Image

Resolve uncertain person or organization identities across aliases, duplicate records, conflicting sources, incomplete identifiers, or competing profile and media candidates. Use when reliable matching requires contextual corroboration, candidate discovery, historical reconciliation, or explicit ambiguity handling. Do not use for straightforward joins on established identifiers or ordinary photo, image, and metadata tasks without an identity-resolution problem.

Comprehensive design skill: brand identity, design tokens, UI styling, logo generation (55 styles, Gemini AI), corporate identity program (50 deliverables, CIP mockups), HTML presentations (Chart.js), banner design (22 styles, social/ads/web/print), icon design (15 styles, SVG, Gemini 3.1 Pro), social photos (HTML→screenshot, multi-platform). Actions: design logo, create CIP, generate mockups, build slides, design banner, generate icon, create social photos, social media images, brand identity, design system. Platforms: Facebook, Twitter, LinkedIn, YouTube, Instagram, Pinterest, TikTok, Threads, Google Ads.

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, illustrations, diagrams, concept art, placeholder images, or visual representations.

Automated appointment management for beauty salons, clinics, studios, and photo booths. Handles booking requests, calendar sync, conflict detection, reminders, no-show tracking, and waitlist management.

Plan and prompt a stylized 3D animated short for Seedance 2.0 with stable character identities, environment continuity, causal story beats, shot-specific performance, camera, sound, and clip handoffs. Use when a story needs one 4–15 second generation or a longer multi-clip plan; not for photoreal live action, a single still, or generic prompt polishing.

Generate one animated character identity reference from a user-supplied photo when the user invokes profilepic or explicitly requests this conversion. Ask for a missing photo and use actual image generation when available. Not for social account avatars, scene renders, or additional character views.

系列海报工艺：节日/节气/上新/倒计时的成套视觉，统一版式语言，支持一次排产多张与按日替换文案变量。

素材寻源工艺：客户没有图时，从全球免费/开源图库检索合规素材（免 key 通道优先），核对授权与署名、下载入库并产出候选清单。

GEO 信源配图工艺：把六段式答案转成对比表/参数图/清单图，实体锚点与实体卡逐字一致，供知乎/公众号/垂媒/百科配图。

商品海报工艺：主图卖点 + 参数锚点 + 价格/CTA 的 3:4 与 1:1 版式，走 Compositor 视觉工位渲染并带回执。绑定 G-VIS0..G-VIS4。

朋友圈发图工艺：1:1/3:4 单图与 3/6/9 宫格套图，含统一色板、序号角标与私域 CTA，可直接转发投放给老客/潜客。

促销活动图工艺：大促/节日/上新横幅与落地页 KV，含价格锚点、倒计时位与权益清单，尺寸覆盖 16:9/3:4/1:1。

商品图精修工艺：Vision 去背、边缘精修、统一色调（曝光/色阶/曲线/渐变映射）、背景虚化与尺寸规范，输出可投放的高清主体图。

Optimize a Google Business Profile (GMB, Google My Business listing) with the Reach MCP server. Finds what the profile is missing (description, hours, services, links, attributes, categories), previews each fix with before and after, and writes one approved change at a time, then reads it back from Google. Use when someone asks to optimize, complete, audit or fix their Google Business Profile, improve their GBP for local SEO, or update hours, description or services.

Use when an answer depends on where something is or how it looks on a screen - "where is X", "how do I do Y in this app/site", explaining a UI or a screenshot the user sends, reporting a bug or writing a ticket (Jira, GitHub, Freshdesk, Slack) about something visible, showing before/after of a change, writing a step-by-step guide, or any reply that would otherwise say "top right, under the..." in words. Also when the user says "ainotate", "show me", "take a screenshot", "annotate".

Helps homeowners and renters plan a new look for their home, yard, or a specific room. Use it for exterior colors (siding, front door, shutters, roof), landscaping and patios, interior redesigns, paint and cabinet colors, virtual staging of an empty room, or clearing out clutter. It gives a short design brief, then a Roomvana (roomvana.ai) link with the right options already picked, where the user uploads a photo of their own space and sees it redesigned.

Give your agents the power of the Hugging Face ecosystem

One-shot ordering skill for the Weshp cross-border store. Use this skill when the user wants to "search products/price", "add to cart/view cart", "place order/buy", "check/cancel order", or "pay/check payment status" (Chinese intents also trigger this skill: "查商品/搜商品/看价格"、"加购物车/看购物车"、"下单/买某个商品/创建订单"、"查订单/取消订单"、"支付/查支付状态"). It drives weshp-cli through the full flow of product search → cart → ordering → payment.

The open-source AI research workbench for scientific research and agent workflows. Local-first, model-agnostic desktop app with extensible skills, MCP tools and connectors, Python/R execution and traceable artifacts for reproducible research on macOS, Windows and Linux.

Kaggle-first end-to-end competition workflow for scored submissions. Use when Codex must run Kaggle or competitive ML workflows through scored submission, including code competitions, validation, metrics, policy-safe public notebook/discussion intel, tabular/text/image modeling, tuning, ensembling/stacking, proactive multi-notebook architectures, producer notebooks that train models and export private Kaggle artifact datasets, downstream consumer notebooks, Kaggle GPU offload, kagglehub access,

Create evidence-aware, interactive visual explainers as self-contained offline HTML. Use when a user asks to explain a concept, repository module, engineering tradeoff, or incident with a diagram, walkthrough, ELI5 treatment, data/request trace, failure view, or teach-back. Do not use for a plain short answer, ordinary prose rewrite, generic website implementation, or unsupported claims presented as facts.

开源中文配图技能 + IP 角色库。用"挑认知锚点 → 现编隐喻 → 反 PPT 自检"的方法,为中文深度文/方法拆解生成由固定角色出演的正文配图(不是通用插画,不是样式库选风格)。自带 31 个原创 IP 角色(手绘线稿 15 + 谐音梗 meme 16),配图时按文章调性选一个角色出演,也可自建角色。当用户说"配图""正文配图""IP 配图""给这篇配图""隐喻配图""选个角色配图""配图 shot list"时使用。

Multi-agent research that keeps bringing gifts back — like cats! Dispatch multiple agents to research a topic in parallel, compile findings, and iterate on new discoveries.

The only memory skill that watches on its own. No database. No vectors. No manual saves. Just an LLM observer that compresses your conversations into prioritised notes, consolidates when they grow, and recovers anything missed. Five layers of redundancy, zero maintenance. ~$0.00/month (using free-tier models). While other memory skills ask you to remember to remember, this one just pays attention.