全部能力

Convert entire PDF documents to clean, structured Markdown for full context loading. Use this skill when the user wants to extract ALL text from a PDF into…

Expert product strategy and product marketing skill. Use when defining product vision, assessing product-market fit, sizing market opportunities, doing competitive positioning, building growth loops, designing PLG strategies, creating product marketing context, or using the Working Backwards methodology. Activates for: product strategy, product marketing, PMM, product manager, product management, growth product manager, working backwards, PR/FAQ, Amazon PR FAQ, product roadmap, product positioning, product-market fit, product launch, feature prioritization, TAM SAM SOM, market sizing, competitive moat, business model design, monetization strategy, north star metric, activation, retention, growth loops, freemium, PLG, product-led growth, growth experimentation, ICP context, marketing context document.

Generates complete page layouts and shells for common patterns (dashboard, authentication, settings, CRUD pages) with consistent navigation, layout components,…

Creates jaw-dropping, production-ready frontend interfaces AND delivers perfectly matched real photos (Unsplash/Pexels direct links) OR flawless custom…

Product management frameworks for business cases, market analysis, strategy, prioritization, OKRs/KPIs, personas, requirements, and user research. Use when…

Turn integrated agent delivery into one packet-first orchestration decision. Use when the user wants a single front door for plan approval, runtime handoff, browser/UI verification, resume or recovery, and durable `.jeo` task history across Claude Code, Codex CLI, Gemini CLI, or OpenCode. Route spec-first execution loops to `ralph`, visual plan review to `plannotator`, runtime-native execution to `omc` / `omx` / `ohmg`, browser verification to `agent-browser`, submit-gated UI feedback to `agentation`, and trust/approval posture tuning to `ralphmode`.

Brad Frost's Atomic Design methodology for UI component hierarchies: atoms (indivisible elements), molecules (small groups of atoms), organisms (complex sections of molecules), and templates (page layouts). Enforces bottom-up composition (never skip levels), presentational components (data via props, events via callbacks, no data fetching), design tokens for all visual properties, and composition over inheritance. Use when building user interfaces, creating component libraries, organizing frontend code, designing form systems, or structuring any UI. Triggers on: "build a component", "component hierarchy", "design tokens", "presentational components", "composition over inheritance", "React/Vue/SwiftUI components", "atomic design". Applies to any UI framework.

Feishu message reading. Activate when user mentions reading messages, chat history, message lookup, or finding previous messages.

Minimal visual reasoning smoke test for Model Studio QVQ.

Expert-level MongoDB database design, aggregation pipelines, indexing, replication, and production operations

Analyze and extract design patterns from visual examples. Deconstructs design systems, color palettes, typography, and layout principles from reference…

Help users craft compelling brand narratives. Use when someone is defining brand strategy, writing company positioning, creating pitch narratives, developing…

中国新闻站点内容提取。支持微信公众号、今日头条、网易新闻、搜狐新闻、腾讯新闻。当用户需要提取中国新闻内容、抓取公众号文章、爬取新闻、或获取新闻JSON/Markdown时激活。

Working Backwards PRFAQ challenge to forge product concepts. Use when the user requests to 'create a PRFAQ', 'work backwards', or 'run the PRFAQ challenge'.

Determine when a product, platform, or communication crosses the regulatory line from education into investment advice requiring registration. Use when the…

解析、验证和解释cron表达式，计算下次运行时间。

Diagnose interface errors, drops, CRCs, duplex mismatches, flapping, speed negotiation issues, and counter trends on routers, switches, and Linux hosts.

Generate production-quality SVG icons with COLOR support using VTracer vectorization. Converts raster images to clean, colorful SVG paths.

Computer vision engineering skill for object detection, image segmentation, and visual AI systems. Covers CNN and Vision Transformer architectures, YOLO/Faster R-CNN/DETR detection, Mask R-CNN/SAM segmentation, and production deployment with ONNX/TensorRT. Includes PyTorch, torchvision, Ultralytics, Detectron2, and MMDetection frameworks. Use when building detection pipelines, training custom models, optimizing inference, or deploying vision systems.

Product interaction and UX expert. Use when reviewing UI/UX, conducting heuristic evaluations, designing user journeys, applying cognitive psychology…