鲜核桃
Six Degrees of Connection
Enter the names of two real people to find the real interpersonal relationship chain connecting them through the fewest intermediaries, using bidirectional research and timeline-overlap checks. Each link is labeled with relationship strength (strong/medium/weak) and verifiable sources. The process first produces copy that can be proofread; after you confirm it, a vertical, shareable long-form image is generated. If the chain cannot be completed within six degrees, the result will not be forced: it will honestly state the minimum number of links and explain that it exceeds the six-degree limit. If the input includes legendary, mythical, or fictional figures (such as He Xiangu or Sun Wukong), no interpersonal chain or image will be created. Instead, the Skill will produce an explanatory document labeled “Not a Six-Degrees Chain.” International pairings follow three additional rules: anchor each person to their original-language name first, to avoid treating transliteration variants as different people; exclude text-based media links; and exclude widely circulated anecdotes that appear only in commemorative articles. Image generation follows strict version control: for text-heavy images, “blank background + text layer” is preferred to avoid typos, and only the final proofread version is saved; rejected intermediate versions are not added to the canvas.
Work Update Coach
A reporting coach based on a two-way, win-win communication model. It supports four key reporting goals—showcasing results, seeking help with problems, managing progress and risks, and aligning with strategy—by using conversation to organize facts and perspectives, uncover root causes and cross-domain solutions, and produce highly persuasive reporting documents, with the option to convert them to Slides. It also captures your style and builds a profile of your leader.
Skill Judge
Enter the name, link, or instructions for the AI Skill to evaluate, and run an evidence-based initial quality review in realistic use scenarios. Keep the six-question quick test (4 positive, 1 negative, and 1 ambiguous), and separately verify automatic selection and execution after explicit invocation; success through manual invocation does not count as successful automatic triggering. Use a five-dimension direct score: triggering 30 / execution 25 / cost 15 / robustness and boundaries 15 / safety 15. Distinguish between evidence from this test, historical runs, static checks, and items not verified. Do not provide an overall score or star rating when key evidence is incomplete. Assess safety based on data access, external transmission, and operational authorization—not on the author's identity or endorsement. Block recommendations in cases of serious privilege overreach. Produce a one-page, conclusion-first report showing the tested scope, unverified items, and priority improvement suggestions, and automatically create a record. Say “deep review” to add independent repeat testing and source verification; clarify the budget before execution. This Skill only evaluates and makes recommendations; it does not automatically modify the Skill being evaluated. Suitable for quality checks of self-created Skills, rechecks of installed Skills, and pre-installation screening of marketplace Skills; results from the six-question test do not constitute comprehensive certification.
Skill Icon Generator
Enter a skill name and one-sentence use case. Roll a four-dimensional dice to set the visual direction, then generate a 1:1 skill avatar icon first. Once you approve it, it becomes the sole anchor image for the entire workflow. The cover illustration (16:9) is generated with the anchor image as a reference, while the header image for the mobile promotional graphic (9:16) uses the original cover illustration directly without model redrawing to prevent visual drift. The information section is generated separately and then assembled. The three-piece set maintains strictly consistent styling, colors, and outlines. Designed specifically for skill avatar slots, cover slots, and mobile promotion. When you only need a single icon or already have established visual guidelines, the three-piece workflow will not start. If the environment does not support automatic assembly, you will first be asked whether you want a header image; if you say no, the result will be a promotional graphic containing only the information section.
B&W Depth Video Maker
Convert any video into a black-and-white (grayscale) depth video that works directly with libTV (LiblibAI’s node-based AI video tool): near areas are bright, distant areas are dark, and depth remains temporally consistent across frames. Drop it into depth-control nodes and use it right away. Use this when you need to prepare depth video assets for libTV or encounter errors such as unrecognized depth nodes, excessive resolution, or failed video generation.
ImageSnowland Tibetan Blessings
Enter a Chinese blessing message and choose a third language. Using a fixed style reference image, this Skill generates a 9:16 vertical Tibetan blessing card. Share auspicious wishes with friends around the world.
ImageChinese Art Seal
Chinese art seal design. Create name seals, blessing seals, collection seals, or brand and studio seals. If you do not have a Chinese name, you can choose one first. After confirming the inscription, layout, font, seal shape, and background, generate visual drafts in red-script and white-script styles. Bilingual Chinese art seal design for personal names, blessings, collections, brands, and studios.
Photo to GIF Emoji
Turn an image or reference GIF into a natural, seamless GIF emoji or sticker. The number of key images depends on the complexity of the action. After you confirm the keyframe visuals, the skill uses the YouMind desktop app to compile the animated GIF. ⚠️ Requires the YouMind desktop app.
Cartoon Self-Intro Video Maker
Upload your photo and self-introduction script to automatically create a cartoon digital twin and generate a cartoon self-introduction video using a fixed three-part script template: medium shot, close-up, and wide shot, with a flexible order, hard cuts, and fixed camera positions. Visual styles come in two tracks: standard (Pixar 3D / Shanghai Animation Film Studio) and distinctive (Keith Haring, Romero Britto, silhouettes, claymation, ukiyo-e, Tim Burton, and other niche art styles). The Skill automatically recommends a tone—serious, humorous, or warm—and can add narration in your own voice, either from an uploaded recording or a voice cloned in YouMind. Ideal for job applications, social media profiles, annual meetings, podcasts, and other self-introduction scenarios. YouMind handles the entire workflow, although video generation can be a little slow. Don’t underestimate how simple this Skill looks: in general, these workflows can’t be completed end to end in YouMind without it. Technical challenges—such as real-person photos not being accepted by the model as references, voice files not being usable as model references, and video-generation tasks timing out—have all been addressed in this Skill, saving you a substantial number of credits.
Script Forge Workshop
A script skill for producing one fruit animation episode per day: enter a short synopsis set in the Fruit World and receive a 30-second episodic storyboard script ready for video generation, including release copy, AI voice prompts, and BGM recommendations. Each script also ends with a fixed “empty-shot video prompt module” containing text prompts only; it does not generate empty-shot images or videos. Strictly follows the worldbuilding in the “Fruit World · Setting Handbook” while keeping credit usage light. After the script is produced, the companion “Daily Fruit Animation Video Generation Workflow” skill provides reference-image prompts, video-generation parameters, and the finished video.
Paper Craft Science Videos
Turn any science topic into a short-video production plan in a paper-craft stop-motion style: from understanding the brief, creative direction, and character, scene, and set design to visual previews, prompts for single images, image series, and image-to-video generation, storyboard pacing, camera moves, transitions, sound, and narration, followed by a final review. The entire process uses miniature paper-sculpture scenes with a handmade stop-motion feel, with each stage confirmed step by step through selection cards. —An iterative upgrade of a non-original Skill.
VideoDaily Fruit Animation Workflow
An end-to-end production workflow for daily animations in the “Fruit Micro World” series, using a **six-step decoupled process with confirmation at each step**: ① organize the fruit knowledge card → ② story outline → ③ script → ④ production plan → ⑤ asset list and prompts → ⑥ video storyboard script. Each step produces exactly one document for that step, which is submitted for user confirmation before moving on; documents are never generated in bulk, and images or videos are never created ahead of schedule. The workflow strictly follows the material transformation, silhouette, naming, and image-quality standards in the “Fruit World · Style Guide,” with the primary goals of producing one episode a day, keeping it lightweight, saving credits, and creating finished videos quickly.
ImageCharacter Foundry
Generate character sheets and three-view image-generation prompts for “Fruit’s Microscopic World,” following all of the project’s visual guidelines. Use finalized characters as master style templates for consistent generation, then review the results against a checklist. This skill can help avoid unnecessary credit waste during image generation.
Scene Forging Workshop
Transform the natural material of fruit into architecture, terrain, and civilizations. Generate image prompts for surreal miniature worlds and bring them to life. Freely combine fruit type, season, setting, and world name—the core concept is material transformation: everything in the scene comes from that fruit. For serialized or series scenes, the setting tier is determined by value (premium → palace fortresses, high-quality → towns and manors, standard → cottages and markets, vegetable-grade → mountain landscapes and farmland). Texture defines the material language only; it does not determine the tier.
Blender MCP Installation Guide
Guides users from scratch to install Blender, the BlenderMCP plugin, and the uv package manager, and configure the MCP server, enabling AI to directly control Blender. Built for users who are completely unfamiliar with the command line, it includes troubleshooting for 6 common issue categories. The main Skill automatically invokes this when it detects MCP is unavailable on first run.
Cycles Black Block/Line Fix
Expert at troubleshooting black blocks and black lines in Blender Cycles renders. Uses a 6-step process that starts with the cheapest fix and escalates as needed. AI can execute repair scripts directly via MCP. Diagnoses three root causes: coplanar surfaces (z-fighting), normal issues, and non-planar faces. Automatically called by the main Skill when black blocks are detected.
Animated Video Sticker Merch
Upload a character reference image and character description. The Skill will automatically plan a 5–7-sticker set and use AI to generate the sticker artwork, with support for three use cases: physical adhesive sticker printing, WeChat sticker packs, and general digital sharing. For text, choose between AI-generated Chinese dialogue or blank spaces for adding text later in Photoshop. Includes printing and publishing guides.
VideoAI Video Production Workflow
AI video production pipeline: Project assessment and budget tiers → Pre-production completion → Dynamic storyboards and asset lock-in → Keyframe image generation and image-to-video → Post-production compositing and final upscaling. Step-by-step control, two-stage review, and credit-efficient finished videos; generate within YouMind or export a resource package for production on other platforms; all characters, scenes, and audio use the user's own content, organized into reusable, locked prompt assets and archived in three folder categories: script, art, and sound.
Spoken 3D Scene Modeling
Through Blender MCP, directly control Blender to model and validate scene space, while iteratively refining AI image-generation prompts. For users who don't know 3D software, the AI agent handles all modeling, rendering troubleshooting, lighting validation, and prompt engineering. The ultimate goal is to keep scenes consistent when creating 3D animation videos: build the scene in Blender, control the camera, and pass the camera reference to the video-generation model.
Tencent Docs to H5
Convert Tencent online documents into deployable mobile H5 pages. Designed for non-technical users, it supports the complete workflow from requirement clarification, data extraction, page development, self-verification to deployment guidance. Suitable for scenarios such as enrollment promotion, product introductions, event pages, etc. Demo: https://exam.reactmobile.cn/jzhx/index.html
SlidesLayered Presentation Master
Generate a 10-page narrative Slides deck for any product or solution, tailored to decision-makers at different levels. Automatically match the audience’s messaging, color scheme, and narrative structure. One solution, layered persuasion—with flexible options for expansion.