Loading...
Loading...
Found 6,674 Skills
基于 Google 搜索的 AI 概览（AI Overview / AI Mode）抓取，针对一个关键词返回主搜索的 AI 概览要点，适合用最新网页信息做深度调研、技术问答、长尾选品分析、海外消费者偏好分析。仅支持单轮对话，如需追问须由 agent 总结上下文后发起新请求。当用户提到 Google AI、AI Overview、AI Mode、谷歌AI概览、谷歌AI搜索、海外深度调研、长尾选品调研、消费者偏好分析、网页要点总结、Google AI search, AI Overview, AI Mode, deep research, consumer preference analysis 等场景时触发此技能。即使用户未明确提到"Google AI"，只要其需求是"用谷歌搜索 + AI 总结网页要点"，也应触发此技能。
Anti AI Slop: Design & Copy Rules. The core rules filter for AI coding agents. Load always to stop generic AI slop.
Use Proxyman MCP to inspect and debug captured HTTP/HTTPS/WebSocket traffic and operate Proxyman through all MCP actions. Use this skill when an agent needs to analyze traffic, diagnose missing capture, manage rules, use Compose, inspect WebSockets, install certificates, control proxy settings, use setup guidance, export flows, generate code, run Proxyman automations, or troubleshoot Proxyman MCP.
Turn a retirement portfolio into sustainable lifetime income: sequence-of-returns risk, the 4% rule and its assumptions, Guyton-Klinger-style guardrails, RMD calculation from the Uniform Lifetime Table, Social Security claiming math (early reduction, delayed credits, breakeven age, survivor benefits), gap-year bracket-filling with Roth conversions, bucket strategies vs total-return, and SPIA annuitization as longevity insurance. Use when the user asks about a 'safe withdrawal rate', 'when should I claim Social Security', a 'guardrails strategy', 'sequence of returns risk', or 'how much can I spend in retirement'. Also trigger on RMD amounts or missed-RMD penalties, Social Security breakeven analysis, '4% rule', 'bucket strategy', retirement paycheck design, drawdown or decumulation planning, and whether to buy an annuity. For accumulation-side savings math, see savings-goals; for asset location and tax mechanics, see tax-efficiency.
Convert an HTML document supplied in the request body to clean Markdown, stripping scripts and styles. Called as POST /v1/doc/html-to-markdown, it takes html and returns markdown, characters, inputBytes. A research agent handed raw HTML must reduce it to readable text before it can reason over it, and passing full markup through a model wastes most of the context window. Reading this schema and dry-running the call are free and need no wallet; a real call costs $0.004, paid in USDC on Base over x402.
Pulls DOIs, arXiv ids, PMIDs, PMCIDs and ISBNs out of free text, deduplicated and normalized, with the character offset of each first occurrence. Called as POST /v1/text/extract-citations, it takes text, kinds and returns count, citations, byKind. An agent handed a references section, an email or a PDF dump has to find the identifiers before it can look any of them up, and a model asked to do it by reading invents DOIs that resolve to nothing. The catalog already answers `crossref.doi-metadata` and `pubmed.citation-search`; neither could tell you what to ask them about. Reading this schema and dry-running the call are free and need no wallet; a real call costs $0.003, paid in USDC on Base over x402.
Fetch a public web page and return it as clean Markdown with its title. Capped at 2 MB. Called as GET /v1/doc/url-to-markdown, it takes url and returns sourceBytes, title, markdown, characters. This is the third-highest-demand category observed on-chain: an agent given a link needs the readable text, not the markup, and cannot run a browser itself. Reading this schema and dry-running the call are free and need no wallet; a real call costs $0.003, paid in USDC on Base over x402.
Makes this agent generate images, transcribe audio, and synthesize speech on the user's own machine through a local Lemonade Server instead of a paid cloud API. Use it above all to change that routing persistently, from now on — keep generating pictures locally while chat stays on the cloud; set this workspace up to make images on my own machine — even when the user asks for no image or file in the same breath. Also use it for a single request the user wants done locally, offline, on-device, or kept private: transcribe this recording, make this picture, read this text aloud. Applies in Claude, Cursor, Codex, or any agent harness. Use when the user wants to cut cost or tokens on image, audio, or voice API calls, or to drop DALL-E, hosted Whisper, ElevenLabs, or other paid multimodal APIs; or mentions Lemonade Server, OmniRouter, SD-Turbo, kokoro, Ryzen AI, or NPU/iGPU/dGPU inference. Changes no application source code; do not use it if the user is adding local AI to an app they ship.
Code comment hygiene for AI coding agents: remove generic AI-slop comments, keep the valuable ones, never touch the code.
Guide the agent on creating visually distinctive, polished Vaadin 25 interfaces that go beyond default theme styling. This skill should be used when the user asks to "make it look good", "improve the design", "style the view", "make it visually appealing", "add polish", "design a UI", "create a beautiful interface", or when building a new view where visual quality matters. Also trigger when the user wants to add animations, visual effects, or build polished component compositions in a Vaadin application.
Refine text, screenshots, hand-drawn sketches, "Little Black" illustrations, or existing HTML relationship diagrams into minimal wireframes with teaching semantics; for relationship-dense diagrams, first write executable relationship structure specifications using Mermaid, then implement them as accessible, responsive inline SVGs, and simultaneously output reusable wireframe generation prompts. Used for comparison diagrams, architecture diagrams, flowcharts, interface or API diagrams, Agent collaboration diagrams, and state relationship diagrams in HTML Presentations, course pages, and web cards; activated when users request "semantic wireframes", "wireframe illustrations", "convert illustrations to SVG", "generate wireframe prompts", "draw GUI/LUI, Agent, task, or system relationships in cards", or require following the STYLE_DNA of course-design for teaching illustrations. Not applicable to photos, decorative posters, complex data charts, emotional hand-drawn illustrations, or direct editing of binary PPTX files.
Covers creation and maintenance of a custom Bitrix module in /local/modules/<vendor>.<module>/ — CModule class, install/index.php, DoInstall and DoUninstall, install/version.php with $arModuleVersion, registration of events and agents during installation, module options (options.php), generation via make:module. Applied when creating a new module, refining installation/uninstallation, registering event handlers and publishing module options in the Admin Panel. Key terms — CModule, DoInstall, DoUninstall, module manifest, install/index.php, make:module, vendor.module.