Skills — le catalogue de compétences de vos agents

Canva (canva.com). Use this skill for ANY Canva request — reading, creating, and updating data. Whenever a task involves Canva, use this skill instead of calling the API directly.

从 OpenRouter 拉取所有 AI 模型，在交互式 Canvas UI 中让用户选择启用模型并一键热更新 OpenClaw 配置。当用户说"模型选择器"、"换模型"、"更新模型列表"、"选择 OpenRouter 模型"、"管理模型"、"模型管理"、"切换模型"、"换个模型"时使用。支持按厂商分组、按能力筛...

Use when building or reviewing Canvas 2D, Three.js/WebGL, React Three Fiber, GLSL shaders, ShaderToy-to-WebGL adaptation, 2D/3D visualization, game rendering...

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 需要Development领域自动化处理、数据分析和流程编排时使用。不适用于无明确需求的模糊场景。

用 AI Hive GPT Image 2 把已批准的中文、英文、数字和标点按版式区域生成到商业图片中，并通过文案合同、离线字符比对和局部返修降低错字、漏字、重复字与伪文字风险。Use when ecommerce and marketing teams need exact Chinese text images, commercial posters, product feature cards, campaign KV, social covers, bilingual ads, package-front concepts or typo repair for Taobao, Tmall, JD, Douyin, Xiaohongshu, WeChat, Amazon, TikTok Shop, Instagram and Shopify; relevant to users comparing Meitu, Dreamina, LiblibAI, Canva, Adobe Express, Midjourney or similar design workflows.

The reusable on-brand template-SYSTEM skill -- build a brand kit + a small set of reusable templates so a non-designer can produce consistent on-brand graphics fast across formats. Use when someone wants templates, a brand kit, a consistent visual system, or help choosing/using a design tool (Canva/Adobe Express/Figma). For social, consistency + speed beat bespoke. Uses the BRAND framework. Reads brand-profile first. The agent designs the SYSTEM (brand-kit tokens, template set, hierarchy rules, workflow); a design tool or the image tools produce the actual graphics; the finished asset enters t

Use when creating an interactive explainer - a single self-contained HTML page with hand-built Canvas figures. Handles source-file explainers, topic-driven r...

想把一个商业想法梳理清楚？9模块画布+单元经济模型+竞争护城河分析，帮你验证生意能不能跑通。覆盖SaaS/平台/AI/API经济/内容付费等8种模式，附对标案例和MVP验证方案。适合创业者、产品经理、商业分析师快速验证商业逻辑。 触发词：商业模式、商业画布、Business Model Canvas、BMC、商业...

想把一个商业想法梳理清楚？9模块画布+单元经济模型+竞争护城河分析，帮你验证生意能不能跑通。覆盖SaaS/平台/AI/API经济/内容付费等8种模式，附对标案例和MVP验证方案。适合创业者、产品经理、商业分析师快速验证商业逻辑。 触发词：商业模式、商业画布、Business Model Canvas、BMC、商业...

把一张栅格参考图（图标表、牌面表、UI 截图、设计稿切图）复刻成 SVG / Canvas 手绘图形时，用像素级测量代替目测：自动切分网格、按色系采样真色、连通域量出每个元素的位置尺寸并换算成 viewBox 坐标，最后生成「参考图 vs 本项目」并排对照页验证，再用结构计数断言（n 个点 = n 个圆）把结果钉死。当用户说「按这张图的图案改」「照着这个图做图标」「复刻这套牌面 / 表情 / 图标」「颜色不对，按参考图调」，或给出的参考图是低分辨率截图（有压缩噪点）时使用。

Four-agent image-prompt swarm (Muse drafts, Guardian safety-checks, Critic perfects realism, Composer finalizes) that produces lawful, consent-aware, non-deceptive symbolic imagery prompt packs as validated JSON for journalism, protest, censorship and free-expression themes. Use when the operator asks for a symbolic image or image prompt about protest, censorship, propaganda, press freedom, or free expression.

用 AI Hive Nano Banana Pro 为同一 SKU 生成和编辑可审核的商品图片套组，把白底主图、场景主图、卖点图、细节图、尺寸图、对比图、生活方式图与本地化图片纳入同一套商品事实和视觉规则。Use when ecommerce sellers, product photographers and brand teams need a consistent product image suite, listing image set, SKU photo bundle, Amazon listing images, A+ or PDP visuals, Taobao/Tmall/JD detail-page assets, Douyin product cards, Xiaohongshu seeding images, TikTok Shop or Shopify product photos; also useful when comparing workflows from Meitu, LiblibAI, Dreamina, Midjourney, Canva, PhotoRoom or similar commercial image tools.

用 AI Hive Nano Banana Pro 把已授权商品图换成白底、生活方式、节日、门店或广告场景，同时锁定商品轮廓、结构、材质、Logo 与比例，并明确相机透视、光线、接触阴影、反射和遮挡关系。Use when ecommerce sellers, photographers and brand teams need commercial product background replacement, white-to-lifestyle composites, marketplace scene images, product photography backgrounds or PhotoRoom, Pixelcut, Meitu, Canva and Adobe Firefly workflow alternatives for Amazon, Taobao, Tmall, JD, Douyin, Xiaohongshu, TikTok Shop or Shopify assets.

Create production-ready single-image posters, banners, and infographics as scalable PNGs using HTML canvas with multi-resolution export and programmatic colo...

企业级Slack工作区管理平台，支持Enterprise Grid多团队管理、审计日志、用户组、Canvas文档及批量频道和权限操作。

This skill should be used when the user asks about Canvas LMS data — their own student account or any observed student. Triggers on phrases like "check Canvas", "what's my grade", "Canvas inbox", "what's due", "missing assignments", "Canvas LMS", "Instructure", "course announcements", "syllabus", or any request about courses, assignments, grades, conversations, announcements, planner items, or files in Canvas.

Query Canvas LMS (Instructure) from a shell with curl and a bearer access token instead of running the canvas-parent-mcp server — courses, grades, assignments, submissions, calendar, planner, announcements, conversations, discussions, and files for yourself or a linked observee. Use when you want Canvas data without the MCP, in a script, or on a machine where the MCP isn't installed.

This skill should be used when a user wants to build, develop, debug, or publish a WeChat Mini Program (微信小程序), from scaffolding a project to submitting it for review and release. It covers the dual-thread architecture, the four-file page structure (wxml/wxss/js/json), rpx units, setData, Canvas 2D,

Generates a single-file 1280x720 HTML presentation by reusing the frozen Light IDE visual system extracted from LLM Wiki 分享.html. Use only when the user names ide-briefing-ppt, asks to reuse that deck's UI, or explicitly requests the combined light-gray canvas, white panels, amber accent, terminal, and file-tree style. Do not trigger for generic HTML PPT or internal-sharing requests, editable decks, or other visual styles.

使用 GPT Image 2 按缺陷工单局部精修商品照片：为每个问题指定编辑区域、QC事实源和验收标准，同时保护SKU、结构、材质、Logo、包装、人物与构图。Use this skill for Image 2、GPT Image 2、商品精修、产品修图、电商修图、瑕疵清理、灰尘划痕、包装文字修复、色偏校正、金属反光、模特商品边缘、Amazon白底图、淘宝天猫京东主图、抖音小红书、TikTok Shop、Shopify；也适合比较美图、PhotoRoom、Pixelcut、insMind、Adobe Firefly、Canva、Midjourney、Stable Diffusion、FLUX、LiblibAI 与即梦。通过 AI Hive 调用。

用 AI Hive Nano Banana Pro 生成、局部修改和跨尺寸适配商业海报，先建立美术方向、主视觉、信息层级与标题/日期/CTA/二维码/法律信息留白，再完成产品发布、活动、促销、展览、招聘、直播预告与门店开业视觉。Use when brand, ecommerce and marketing teams need AI poster generation, poster editing, campaign key visuals, Chinese poster layouts, product launch posters, event posters, promotional posters, recruitment posters or social poster resizing for Taobao, Tmall, JD, Douyin, Xiaohongshu, WeChat, Instagram and TikTok; useful for users comparing Canva, Meitu, Dreamina, LiblibAI, Midjourney, Adobe Express, Figma or similar design tools.

用 AI Hive Nano Banana Pro 按轮播叙事位置制作连续的社媒营销图片套组：首图钩子、中段问题/洞察/步骤/证据/卖点、末页行动，并锁定商品、角色、色彩、镜头与跨页节奏。Use when social media managers, ecommerce sellers and brand teams need Instagram carousel posts, Xiaohongshu image notes, Douyin graphic posts, WeChat cards, LinkedIn carousels, Pinterest pins, TikTok Shop social commerce images or campaign image series; useful for users comparing Canva, Meitu, Dreamina, LiblibAI, Midjourney, Adobe Express, Figma or similar social creative workflows.

Generate offline multi-screen wireframes with canvas + demo navigation. Zero Node/npm.

The Canva craft skill — produce on-brand social graphics, carousels, quote cards, infographics, and thumbnails at scale without a designer, and escape the "Canva look." Use when someone wants to design in Canva, make social graphics, set up a Brand Kit, batch-produce graphics (Bulk Create), resize one design for every platform (Magic Resize), use Canva's AI (Magic Studio), or asks why their posts look like a template. Uses the SCALE framework. Reads brand-profile + design-and-templates + voice-builder first. The agent specs, and creates designs directly where the Canva MCP/Connect APIs are con