Scan to join WeChat groupBrowse curated skills with source links, package snapshots, README assets and install signals in one calm, searchable catalog.
Compiles any research input — PDF papers, GitHub repositories, experiment logs, code directories, or raw notes — into a complete Agent-Native Research Artifact (ARA) with cognitive layer (claims, conc…
Use when targeting Art History (the Association for Art History journal) or deciding whether a theoretically engaged art-history manuscript fits this venue. Encodes the journal's fit as a critically a…
Use when executing and reporting the analysis for an Administrative Science Quarterly (ASQ) manuscript — qualitative coding and data-to-theory construction, or quantitative estimation and robustness. …
PyTorch library for audio generation including text-to-music (MusicGen) and text-to-sound (AudioGen). Use when you need to generate music from text descriptions, create sound effects, or perform melod…
Orchestrates end-to-end autonomous AI research projects using a two-loop architecture. The inner loop runs rapid experiment iterations with clear optimization targets. The outer loop synthesizes resul…
Create an academic presentation as a LaTeX Beamer source and reviewed PDF with an original theme. Use when the requested deliverable is a conference, seminar, or lecture deck in Beamer. Not for PowerP…
Define benchmark runs and log outcomes with consistent metrics, acceptance criteria, and reproducible artifact references.
Compare a project .bib against a Paperpile project/topic folder to find uncited papers or unfiled entries. Use when the user asks to compare a project .bib against a Paperpile project/topic folder to …
Autonomously improve a real artifact (code, training recipe, agent harness, data pipeline, prompt) against an objective and an evaluator, using Hypothesis Tree Refinement (HTR) from the Arbor paper. U…
Use when finding, comparing, reading, or monitoring arXiv papers, including requests for abstracts, citation graphs, original LaTeX, section-level technical details, or literature reviews.
Core Python library for astronomy and astrophysics workflows that need Astropy APIs, including units/quantities, coordinates, FITS I/O, tables, time systems, WCS, and cosmology. Use when implementing …
Rewrite AI-assisted academic drafts into author-specific, evidence-grounded prose. Use when users need to diagnose machine-like writing, strengthen claim-evidence alignment, or revise AI drafts for ac…
Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. Use when deploying large models (7B-70B) on limited GPU memory, when you need faster inference…
Deploy BEHAVIOR-1K (OmniGibson + Isaac Sim) on RTX 5080/50-series Blackwell GPUs. Use this skill whenever setting up BEHAVIOR-1K, OmniGibson, or Isaac Sim on RTX 5080, RTX 5090, or any Blackwell-archi…
>-
Extract citations from a PDF and generate a validated .bib file. Use when the user asks to extract citations from a PDF and generate a validated .bib file. Reads the PDF, identifies referenced works, …
Infer gene regulatory networks (GRNs) from gene expression data using scalable algorithms (GRNBoost2, GENIE3). Use when analyzing transcriptomics data (bulk RNA-seq, single-cell RNA-seq) to identify t…
Use when sharpening the theoretical contribution and the "so what" for an Administrative Science Quarterly (ASQ) manuscript once results exist. Frames the contribution; it does not develop the underly…
M-estimation, influence functions, and semiparametric efficiency theory for causal inference
Design patterns for building autonomous coding agents. Covers tool integration, permission systems, browser automation, and human-in-the-loop workflows. Use when building AI agents, designing tool API…
Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support
AI operational modes (brainstorm, implement, debug, review, teach, ship, orchestrate). Use to adapt behavior based on task type.
Search scientific papers and retrieve structured experimental data extracted from full-text studies via the BGPT MCP server. Returns 25+ fields per paper including methods, results, sample sizes, qual…
>