Loading...
Loading...
Found 37 Skills
Run the TikSpyder tool to collect TikTok data — search by keyword, username, or hashtag, download videos, extract keyframes, and export structured data. Use this skill whenever the user wants to collect TikTok data, search TikTok profiles or hashtags, search TikTok videos, download TikTok content, run tikspyder, or launch the TikSpyder Streamlit interface. Also trigger when the user mentions data collection from TikTok, even if they don't say "tikspyder" by name.
Analyze video files using ffprobe, mp4dump, and jq. Use when investigating video samples, keyframes, MP4 box structure, codec info, packet timing, or debugging video playback issues.
Convert short-drama storyboards and frozen keyframes into directly copyable video prompt Markdown, and optionally write timeline soundtrack/theme song intent on request. Use when the user mentions text-to-video/image-to-video motion, character performance, camera movement, lip sync, environment motion, shot duration, start/end states, converting storyboards to video prompts, or writing soundtrack prompts; it does not generate media, create lyrics, or alter storyboard boundaries.
Reviews source analysis, story, script, visual design, image prompts, storyboards, frozen keyframes, video prompts, and existing media in short-drama projects. Used when the user asks to "review/check script", "check assets or continuity", "check image/video prompts", "check source analysis", "review template feel", or "calibrate the project based on production observations". Only writes review issues, conclusions, and revision requirements; it does not modify source files on behalf of the owner.
Turn a chemical reaction into a self-contained microscopic 3D interactive demonstration webpage: The left/top section features a Three.js interactive molecular animation (drag the slider to view bond breaking, bond forming, and atomic recombination with step-by-step highlighting), while the right section includes KaTeX reaction equations + step-by-step explanations + atom conservation counting + optional energy-reaction progress curves. Three entry methods are supported—given text reactions/equations, random question generation, and demonstration after image upload and recognition. It covers combustion, combination/decomposition/single displacement/double displacement reactions, redox reactions (electron transfer visualization), and organic reaction mechanisms (esterification and other reactions involving catalysts and transition states). It is precisely driven by sympy: automatically balance equations, verify atom conservation and atomic mapping, deduce bond breaking/forming, ensuring consistency between answers and geometric models. Two built-in engines are available with automatic selection: morph (atomic deformation, demonstrating atom conservation) and mechanism (mechanism keyframes, demonstrating catalysis/transition states). Hybrid geometry: uses a self-built VSEPR molecular library by default; if RDKit is installed in the environment, it can generate conformations from SMILES (never installed automatically). Other agents can also call this skill to generate such webpages. Its form is parallel to edu-solid-geometry / edu-analytic-geometry, but uses Three.js + KaTeX to demonstrate molecular reactions. Trigger words: chemical reaction, microscopic demonstration, molecular animation, combustion, methane combustion, hydrogen combustion, water electrolysis, redox reaction, electron transfer, esterification reaction, reaction mechanism, bond breaking and forming, atom conservation, mass conservation, chemical equation balancing, solve this chemical reaction, generate a random chemical reaction, the chemical reaction in this image; chemistry reaction, microscopic/molecular animation, combustion, electrolysis, redox electron transfer, esterification mechanism, bond breaking and forming, atom conservation, balance equation, interactive chemistry reaction page.
Motion / animation context for the `use_figma` MCP tool — animating Figma nodes via manual keyframes, animation styles, easing, and timeline duration. Load alongside figma-use whenever a task involves adding, editing, or inspecting animation on a node.
Generates and edits SVG logos, icons, and graphics. Use when creating SVG files, designing logos or icons, writing path data, optimizing SVGs, building icon systems, animating SVG elements, or modifying existing vector graphics. Covers path commands, shape primitives, styling, accessibility, gradients, masks, sprites, optimization, and animation (CSS keyframes, GPU acceleration, staggering, easing, SVG-specific techniques).
The Luma Dream Machine craft skill — generate cinematic AI video shots (Ray3: text-to-video, image-to-video, keyframes, character reference, Modify V2V, HDR) with draft-first economics and the right rights. Use when someone wants to generate video with Luma/Dream Machine/Ray3, animate a still into video, keep a character consistent across shots, restyle real footage, control credit burn, pick a Luma model or plan, or build a multi-shot AI brand film. Uses the DREAM framework. Reads ai-video + brand-profile + short-form-video-script first. The agent writes shot briefs and can drive the API where connected; the HUMAN judges every clip; WoopSocial publishes. Generations are shots not films (no native audio); Draft Mode first, HDR only for finals; verify tiers in-app. Never use unpermitted likeness, generate fake-event footage, or state credit rates as fact. Distinct from ai-video, veo-3/kling/runway, flux (the stills this animates), heygen/synthesia, and capcut.
Create complete director-grade storyboard production packages for Image 2 and SceneDance/Seedance video generation. Use when the user provides a script, scene idea, ad concept, short drama, long-form drama, period drama, sci-fi animation, product video, or asks for 分镜图, 剧本分镜, SceneDance/Seedance 视频素材, Image 2/Img2 prompts, character consistency sheets, continuity bibles, shot cards, clip references, keyframes, Jianying/CapCut edit lists, or image-to-video production assets.
Use when animating 2D game art with Scenario: character walk cycles, idle or attack animations, sprite sheets, animated GIFs, frame-by-frame pixel art animation, VFX loops such as fire or smoke, looping a sprite seamlessly, animating an existing character image, a full animation sheet from one prompt, extracting animation frames from a generated video, or slicing a sprite sheet into engine-ready frames for Unity, Godot, or Unreal. Keywords: spritesheet, keyframes, frame grid, GIF.
The “Archival Collage” visual style + a method for chaining start and end frames through keyframes. Full-bleed ivory paper, monochrome black-and-white printing, and a single dark brick-red accent. First generate a sequence of distinct reference images, then use each adjacent pair as the start and end frames to create a shot, with transitions that align perfectly. No specific model is required; any video tool that supports start and end frames will work. Use this when the user wants to create a short video in the archival collage/paper collage/editorial design style, or wants to build a coherent storyboard using the start/end frame method.
Add particle effects (smoke, fire, sparks, magic, glow, dust, snow, drips, bubbles, bursts) to Blockbench models with MCP tools. Covers Bedrock/Snowstorm particle JSON, presets and design knobs, locators, particle keyframes on animations, Blockbench's Animate-mode preview, and delivery to Bedrock resource packs (client entity particle_effects) and GeckoLib, plus fallbacks for glTF, Java block and Hytale targets that cannot carry particles. Use when a model needs an emitter, VFX, particle effect, locator, Snowstorm file, particle_effects keyframe, or effect polish in a deliverable.