Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Use as the docs-priming stage of the Butterbase journey, immediately after journey-preflight and before the first build stage. Reads the plan to discover which capabilities the app uses, calls butterbase_docs once per relevant topic, and caches a summary the build stages can re-read.
Generate a high-quality deep-reading note for a single paper and write it into an Obsidian-style vault. Use when the user gives a paper title, DOI, URL, arXiv ID, Zotero item, or local PDF and wants a polished Markdown note with strong structure, evidence-based analysis, and figure placeholders.
Convert EmbodiedGen URDF assets to simulator-specific formats (USD/MJCF/URDF) using embodied_gen.data.asset_converter APIs. Use this skill whenever users ask to export assets for IsaacSim, MuJoCo, Genesis, IsaacGym, PyBullet, or SAPIEN, batch-convert URDF assets, or choose the correct converter/source_type per simulator.
Retrieve existing EmbodiedGen assets from a configurable dataset index CSV by natural-language descriptions and return matching `.urdf` paths. Use when users describe an asset they want, ask to find one or several existing URDF assets, or need a fast lookup over the local asset index instead of scanning folders manually.
Create reusable black-background white-text opening animations for new videos. Use when the user asks for "黑底白字开场", "纯黑加白字", "白色文字逐渐出来", "一个个字出来", "打字效果", "打字音效", "字体变化开头", "opening title animation", "kinetic text opener", or a short black-and-white intro before a HyperFrames, Remotion, ffmpeg, SaaS/product, tutorial, commentary, or course video. This is for original opener creation, not pixel-level reference matching.
Motion-first AI video director for topic-to-video creation. Use when the user gives a theme, idea, article, script, or brief and wants AI to freely create a real animated video instead of a PPT/slideshow-style explainer; when deciding visual metaphors, motion grammar, scene beats, component choices, generated image needs, HyperFrames/Remotion implementation strategy, and anti-PPT QC.
Analyze a public or local reference video, isolate a time range, deconstruct its layout, motion, timing, and transitions, then build an original verified motion replica with reusable templates and final MP4 QC. Use when the user says 复刻这个视频效果, 参考这个视频做同款动效, 拆解前 N 秒, 还原方框/连线/卡片动画, or provides a video or URL as a motion reference rather than asking to copy its footage or script.
Analyze, recreate, align, and verify reference-video motion. Use when the user asks to recreate, copy, match, align, pixel-align, or compare a video; when a HyperFrames or Remotion remake is judged not aligned; when fixed reference playback and reusable motion components must be separated; or when delivery needs full-frame runtime, render, decode, boundary, timing, and archive evidence instead of sampled screenshots alone.
Audit documentation hygiene for the let-go docs/ tree — find stale or unverified docs, dangling or one-sided supersession links, duplicate authoritative-for claims, and docs missing from the README index. Use when asked to check doc freshness, run doc triage, audit docs/, find stale docs, or verify documentation hygiene before a docs PR.