mentions zodipus, prisma zod schemas, prisma validation, zod from prisma, query builders with zod, runtime database validation, or type-safe prisma queries.

Use when building internationalization features, managing translation keys, setting up localization workflows, integrating AI translation, connecting GitHub repositories, delivering translations via CDN, using MCP tools for translation management, or implementing i18n SDKs in React/Next.js applications.

[Internal] Add a task to the jaan.to development roadmap. For jaan.to project maintenance, not end-user use. Maps to: to-jaan-roadmap-add

Generate changelogs from git commit history.

Write clear, useful API documentation.

Triple-checks proposals and claims before execution. Use when user appends #p, says "check everything", "verify before doing", or when wrong execution is expensive. Three passes: facts, completeness, consequences. For post-hoc evidence proving, use mode-verify instead.

Matrix chat communication. AUTOMATICALLY TRIGGER when user mentions Matrix rooms (#room:server), asks to send messages to chat, or wants to interact with Matrix. Use for sending messages to Matrix rooms on behalf of users via access token authentication.

Shotgun codebase exploration with iterative passes - generates many commands, executes in parallel, extracts relevant context. Use before writing code to understand existing patterns, before generating tests, or when exploring unfamiliar codebases.

デザイントークンの設計・利用・追加。@fluorite/design-tokens パッケージが SSoT。Desktop (Tailwind v4 @theme) と Mobile (RN StyleSheet) の両方で利用。トークンの追加・変更、スタイリング時のトークン参照、CSS 生成時に使用。

Valibot を使った汎用スキーマ定義パターン。フォームバリデーション、API レスポンスのパース、環境変数の検証など、システム境界でのデータ検証に使用。react-declarative(utils 分離)や component-common(ディレクトリ構成)と組み合わせて使う。

Configure Claude Code for this project - detects languages and sets up rules, skills, and validators

MoonBit code generation best practices. Use when writing MoonBit code to avoid common AI mistakes with syntax, tests, and benchmarks.

Classify and govern data with tags. Handles "tag this table as PII", "apply financial tag", "list tags", "classify data", "add governance label".

Query and manage alerts. Handles "what alerts fired", "show alerts", "yesterday's alerts", "unresolved alerts", "critical alerts".

Add data quality checks with metrics and validity rules. Handles "add null check", "create row count metric", "list metrics", "add uniqueness check", "data quality status".

Trigger AI analysis for your data assets. Handles "analyze my database", "generate intelligence", "refresh analysis", "update AI knowledge".

Explore data lineage and dependencies. Handles "what depends on this table", "where does this data come from", "impact analysis", "upstream dependencies", "downstream consumers".

Set up monitoring for freshness and schema drift. Handles "monitor my table", "setup freshness", "enable schema monitoring", "track changes".

Profile tables and columns for statistics and distributions. Handles "profile this table", "show column stats", "data distribution", "table statistics", "cardinality analysis".

Fast Apple Mail search via SQLite on macOS. Search emails by subject, sender, date, attachments - results in ~50ms vs 8+ minutes with AppleScript. Use when asked to find, search, or list emails.

Web scraping and crawling with Firecrawl API. Fetch webpage content as markdown, take screenshots, extract structured data, search the web, and crawl documentation sites. Use when the user needs to scrape a URL, get current web info, capture a screenshot, extract specific data from pages, or crawl docs for a framework/library.

Fixes corrupted Panda CSS styled-system when styles appear broken, CSS isn't applying, or the build fails with styled-system errors. Use when CSS looks wrong, styles are missing, or after prettier/formatters may have corrupted generated files.

Creates a database migration using Drizzle. Use this EVERY TIME you need to modify the database schema. Walks through the complete workflow including generating migration, writing SQL, running it locally, and committing ALL required files.

Manage astrophotography gallery - add new photos, update metadata, optimize images, and list current photos.

Opens markdown files from this Obsidian vault in the Obsidian app interface. Use when the user wants to view, preview, or open a note in Obsidian rather than just reading it in the terminal.

Triage production/local issues using a log → trace → metrics workflow (HTTP/gRPC/async consumers). Use when debugging incidents, regressions, or SLO violations in an already-instrumented enterprise web app; not for adding new instrumentation.

Apply modern observability patterns (structured logs with trace correlation, RED metrics, OpenTelemetry spans, dashboards/alerts). Use when adding or changing logs/metrics/traces instrumentation, defining telemetry field contracts, or creating verification steps/runbooks for production debugging in enterprise web apps.

Design and maintain a shared platform library (e.g. `packages/shared`) that standardizes cross-cutting concerns across services (auth, config, gRPC/HTTP helpers, lifecycle, typed errors/results, observability, retries/timeouts). Use when multiple services duplicate boundary logic or when introducing shared primitives without creating a “utils junk drawer”.

CLI to manage emails via IMAP/SMTP. Use `himalaya` to list, read, write, reply, forward, search, and organize emails from the terminal. Supports multiple accounts and message composition with MML (MIME Meta Language).

Manage Apple Reminders via the `remindctl` CLI on macOS (list, add, edit, complete, delete). Supports lists, date filters, and JSON/plain output.

Manage Things 3 via the `things` CLI on macOS (add/update projects+todos via URL scheme; read/search/list from the local Things database). Use when a user asks Penguin to add a task to Things, list inbox/today/upcoming, search tasks, or inspect projects/areas/tags.

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

Set up and use 1Password CLI (op). Use when installing the CLI, enabling desktop app integration, signing in (single or multi-account), or reading/injecting/running secrets via op.

Display HTML content on connected Penguin nodes (Mac app, iOS, Android).

Restart Moltbot

Use this skill when: - Implementing the knowledge base for PatchPilot - Storing failure traces with embeddings - Retrieving similar past failures - Storing and retrieving fix patterns - Integrating Redis with Triage and Fixer agents

Use this skill when: - Implementing the Tester Agent - Writing E2E tests for the demo app - Setting up browser automation - Capturing screenshots and DOM state on failures - Converting natural language to browser actions

Install dependencies with monorepo awareness. Use when: user asks to install a package, add a dependency, or setup Python/JS packages. Triggers: "install X", "add package", "setup dependency", "I need lodash", "install docling".

Convert Markdown files with Mermaid diagrams to styled PDF. Use when user wants to export/convert markdown to PDF, generate PDF documentation, or create printable documents.

Creates and modifies Claude Code sub-agents following best practices. Use when user requests creating, updating, modifying, improving, or editing sub-agents. Triggers include "create/make/new agent", "sub-agent for X", file paths with /agents/, "update/modify/improve agent Y". Handles agent structure, YAML frontmatter (name, description, tools, model), system prompt design, tool restrictions (minimal permissions), isolated context benefits. Delegates to edit-tool orchestrator if uncertain about tool type (agent vs skill vs command vs script).

Self-custodial Bitcoin Lightning wallet for AI agents. Use when the agent needs to send or receive bitcoin payments, check its balance, generate invoices, or manage its wallet. Supports bolt11, bolt12, LNURL, and lightning addresses. Zero config — one command to initialize.

Free local speech-to-text using MLX Whisper on Apple Silicon. Free, private, no API costs.

Read-only audit agent that finds design token violations without modifying files.

Generates pull request title and body following VitalArc conventions.

Validate code quality without requiring builds. Use in cloud sessions to catch issues before they reach CI. Checks syntax, design system compliance, secrets, and import consistency.

Applies automatic fixes for design token violations. **Workstation only** - requires build capability to verify fixes.

Firecrawl MCP 도구를 사용하여 웹 페이지를 스크래핑, 크롤링, 검색합니다. 사용자가 웹 콘텐츠 수집, 사이트 크롤링, 웹 검색, 구조화된 데이터 추출을 요청할 때 사용합니다.

OXI E16 MIDI controller scene configuration. Use when creating, editing, or analyzing .oxie16 scene files for the OXI E16 controller. Handles MIDI CC, NRPN, and 14-bit mappings for synthesizers and other MIDI gear.

Add a new API endpoint following project conventions (Zod, route registration, client, tests). Use when creating or extending backend API routes.

Send SMS and make voice calls via Dialpad API. Supports single/batch SMS, voice calls with TTS, and caller ID selection.

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

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

プレゼンテーション用のスライドJSON（public/slides.json）を一から作成する。ユーザーがスライドの作成、プレゼンの作成、slides.jsonの生成を依頼したときに使用する。

| name | description | license | | --------------- | ------------------------------------------------------------ | ------------------------------------------- | | openclaw-helper | 专为解决用户在使用 OpenClaw/ClawBot/BoltBot 过程中遇到的问题而设计的动态辅助工具。优先检索本地 docs，找不到则联网查询，再通过交互排查并引导用户补充信息，最终提供可执行解决方案。 | Proprietary. LICENSE.txt has complete terms |

Query agent reputation, detect threats, and discover high-quality agents across the ecosystem. Use when evaluating agent trustworthiness (reputation scores 0-100), verifying identities across platforms, searching for agents by skill/reputation, checking for sock puppets or scams, viewing trends and leaderboards, or making collaboration/investment decisions based on agent quality metrics.

Format, lint, test changed files, then commit with English message

同步 DEV_SPEC.md 并将其拆分为 specs/ 目录下的章节特定文件。运行 sync_spec.py 进行更新，然后阅读 SPEC_INDEX.md 进行导航。所有基于规范的操作的基础。当用户说"同步规范"、"sync spec"或在任何依赖规范的任务之前使用。

Run the mandatory verification stack when changes affect runtime code, tests, or build/test behavior in the OpenAI Agents Python repository.

Creates new Claude Skills with proper structure, SKILL.md templates, and directory organization. 创建符合规范的新 Claude Skill，包含完整结构、模板和目录组织。当用户需要创建新 skill、为 Claude Code 添加功能或搭建 skill 脚手架时使用。

Automated testing framework for overnight builds. Every project must include test.sh. Tests run before delivery.

Comprehensive data analytics capabilities including SQL/SQLite querying, Python/pandas analysis, Excel processing, and visualization generation.

Browser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows. Trigger phrases include "go to [url]", "click on", "fill out the form", "take a screenshot", "scrape", "automate", "test the website", "log into", or any browser interaction request.

Complete browser automation using agent-browser CLI with AI-friendly semantic locators, ref system, and advanced waiting. Use when Claude needs to navigate and interact with web pages, extract structured data, fill forms, take screenshots, run E2E tests, or debug web applications. Covers semantic locators (role/text/label/placeholder), snapshot+ref workflow, session isolation with --profile, visible browser with --headed, JSON output for token efficiency, and error recovery strategies.

Exploratory data analysis using ydata-profiling. Use when users upload .csv/.xlsx/.json/.parquet files or request "explore data", "analyze dataset", "EDA", "profile data". Generates interactive HTML or JSON reports with statistics, visualizations, correlations, and quality alerts.

Diagnose and fix oh-my-claudecode installation issues

Analyze your OMC usage patterns and get personalized recommendations

Generate progressive disclosure indexes for GitHub repositories to use as Claude project knowledge. Use when setting up projects referencing external documentation, creating searchable indexes of technical blogs or knowledge bases, combining multiple repos into one index, or when user mentions "index", "github repo", "project knowledge", or "documentation reference".

Install skills from github.com/oaustegard/claude-skills into /mnt/skills/user. Use when user mentions "install skills", "load skills", "add skills", "update skills", "refresh skills", or references a skill not currently installed.

Expert on testing Move smart contracts including unit tests, integration tests, Move Prover formal verification, debugging strategies, test coverage, and CI/CD integration for Aptos development.

Expert on Aptos Object Model for composable, transferable assets. Covers ObjectCore, Object<T> wrapper, ConstructorRef, ExtendRef, DeleteRef, TransferRef capabilities, object ownership, named vs generated objects, and composability patterns.

Generate M&A financial proposals with IRR/MOIC calculations, payment schedules, earnouts, and debt modeling. Use for qualified deals needing financial analysis.

Create PowerPoint presentations for M&A board approval. Generates executive dashboards, financial highlights, risk assessments in Nuvini brand style.

Git-workflow plugin cache management. Use when Provider cache shows "not cached" to detect and cache the git provider. Also use to understand cache format or refresh cached values.

Explanations of common asynchronous patterns used in tursodb. Involves IOResult, state machines, re-entrancy pitfalls, CompletionGroup. Always use these patterns in `core` when doing anything IO

Overview of Experimental MVCC feature - snapshot isolation, versioning, limitations

Information about the differential fuzzer tool, how to run it and use it catch bugs in Turso. Always load this skill when running this tool

Use to run the local Go CLI that queries Naver Place rankings for a keyword + shop and returns JSON. Trigger when asked to check Naver Place rank, list all places for a keyword, or produce machine-readable ranking output from this repo.

Manages git operations with controlled write access. Use for commits, branches, staging, and git history exploration.

Automate stock trading operations on TongHuaShun (同花顺) mobile app for simulated trading. Use when working with stock trading tasks including: (1) Query account balance and positions, (2) Buy or sell stocks, (3) Manage pending orders and cancellations, (4) Manage favorite stocks (add/remove/search using pinyin initials), (5) Trade from favorites using pinyin initials instead of codes, (6) Automate trading strategies. Supports pinyin initial search (e.g., 'hkws' for 海康威视). Works with Android emulator (BlueStacks) via ADB and uiautomator2. Features stable Device architecture and cnocr Chinese OCR.

Este skill permite agregar transacciones al libro mayor de Beancount a partir de entrada en lenguaje natural en español.

Create a git worktree for a subtask, open a tmux window split, and start a new agent with an initial prompt.

Use the Strategy MCP server to access the Strategy Cloud library:

After a review completes, post a summary message using the Slack MCP server:

Answer questions about the AI SDK and help build AI-powered features. Use when developers: (1) Ask about AI SDK functions like generateText, streamText, ToolLoopAgent, embed, or tools, (2) Want to build AI agents, chatbots, RAG systems, or text generation features, (3) Have questions about AI providers (OpenAI, Anthropic, Google, etc.), streaming, tool calling, structured output, or embeddings, (4) Use React hooks like useChat or useCompletion. Triggers on: "AI SDK", "Vercel AI SDK", "generateText", "streamText", "add AI to my app", "build an agent", "tool calling", "structured output", "useChat".

Generate marketing images using Google's Imagen 3 (Nano Banana) model. Use when the user wants to create product mockups, social media visuals, blog hero images, carousel graphics, or any AI-generated marketing imagery. Triggers on requests like "generate an image of...", "create a visual for...", "make a mockup showing...", "design an image", or any image generation request for marketing content.

Build macOS .pkg installer for BriefDesk distribution. Use when the user wants to create a package, build an installer, distribute BriefDesk, or mentions .pkg files.

Safely remove a git worktree and its associated branches. Use when done with a feature branch worktree. Prevents shell breakage by ensuring correct CWD.

Use appropriate error classes from src/lib/errors.ts when handling errors in queries, API routes, and server actions. Apply automatically when writing error handling code.

NES development skill. Use when programming NES games, working with PPU/APU registers, sprites, backgrounds, scrolling, mappers, or any NES hardware. Covers 2A03 CPU, PPU graphics, APU audio, input, memory maps, and timing.

Publish the openwrk npm package with clean git hygiene. Triggers when user mentions: - "openwrk npm publish" - "publish openwrk" - "bump openwrk"

Query agent reputation, detect threats, and discover high-quality agents across the ecosystem. Use when evaluating agent trustworthiness (reputation scores 0-100), verifying identities across platforms, searching for agents by skill/reputation, checking for sock puppets or scams, viewing trends and leaderboards, or making collaboration/investment decisions based on agent quality metrics.

Testing guide using Vitest. Use when writing tests (.test.ts, .test.tsx), fixing failing tests, improving test coverage, or debugging test issues. Triggers on test creation, test debugging, mock setup, or test-related questions.

Validates synthetic training data for structured output models, checking structural validity and semantic accuracy to ensure zero hallucinations. Use when verifying JSONL training data files, assessing data quality, or confirming AI-generated datasets contain only factual extractions without fabrications.

翻译和分析马基雅维利著作中的核心政治哲学术语（stato、patria、virtù、fortuna等）。当遇到这些术语的翻译、对比或概念分析时使用此技能。