发现 Skills

Query Supabase projects - count users, list signups, check stats. Use for database queries and user analytics.

Browse the web, read page content, click buttons, fill forms, take screenshots, and get accessibility snapshots using the webcli headless browser. Use when the user asks to visit a website, gather information from a web page, or interact with a web app.

YouTube Data API v3 analytics toolkit. Analyze YouTube channels, videos, and search results. Use when the user asks to: check YouTube channel stats, analyze video performance, compare channels, search for videos, get subscriber counts, view engagement metrics, find trending videos, get channel uploads, or analyze YouTube competition. Requires a YouTube Data API v3 key from Google Cloud Console.

Deep-research orchestrator covering the full workflow: planning → dimensioned evidence collection → synthesis → final draft (report.md). Outputs are written to report_dir and it supports resumable runs. Before starting it must perform a minimal generic web_search probe to confirm the current session's search capability; if the probe fails or cannot confirm, stop and prompt the user to configure. **Proactively use this skill (do not just search a few items and answer) whenever any of the following apply:** ① User uses trigger terms: deep research / in-depth research / comprehensive research / systematic research / research / survey / due diligence / industry research / market research / competitor analysis / policy research / technical research / trend research / fact-checking / write a research report / research report / in-depth report; ② The request requires evidence collection from multiple sources, multi-dimensional comparison, or cross-validation to reach a reliable conclusion; ③ The user requests a deliverable such as a report, white paper, industry analysis, or due-diligence document; ④ The topic involves up-to-date policy/market/product/pricing/regulation that needs systematic verification. Vague or broad "research/learn about X" queries should also preferentially trigger. Not intended for: single-fact Q&A ("What is X"), one-sentence summaries, organizing content already provided from a single source, or pure copy-editing/paraphrasing.

Specialized knowledge for writing modern high-quality CSS. Trigger this skill when starting a new CSS project/file, when the user asks about new CSS features (e.g. Masonry, View Transitions, Container Queries, Scroll-driven animations), or requests refactoring of legacy styles to modern standards.

Implement mHC (Manifold-Constrained Hyper-Connections) for stabilizing deep network training. Use when implementing residual connection improvements with doubly stochastic matrices via the Sinkhorn-Knopp algorithm. Based on DeepSeek's 2025 paper (arXiv:2512.24880).

Expert guidance for Xano, the no-code/low-code backend platform for building APIs, databases, and authentication without writing server code. Helps developers and non-technical builders create production-ready REST APIs with visual function stacks, manage data models, and integrate with frontend fra

Master Rust async programming with Tokio, async traits, error handling, and concurrent patterns. Use when building async Rust applications, implementing concurrent systems, or debugging async code.

Web frontend project development rules. Use this skill when developing web frontend pages, deploying static hosting, and integrating CloudBase Web SDK.

Integrate AgentZero with Telegram so users can chat with the AI via a Telegram bot. Covers full setup from BotFather token to auto-start supervisord service. Use when asked to set up, deploy, or configure Telegram integration for AgentZero.

Use this skill whenever a user asks to generate, create, draw, render, or edit images with GPT Image 2 / gpt-image-2, text-to-image, reference-image editing, inpainting, posters, typography, Chinese text, UI mockups, diagrams, or gallery prompts. Analyze the user's prompt, search the bundled Reference Gallery/craft files for matching design patterns, confer on direction when useful, then call the packaged `gpt-image` CLI or bundled `scripts/generate.py`. Do not write new image-generation code unless explicitly asked to modify this repo.

View, search, and download academic papers from arXiv. Supports API queries, web scraping via Actionbook, and HTML paper reading via ar5iv. Use when user asks about arxiv papers, academic papers, research papers, paper summaries, latest papers, or wants to search/download/read papers.

自动分析B站视频内容，下载视频并拆解成帧图片，使用AI分析并生成详细的专题文档或实操教程。

Patchright-based browser automation with bot detection bypass. Use when Claude needs to interact with local web applications, test localhost/dev servers, take screenshots, or perform UI interactions on private networks. Ideal for QA automation, frontend debugging, E2E testing, and pre-deployment verification on local development environments.

Automatically captures, crops, and beautifies screenshots from URLs for your portfolio or docs.

Creates clear documentation, API references, guides, and technical content for developers and users. Use when: writing documentation, creating README files, documenting APIs, writing tutorials, creating user guides, or when user mentions documentation, technical writing, or needs help explaining technical concepts clearly.

Design AWS architectures for startups using serverless patterns and IaC templates. Use when asked to design serverless architecture, create CloudFormation templates, optimize AWS costs, set up CI/CD pipelines, or migrate to AWS. Covers Lambda, API Gateway, DynamoDB, ECS, Aurora, and cost optimization.

Deployment automation skill for CI/CD pipelines

Real-time search engine supporting web search, vertical domain search (23 domains), parallel batch search, and URL content extraction.

Generate interactive TiddlyWiki-style HTML software manuals with screenshots, API docs, and multi-level code examples. Use when creating user guides, software documentation, or API references. Triggers on "software manual", "user guide", "generate manual", "create docs".

图片生成, 架构图, 流程图, 时序图, 泳道图, diagram, architecture, flowchart, sequence, swimlane, image generation, nano banana, 生图, 画图, 画一个, 生成图片, generate image, draw diagram

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) modifying existing spreadsheets while preserving formulas, (4) data analysis and visualization in spreadsheets, or (5) recalculating formulas.

Converts documents to markdown with multi-tool orchestration for best quality. Supports Quick Mode (fast, single tool) and Heavy Mode (best quality, multi-tool merge). Use when converting PDF/DOCX/PPTX files to markdown, extracting images from documents, validating conversion quality, or needing LLM-optimized document output.

Enhanced web search and real-time content retrieval via Grok API with forced tool routing. Use when: (1) Web search / information retrieval / fact-checking, (2) Webpage content extraction / URL parsing, (3) Breaking knowledge cutoff limits for current information, (4) Real-time news and technical documentation, (5) Multi-source information aggregation. Triggers: "search for", "find information about", "latest news", "current", "fetch webpage", "get content from URL". IMPORTANT: This skill REPLACES built-in WebSearch/WebFetch with Grok Search tools.