Scan to join WeChat groupBrowse curated skills with source links, package snapshots, README assets and install signals in one calm, searchable catalog.
Deep-dive usability evaluation of specific user tasks. Simulates novice user cognition step-by-step to identify learnability issues, unclear actions, and points of confusion.
Use when designing empty states, error handling, offline behavior, loading content, and boundary conditions for an app's screens.
Use when evaluating first-run experience, progressive disclosure, onboarding tutorials, and how new users learn to use the product.
Extract video clips from long videos based on natural-language descriptions. Use this skill when user needs to: - Extract highlights or specific scenes from videos - Find specific people/objects in vi…
小红书（Xiaohongshu/RED）公开笔记与用户数据分析 skill，通过 MaxHub API 查询笔记详情、评论、用户资料、搜索、话题、商品/种草内容和推荐流。适合品牌种草分析、KOL 画像、内容选题、竞品监控和评论洞察。默认 read-only；agent 应按 recipes 选择笔记/用户/搜索/评论链路，使用 note_id/user_id/keyword 等字段流传参，并避免采…
Creative research ideation and exploration. Use for open-ended brainstorming sessions, exploring interdisciplinary connections, challenging assumptions, or identifying research gaps. Best for early-st…
文案诊断助手适合内容创作者、运营、市场营销、内容媒体在用户提出“这段文案能打动人吗”这类问题，需要快速拆解目标、判断重点并形成可执行结果时使用，帮助基于输入材料生成摘要、诊断结论、行动建议和可复用交付物。
Generate images using Google Gemini's image generation capabilities. Use this skill when the user needs to create, generate, or produce images for any purpose including UI mockups, icons, illustration…
Use when evaluating information hierarchy within screens — what's prominent, what's secondary, and how the user's eye is guided through content.
Use when evaluating photography style, illustration systems, hero visuals, and decorative imagery for a product or marketing site.
Create and check long-running video material evaluation tasks. Use this skill when the user wants to submit videos for evaluation, check an existing video evaluation task list, or fetch the result of …
Video resolution resize operator (las_video_resize). Use this skill when user needs to: - Resize video resolution into a target range (min/max width/height) - Preserve aspect ratio with increase/decre…
This skill should be used when working with pre-trained transformer models for natural language processing, computer vision, audio, or multimodal tasks. Use for text generation, classification, questi…
基于 PaddleOCR + Qwen3-VL-4B (OpenVINO) 的本地 AI 营销海报合规审核 Skill。自动检测广告法违规风险（绝对化用语、虚假宣传、行业禁用词等），生成结构化审核报告。所有推理在本地 Intel CPU 上完成，数据不出设备。
当用户提到邮箱相关能力时，进入这个skill，统一邮件入口（纯路由层）：识别用户意图后路由到 public-skill 或 imap-smtp-email，自身不执行任何脚本
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create ori…
Use when evaluating depth, layering, shadow systems, surface treatments, and shape language (border radius, corner treatment) in a design.
Use when evaluating loading states, perceived performance patterns, skeleton screens, optimistic UI, and progress indicators.
Audio format conversion operator. Use this skill when user needs to: - Convert audio files between formats (wav, mp3, flac) - Change audio properties (sample rate, bit rate) using ffmpeg params Suppor…
Video content understanding operator (las_vlm_video) via Doubao models. Use this skill when user needs to: - Analyze/describe video content with natural language prompts - Ask questions about what hap…
Python library for working with DICOM (Digital Imaging and Communications in Medicine) files. Use this skill when reading, writing, or modifying medical imaging data in DICOM format, extracting pixel …
将文字转为语音音频文件（MP3） - 基于 edge-tts 引擎，支持多语种多音色，输入文字交付音频文件。
Build AI agents using Strands Agents SDK. Suitable for developing model-agnostic agents, implementing the ReAct pattern, creating multi-agent systems, or building production-grade agents on AWS. Trigg…
Narrative generation skill for transforming analytical insights into compelling business stories