Scientific

16,357 mods in this category, of every kind an agent can take. Each one carries what it costs per session, what the scan found, and whether it is the original.

deepmd-finetune-dpa3

193

jinzhezenggroup/computational-chemistry-agent-skills

Skill Claude CodeCodex

Fine-tune a DPA3 model in DeePMD-kit using the PyTorch backend. Use when the user wants to adapt a pre-trained DPA3 model to a new downstream dataset. Supports fine-tuning from a self-trained DPA3 model (.pt checkpoint), from a multi-task pre-trained model, or from a built-in pretrained model downloaded via dp…

not rated 156 +1 4d ago A 131 tokens LGPL-3.0

arxiv-paper-report

194

yofine/skills

Skill Codex

Search arXiv and, when needed, verify external academic sources to update field beliefs and one primary decision through testable propositions, capability frontiers, explicitly labeled mechanism models, technical options, transition theses, five-dimensional maturity, leading indicators, and a restrained bilingual…

not rated 155 +1 2mo ago A 90 tokens

paperlocus

195

littleZ05/PaperLocus

Skill Codex

Reference-aware whole-paper reading and structured research-note generation. Use when the user wants to understand an entire paper, place it in the literature, compare it against core prior work or baselines, or decide whether a paper should be read as a method paper or as a Nature or Science-style evidence-chain…

not rated 155 +1 4mo ago A 65 tokens original MIT

paper

196

sjqsgg/Paperwise

Skill Claude CodeCodex

Academic paper workflow — find, read/annotate (HTML), daily digest, cite. Use when user invokes /paper, needs paper annotation, literature search, citation generation, or daily paper discovery.

not rated 153 7mo ago A 42 tokens original MIT

suggesting-remedies

197

Netflix-Skunkworks/oci-agent

Skill Claude CodeCodex

Invoke this skill when an OCI diagnostic fails or warns and a spec change is needed. Keywords: covariate balance failure, overlap warning, placebo warning ATOTHRESHOLD, trimming extreme propensities changing estimand: ATE → ATT, ATE → ATO adding covariates, dataset insufficiency actor-critic feedback loop, suggested…

not rated 153 +4 2mo ago A SkillSpector: pass 85 tokens original Apache-2.0

thesis-figure-skill

198

0xE1337/thesis-figure-skill

Skill Claude CodeCodex needs its repo

An academic-diagram skill for creating research-paper figures as TikZ/LaTeX code or draw.io XML. TikZ is code that embeds precisely into LaTeX papers, while draw.io XML creates diagrams editable in the draw.io app.

not rated 151 +2 3mo ago A SkillSpector: pass 107 tokens original MIT

ma-manuscript-quarto

199

htlin222/meta-pipe

Skill Claude CodeCodex

Draft and render a meta-analysis manuscript with Quarto using an IMRaD structure and embedded figures/tables. Use when preparing the final paper from analysis outputs.

not rated 151 +1 2d ago A 39 tokens

cesium-mcp

200

gaopengbin/cesium-mcp

Plugin Claude Code

Bundles 1 skill, 3 MCP servers · 34 tokens together

AI-powered 3D globe control for Claude Code — load tilesets, fly to locations, style layers, and query spatial data with natural language.

not rated 150 +1 yesterday A tokens not measured original MIT

limi124/remote-sensing-research-radar

Skill Codex

Track, retrieve, screen, and synthesize research frontiers for geospatial AI, remote sensing big data, and transferable computer vision methods. Use when Codex is asked to search recent papers, arXiv, GitHub projects, Papers with Code, datasets, benchmarks, competitions, or conference/workshop programs in remote…

not rated 149 6mo ago A 124 tokens

good-story

202

Rimagination/good-story

Skill Codex

Use when the user asks to find, sharpen, evaluate, rewrite, or explain the story in scientific or scholarly materials across disciplines, including manuscripts, grants, paper outlines, abstracts, figures, results, discussions, cover letters, research pitches, high-impact writing, journal fit, significance, novelty…

not rated 147 +3 4mo ago A 73 tokens original MIT

cumcm-c-problem

203

liufanshan11/cumcm-c-problem-lfs

Skill Codex

A skill for solving and reviewing C problems in the China Undergraduate Mathematical Contest in Modeling, a university competition where students use data and mathematics to answer practical questions. It covers modelling, algorithms, visualisations and paper writing for the undergraduate C problem.

not rated 147 +1 2mo ago A 142 tokens

autoresearch

204

alfredolopez80/multi-agent-ralph-loop

Skill Claude Code

Autonomous experiment loop: modifies code, runs experiments, evaluates metrics, keeps improvements. Inspired by karpathy/autoresearch + pi-autoresearch + autoexp. Triggers: /autoresearch, 'auto research', 'optimize continuously', 'experiment loop', 'autonomous optimization'.

not rated 146 2mo ago A 61 tokens

kimi3manim

205

HarleyCoops/KimiK3Manim

Skill Claude CodeCodex

Turn math and physics concepts into rendered Manim films.

not rated 144 +1 14d ago A SkillSpector: pass 15 tokens original MIT

stars-we-prefer

206

block/ai-rules

Skill Claude CodeCodex ✓ vendor

Our preferred stars for celestial navigation and astronomical reference.

not rated 144 +2 5mo ago A 14 tokens original Apache-2.0

gmoverid

207

Arcadia-1/gmoverid-skill

Skill Claude CodeCodex

Dependency: ngspice skill (netlist execution, wrdata parsing). Model files are built in — the transistor-models skill is not required.

not rated 143 +3 4mo ago A 247 tokens

paper-search

208

dr-dumpling/paper-search-cli

Skill Claude CodeCodex

A command-line tool for searching academic papers and getting research files. It can work with sources such as PubMed, arXiv, bioRxiv, and Crossref; bioRxiv is a website for sharing scientific papers before formal journal review.

not rated 139 4mo ago A SkillSpector: warn 361 tokens original MIT

graham-a-colditz

209

K-Dense-AI/mimeographs

Skill Claude CodeCodex

Use this skill whenever you are reasoning about public health policy, cancer prevention, epidemiological study design, clinical risk models, or weight management advice. This skill channels the thinking of Graham A. Colditz, epidemiologist at Washington University in St. Louis. Reach for this when evaluating lifestyle…

not rated 139 +3 2mo ago A SkillSpector: pass 126 tokens original MIT

paper-humanizer

210

crabin/paper-humanizer-skill

Skill Claude CodeCodex

Academic text polisher and humanizer for Chinese and English research writing. Removes AI-like patterns while preserving factual accuracy. Use when polishing academic text, reducing AI-generated patterns in papers/theses, improving naturalness of research writing while maintaining data integrity, or enhancing…

not rated 138 +2 7mo ago A 86 tokens

jameslemon2002/research-idea-explorer

Skill Codex

Use when the user wants cross-disciplinary research ideas generated as concise research cards with Title, Abstract, Design, Distinctiveness, and Significance rather than one-shot prompting.

not rated 137 7mo ago A 40 tokens original MIT

hajimi-kun/latex-to-word-workflow

Skill Codex

Load when the user asks to convert an academic LaTeX manuscript, thesis, or report into an editable Word DOCX, adapt it to a Word template, preserve citations or cross-references, or diagnose a LaTeX-to-Word conversion problem. Do not use for PDF-only LaTeX compilation, general Word editing, or DOCX-to-LaTeX…

not rated 137 +2 3mo ago A SkillSpector: pass 81 tokens original MIT

data-check

213

FrontisAI/NatureBench

Skill Claude Code

Acquire and verify data for CNS papers that passed paper-filter. Clones repositories, downloads and organizes datasets per evaluation setting, performs Level 4 deep verification (acquisition integrity, initial state, separability, consistency, per-setting completeness), creates an organized data environment. Updates…

not rated 137 +1 17d ago A SkillSpector: pass 72 tokens original MIT

RConsortium/pharma-skills

Skill Claude CodeCodex

Design group sequential clinical trials for survival endpoints (OS, PFS, DFS) with interim analyses, spending functions, boundaries, multiplicity, and event/enrollment prediction. Triggers on: Phase 3 trial design, sample size/events for survival endpoints, alpha spending, group sequential design, interim analysis…

not rated 137 +8 14d ago A 76 tokens

com-b-diagnostic

215

johnpcutler/change-lenses-and-actions

Skill Claude CodeCodex

Run a structured behavioral diagnosis using COM-B, the Behavior Change Wheel, and BCT Taxonomy v1. Activate when the user describes a stuck or problematic behavior, wants to understand why people aren't doing something, or asks for a COM-B analysis.

not rated 136 +1 6mo ago A 55 tokens original MIT

k-telux/OpticalModeler

Skill Claude CodeCodex

A Japanese-language workflow for building and auditing physically valid optical systems in Blender from two-dimensional optical diagrams and manufacturer CAD models. Blender is software for creating and rendering 3D scenes; CAD files describe engineered parts.

not rated 135 +1 changed 1mo ago A SkillSpector: pass 106 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: