微信扫一扫把 Skill 的源码、资源快照、README、包体和安装信号放进一个可搜索、可筛选的公开目录。
Create or refine TikZ figures for technical papers and slides. Use when Codex needs to add a new diagram, improve an existing figure, align a visual with manuscript notation, or iteratively compile an…
Provides guidance for PyTorch-native agentic RL using torchforge, Meta's library separating infra from algorithms. Use when you want clean RL abstractions, easy algorithm experimentation, or scalable …
>
>-
Retrieve a bounded bundle of relevant external skills from the local skill workspace using vector embedding similarity only.
AI-powered web research assistant that leverages BrowserAct API to supplement restricted web access by searching the internet for additional information. Designed for OpenClaw and Claude Code.
Use when all workflow stages are completed and verified — generates summary report, archives results, and commits
Chunked N-D arrays for cloud storage. Compressed arrays, parallel I/O, S3/GCS integration, NumPy/Dask/Xarray compatible, for large-scale scientific computing pipelines.
Efficient storage and retrieval of genomic variant data using TileDB. Scalable VCF/BCF ingestion, incremental sample addition, compressed storage, parallel queries, and export capabilities for populat…
Trains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies. Use when training models >1B parameters, need maximum GPU efficiency (47% MFU on H100…
UMAP dimensionality reduction. Fast nonlinear manifold learning for 2D/3D visualization, clustering preprocessing (HDBSCAN), supervised/parametric UMAP, for high-dimensional data.
Keep research documentation current with dated supersession and historical preservation.
Prepare journal manuscripts, conference papers, research posters, and grant documents using venue-specific formatting guidance and bundled LaTeX scaffolds. Use when selecting an official template, che…
This skill helps users automatically extract complete Markdown content from any website via the BrowserAct Web Search Scraper API. The Agent should proactively apply this skill when users express need…
Use when an experiment design is approved and needs to be turned into a concrete stage-by-stage execution plan with checkpoint files
Audit and curate a Zotero library — find duplicate DOIs, orphan items missing required tags, propose collection rebinds, identify bloated or under-used collections, generate tag hygiene reports, emit …
Search IEEE Xplore, arXiv, and Google Scholar for papers on a user-specified research topic, score verified candidates, and produce a sourced shortlist of up to ten papers. Use when the user asks for …
Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. Use when reverse-engineering mo…
>-
Use when starting any conversation in a computational science project — establishes harness awareness and checks for existing workflow state
Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexib…
Deep-crawl any website from start URLs, return per-page LLM-ready text/markdown/HTML plus metadata (title, description, author, language, canonical URL, OG) and in-scope outbound links. Use when user …
Set up and run X-VLA model evaluation against BEHAVIOR-1K simulator on a SLURM cluster. Use this skill when deploying X-VLA for BEHAVIOR-1K evaluation, setting up websocket-based policy servers for Om…
Run and manage Google Colab notebooks for Python and ML research