AI Skills Hub - Browse 180,000+ Agent Skills

Capture an idea for later without interrupting your flow.

CCXT cryptocurrency exchange library for Binance Futures gold trading. REST and WebSocket API patterns.

Calculate portfolio risk metrics including VaR, CVaR, Sharpe, Sortino, and drawdown analysis for gold futures.

Scout price discrepancies between Polymarket and Kalshi for discovery and comparison. Read-only; no execution.

Create conversation adapters for importing AI chat history from different tools (Claude Code, Cursor, Warp, Codex, etc.). Covers the adapter.Adapter interface, caching strategies, incremental parsing, watch/FD management, and performance standards. Use when creating a new adapter, modifying adapter behavior, or debugging adapter performance issues. See references/ for Cursor DB and Warp SQLite schema details.

Release new versions of sidecar. Covers version tagging with semver, td dependency updates, go.mod validation, CHANGELOG updates, GoReleaser automation, Homebrew tap updates, and verification steps. Use when preparing or executing a release.

Create new sidecar plugins implementing the plugin.Plugin interface, rendering views with Bubble Tea, handling keyboard input via keymap contexts, and integrating with the app shell (footer hints, event bus, adapters). Use when creating a new plugin, modifying plugin architecture, or debugging plugin rendering/lifecycle issues. See references/ for sidebar list and fixed footer layout details.

Interactive first-run workspace setup with directory scaffolding, integration verification, and context gathering

Blender 3D development via BlenderMCP for scene creation, materials, assets, and procedural workflows

Use this skill when the user is working in the **Metadata-Upload** repository or asks about X-ray metadata ingestion, file watchers, auto-commit to GitHub, or maintaining this codebase.

Use when you need to start a local development server, view the site locally, provide a localhost URL, or when the user wants to preview their work. Handles port conflicts automatically.

PROACTIVELY search conversation history when receiving user instructions. Find previous discussions, decisions, and context BEFORE starting new work. Your memory is valuable - use it.

Guides writing bundler tests using itBundled/expectBundled in test/bundler/. Use when creating or modifying bundler, transpiler, or code transformation tests.

Creates JavaScript classes using Bun's Zig bindings generator (.classes.ts). Use when implementing new JS APIs in Zig with JSC integration.

Guides writing HMR/Dev Server tests in test/bake/. Use when creating or modifying dev server, hot reloading, or bundling tests.

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

Crea y edita presentaciones PowerPoint programáticamente usando HTML, plantillas o edición directa de XML. Incluye herramientas para miniaturas, reordenamiento de diapositivas y reemplazo de texto.

Comprehensive Mastra framework guide. Teaches how to find current documentation, verify API signatures, and build agents and workflows. Covers documentation lookup strategies (embedded docs, remote docs), core concepts (agents vs workflows, tools, memory, RAG), TypeScript requirements, and common patterns. Use this skill for all Mastra development to ensure you're using current APIs from the installed version or latest documentation.

Query Jo dev conversations - list, search, and dump full context windows from the local database. Use when you need to read Jo conversation history, find specific conversations, or inspect message content.

Build MCP (Model Context Protocol) servers and tools with laravel/mcp to expose functionality to external AI clients like Claude Code.

Add and update the documentation website for Syncpack. Use when making user-facing changes to the codebase.

Debug and fix bugs in Syncpack using scientific debugging methodology. Use when a test is failing, unexpected behaviour occurs, or investigating issues. Covers hypothesis-driven debugging and TDD-based fixes.

Fill standard legal agreement templates (NDAs, cloud service agreements, SAFEs) and produce signable DOCX files. Supports Common Paper, Bonterms, and Y Combinator templates. Use when the user needs to draft a legal agreement, create an NDA, fill a contract template, or generate a SAFE. DOCX generation requires Node.js >=20.

Process entity notes into structured tasks and profile updates. Use when the user says "process notes", mentions extracting tasks from notes, wants to update entity information from meeting notes, or provides meeting notes to organize. Supports batch processing across multiple entities.

Query the tinkerer.club Discord community data. Search messages, explore conversations, view threads, track user activity, and get channel statistics. Use when the user asks about tinkerer.club Discord data, community activity, or conversation history.

Post moments, mint likes, create collections, and interact with Forever Moments on LUKSO. Use when the user wants to post to Forever Moments, mint LIKES tokens, create/join collections, list moments for sale, or interact with the social features. Supports both gasless relay and direct transaction execution. Now with image support - pin images to IPFS and attach to moments.

Compile LaTeX documents to PDF using the container's TeX Live installation. Supports pdflatex, xelatex, and lualatex engines.

moltart gallery — tools and a wall for making visuals. You write code, the code makes art, it goes on the wall.

moltart gallery — tools and a wall for making visuals. You write code, the code makes art, it goes on the wall.

Interactive code review of PRs or local changes against team standards, golden paths, and optionally the Engineering Codex.

Draft a Pax8 Product Requirements Document from an approved Opportunity Brief, enriched with Engineering Codex technical insights, Pax8 ADR standards, and best practices.

Time-boxed research and investigation skill for answering specific technical questions, evaluating options, and reducing uncertainty before committing to implementation.

Explains the mental model and architecture of the code under `packages/forms/signals`. You MUST use this skill any time you plan to work with code in `packages/forms/signals`

Run the OTEL eval workflow end-to-end (export trace, run eval packs via run-skill-eval.sh, collect JSON/Markdown report locations, and summarize results). Use when asked to execute or verify evals, generate LLM-as-judge reports, or audit eval pipeline outputs.

Agents work in parallel on the same task; judges evaluate and select the winner.

Two agents co-create an artifact through turn-based iteration until both signal DONE.

Automate HelpDesk tasks via Rube MCP (Composio): list tickets, manage views, use canned responses, and configure custom fields. Always search tools first for current schemas.

Guide for creating and editing skills. Use when users want to create a new skill, update an existing skill, or learn about skill structure and best practices.

Guides Python SDK development in Apache Beam, including environment setup, testing, building, and running pipelines. Use when working with Python code in sdks/python/.

Guides understanding and using the Gradle build system in Apache Beam. Use when building projects, understanding dependencies, or troubleshooting build issues.

Search for jobs across LinkedIn, Indeed, Glassdoor, ZipRecruiter, Google Jobs using the JobSpy MCP server.

Vercel AI SDK 5 patterns. Trigger: When building AI features with AI SDK v5 (chat, streaming, tools/function calling, UIMessage parts), including migration from v4.

Use this skill for creating, formatting, or editing scientific manuscripts and academic papers as Word documents (.docx). Triggers include: writing or rewriting a research paper, generating a manuscript from data/results, formatting a paper for journal submission, adding real references from DOIs or BibTeX, injecting Zotero/Mendeley-style field codes into citations, creating supplementary materials, cover letters, or reviewer responses. Also use when the user mentions 'paper', 'manuscript', 'journal submission', 'references', 'bibliography', 'citation style', 'Vancouver', 'APA', or discusses integrating analysis results (ML, metabolomics, clinical trials, omics) into a publication. Use this skill even when the user just uploads data and asks to 'write up the results'. This skill extends the docx skill with academic-specific features: real reference fetching, Zotero field code injection, journal-style formatting, and structured scientific sections.

iOSアプリのよくあるバグパターンを網羅的にチェック。メモリリーク、循環参照、並行処理バグ、UIレイアウト問題、Force Unwrap、ライフサイクル問題、Swift Concurrencyエラーなどを静的解析＋動的チェック。トリガー：「バグチェック」「クラッシュ調査」「メモリリーク」「コードレビュー」「品質チェック」「iOS診断」。

WebアプリとChrome拡張機能のデバッグスキル。Chrome DevTools MCPを使ってブラウザをリモートデバッグ。コンソールエラー確認、ネットワーク監視、DOM検査、JavaScript実行、スクリーンショット取得。トリガー：「デバッグ」「コンソールエラー」「ネットワーク確認」「DOM検査」「ブラウザテスト」「Chrome拡張機能デバッグ」「DevTools」「JS実行」「エラー調査」。

Fetch official Apple developer documentation using the apple_docs.py tool. Use for Xcode, SwiftUI, UIKit, Swift, iOS SDK, and any Apple framework documentation. Converts Apple's JSON API docs to clean Markdown.

Show which GSD plans can run in parallel based on wave assignments. Reads wave frontmatter from PLAN.md files and displays terminal assignment suggestions.

Communicate with the Round Table via NATS. Use when you need to send results, reports, or messages to Tim or other knights through the NATS messaging bus. Your nats-bridge sidecar exposes a local HTTP API for publishing.

Fix MkDocs navigation YAML errors by adding frontmatter with title to all index.md files

Contribute team discoveries (skills, knowledge, framework fixes) to parent organization repository

Fix GitHub Pages homepage 404 by creating docs/index.md

Diagnose and fix MkDocs build issues — broken mermaid diagrams, plugin errors, package compatibility

Guidelines for writing docs content — mermaid diagrams, formatting, dark mode compatibility

Contribute instance discoveries (skills, knowledge) to parent team repository

Structured debug protocol for investigating hard-to-diagnose issues. Maintains a debug log to prevent re-trying failed approaches and preserve institutional knowledge. Use when the user says "debug", is investigating a bug, hang, performance regression, or any issue that isn't immediately obvious.

Send a Slack message to a channel. Use when the user says "send slack", "slack message", "notify on slack", "post to slack", or wants to send a message to a Slack channel.

Reference for NVIDIA Nsight Compute (ncu) CLI flags and common usage patterns. Use when running NCU commands to profile, export, or query CUDA kernels. Consult this before constructing any ncu command to avoid flag mistakes.

Provides Event Storming workshop facilitation guidance — discovering domain events, commands, aggregates, policies, and bounded contexts. Use when starting domain exploration, mapping business processes, finding aggregate boundaries, running an event storming session, or exploring how a system works from a DDD perspective.

Use when the user asks to generate, remix, poll, list, download, or delete Sora videos via OpenAI’s video API using the bundled CLI (`scripts/sora.py`), including requests like “generate AI video,” “Sora,” “video remix,” “download video/thumbnail/spritesheet,” and batch video generation; requires `OPENAI_API_KEY` and Sora API access.

Analyze git repositories to build a security ownership topology (people-to-file), compute bus factor and sensitive-code ownership, and export CSV/JSON for graph databases and visualization. Trigger only when the user explicitly wants a security-oriented ownership or bus-factor analysis grounded in git history (for example: orphaned sensitive code, security maintainers, CODEOWNERS reality checks for risk, sensitive hotspots, or ownership clusters). Do not trigger for general maintainer lists or non-security ownership questions.

Link readings, flashcards, and questions through adaptive progression rules for learning apps. Use when defining or implementing unlock logic, remediation recommendations, or event-driven content sequencing based on missed questions, reading completion, and topic-level performance trends.

Use when the user asks for text-to-speech narration or voiceover, accessibility reads, audio prompts, or batch speech generation via the OpenAI Audio API; run the bundled CLI (`scripts/text_to_speech.py`) with built-in voices and require `OPENAI_API_KEY` for live calls. Custom voice creation is out of scope.

Transcribe audio files to text with optional diarization and known-speaker hints. Use when a user asks to transcribe speech from audio/video, extract text from recordings, or label speakers in interviews or meetings.

专业的中文文本“去 AI 化”编辑器。消除机械感、翻译腔与虚假的逻辑词。使用场景：改写 AI 稿件、优化汇报、使公文“说人话”。

Talk to your Garmin data naturally - "what was my fastest speed snowboarding?", "how did I sleep last night?", "what was my heart rate at 3pm?". Access 20+ metrics (sleep stages, Body Battery, HRV, VO2 max, training readiness, body composition, SPO2), download FIT/GPX files for route analysis, query elevation/pace at any point, and generate interactive health dashboards. From casual "show me this week's workouts" to deep "analyze my recovery vs training load".

使用 Google NotebookLM 深度查询自有文档。支持浏览器自动化、库管理与持久化认证。场景：基于文档的深度问答、研究分析。

Implements Manus-style file-based planning for complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when starting complex multi-step tasks, research projects, or any task requiring >5 tool calls.

Intelligent document-to-LaTeX conversion engine. Converts .docx/.md/.txt to professional PDF/LaTeX using specific styles (Academic, Tech Book, CV). Use when user asks to "generate PDF", "make a resume", "format my thesis", or "publish this book".

Convert any document (PDF, DOCX, PPTX, XLSX), image, or media file to clean Markdown. Powered by Microsoft MarkItDown. Use when you need to "read" non-text files for analysis.

获取股票价格、基本面、新闻及历史趋势。支持多代码查询、自然语言日期解析及 JSON 输出。当用户询问“XX股价是多少”、“查看XX公司的最新新闻”或“分析XX过去一年的表现”时触发。

Manages project knowledge using ByteRover context tree. Provides two operations: query (retrieve knowledge) and curate (store knowledge). Invoke when user requests information lookup, pattern discovery, or knowledge persistence. Developed by ByteRover Inc. (https://byterover.dev/)

Automatic conversation backup system for Obsidian with incremental snapshots, hourly breakdowns, and formatted chat-style markdown. Use when setting up conversation archival, preventing data loss from /new resets, or organizing chat history in Obsidian vault with proper formatting (colored callouts, timestamps, multi-paragraph support).

Fetch and read transcripts from YouTube videos. Use when you need to summarize a video, answer questions about its content, or extract information from it.

Enable and configure Moltbot/Clawdbot memory search for persistent context. Use when setting up memory, fixing "goldfish brain," or helping users configure memorySearch in their config. Covers MEMORY.md, daily logs, and vector search setup.

Generate consistent multi-scene storyboard images using Gemini. Use when the user wants to create a storyboard, generate sequential scene images, or create consistent multi-panel illustrations.

Analyze git repository statistics: commit type distribution, layer activity, hotspot files, velocity, and tag inventory. Use when user types /repo-stats, asks about codebase activity, commit patterns, or "what's been changing".

Release management with changelog generation, version tagging, and GitHub releases. Gathers commits since last semver tag, groups by conventional commit type, suggests version bump. Use when user types /release or asks about versioning, changelog, or publishing a release.

When answering questions, you MUST check conflicts and surface caveats.

Performs financial ratio analysis, DCF valuation, budget variance analysis, and rolling forecast construction for strategic decision-making

Technology stack evaluation and comparison with TCO analysis, security assessment, and ecosystem health scoring. Use when comparing frameworks, evaluating technology stacks, calculating total cost of ownership, assessing migration paths, or analyzing ecosystem viability.

This skill should be used when the user asks to "design REST APIs", "optimize database queries", "implement authentication", "build microservices", "review backend code", "set up GraphQL", "handle database migrations", or "load test APIs". Use for Node.js/Express/Fastify development, PostgreSQL optimization, API security, and backend architecture patterns.

Analyzes pipeline coverage, tracks forecast accuracy with MAPE, and calculates GTM efficiency metrics for SaaS revenue optimization

Monitors customer health, predicts churn risk, and identifies expansion opportunities using weighted scoring models for SaaS customer success

Personal task management system using semantic analysis to manage roadmap.md with natural language input

Expert code review of current git changes with a senior engineer lens. Detects SOLID violations, security risks, and proposes actionable improvements.

Use when testing React components with Vitest and React Testing Library

Use when implementing React server-side rendering with streaming, Suspense, or partial pre-rendering

Use when working with React forms, async actions, or needing optimistic UI updates

Distributed task coordination via GitHub Issues. Use when working in a beehive project (identifiable by .bh/ directory). Provides the protocol for claiming tasks, working on them, and submitting results as PRs. Covers all roles (execute, explore, verify, formalize, advisor).

Use when setting up gog CLI authentication — storing OAuth credentials, adding Gmail accounts, refreshing tokens, or troubleshooting gog auth issues

Produce a structure-mirrored, evidence-first technical handbook from a repository.

Auto-generate README.md from project metadata on each commit

Semantic code search using natural language queries. Use when users ask "where is X implemented", "how does Y work", "find the logic for Z", or need to locate code by concept rather than exact text. Returns file paths with line numbers and code snippets.

Writes and maintains reliable Playwright end-to-end tests using accessible selectors (getByRole, getByLabel) and web-first assertions. Use when creating e2e tests, fixing flaky tests, or reviewing test code for best practices.

Interact with the Cal.com API v2 to manage scheduling, bookings, event types, availability, and calendars. Use this skill when building integrations that need to create or manage bookings, check availability, configure event types, or sync calendars with Cal.com's scheduling infrastructure.

Simulate a specific transaction path through the fee distribution system and display all results.

Collaborative planning, discussion, and analysis between Claude and Gemini. Both AIs independently research and then cross-verify through structured rounds. Triggers: "collaborate with Gemini", "Gemini와 협업", "AI 협업", "Gemini와 함께 계획", "PRD 작성", "워크플로우 설계", "discuss with Gemini", "Gemini와 논의", "Gemini한테 물어봐", "AI끼리 토론", "두 AI 의견 비교".

Filter duplicate file groups to keep only consistent decisions (all KEEP or all ARCHIVE). Use when processing CSV duplicate file groups and need to focus on groups with clear, consistent decisions.

Generate bash scripts to move files to archive directory. Use when creating archival scripts for duplicate file groups.

Process CRISPR screening data to identify essential genes and hit candidates. Performs quality control, statistical analysis (RRA), and hit calling for pooled CRISPR screens including viability screens and drug resistance/sensitivity studies.