Scientific

15,055 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.

kimi3manim

169

HarleyCoops/KimiK3Manim

Skill Claude CodeCodex

Turn math and physics concepts into rendered Manim films.

not rated 142 +1 1mo ago A 15 tokens original MIT

中医

170

YuanZHAO321/TCM.Skill

Skill Claude CodeCodex

A Chinese-language reference skill for traditional Chinese medicine, including its theories, diagnostic approaches, herbs, formulas, and treatment principles.

not rated 139 +3 2mo ago A 889 tokens

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 138 +1 3mo ago A 124 tokens

paperlocus

172

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 138 +5 2mo ago A 65 tokens original MIT

section-11

173

CrankAddict/section-11

Skill Claude CodeCodex

Evidence-based endurance coaching protocol (v11.63). Use when analyzing training data, reviewing sessions, generating pre/post-workout reports, planning workouts, answering training questions, or giving endurance coaching advice. Always read or fetch athlete JSON data before responding to any training question.

not rated 137 +1 12d ago A 58 tokens original MIT

suggesting-remedies

174

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 137 +4 21d ago A 85 tokens original Apache-2.0

deepmd-finetune-dpa3

175

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 136 +2 today A 131 tokens LGPL-3.0

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 135 5mo ago A 40 tokens original MIT

paper

177

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 135 +3 5mo ago A 42 tokens original MIT

cesium-mcp

178

gaopengbin/cesium-mcp

Plugin Claude Code

Bundles 3 MCP servers

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

not rated 135 +1 today A tokens not measured original MIT

com-b-diagnostic

179

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 132 4mo ago A 55 tokens original MIT

paper-critic

180

flonat/flonat-research

Agent Claude Code

Adversarial auditor for LaTeX papers. Read-only with respect to project files (paper, bib, code, data); writes its own report at reviews/ /paper-critic/ .md plus a findings.json sidecar. Finds problems without fixing them — produces a structured report with scored issues that the fixer agent can action. Assumes the…

not rated 132 +2 11d ago A 625 tokens original MIT

paper-search

181

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 131 2mo ago A 361 tokens original MIT

happy-figure-skill

182

BAIKEMARK/happy-figure-skill

Skill Claude CodeCodex

A skill for turning research papers and other scientific material into reusable prompts for AI-generated figures. It can also use reference images when available.

not rated 131 +3 3mo ago A 231 tokens

stars-we-prefer

183

block/ai-rules

Skill Claude CodeCodex ✓ vendor

Our preferred stars for celestial navigation and astronomical reference.

not rated 130 +2 3mo ago A 14 tokens original Apache-2.0

psu-efd/pyHMT2D

Cursor rule Cursor

This rule covers the calibration and parametric study capabilities of pyHMT2D.

not rated 130 +2 27d ago A 0 tokens original MIT

thesis-figure-skill

185

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 130 +1 1mo ago A 107 tokens original MIT

yam-runtime-artifacts

186

NVlabs/ASPIRE

Skill Claude CodeCodex

Use when inspecting YAM logs, videos, SAM3 overlays, observations, planner previews, function-call JSON, result files, or failure evidence.

not rated 127 +3 5d ago A 34 tokens original Apache-2.0

proof-checker

187

AI4Scientist/nano-scientist

Skill Claude Code

A rigorous proof-checking and repair skill for LaTeX mathematics. LaTeX is a text format commonly used to write mathematical documents.

not rated 127 +1 3mo ago A 90 tokens

distribution-search

188

lazyFrogLOL/Harness_Engineering

Skill Claude CodeCodex

Guidance for finding probability distributions that satisfy specific statistical constraints such as KL divergence targets, entropy requirements, or moment conditions. This skill should be used when tasks involve constructing discrete or continuous probability distributions with specified divergence measures, entropy…

not rated 126 3mo ago A 58 tokens

chem-tools

189

DrugClaw/DrugClaw

Skill Claude CodeCodex

Computational chemistry workflow guide for DeepChem, PySCF, RDKit, assay-table normalization, PDBbind-style structure datasets, QSAR and structure benchmarks, DrugBank lookup, ligand-only and structure-aware affinity prediction, ADMET triage, bioactivity prediction, virtual screening, and docking follow-up.

not rated 125 5mo ago A 65 tokens original Apache-2.0

nature-writing

190

SyntaxSmith/nature-writing-skill

Skill Claude CodeCodex

A Chinese-language academic writing skill for AI and machine-learning researchers preparing papers for Nature journals. It focuses on story, structure, and writing quality for venues such as Nature Machine Intelligence and Nature Communications.

not rated 125 +7 4mo ago A 283 tokens

ma-manuscript-quarto

191

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 124 2d ago A 39 tokens

research-superpower

192

kthorn/research-superpower

Plugin Claude Code

Bundles 10 skills, 1 hook · 217 tokens together

Systematic literature searching and review toolkit for Claude Code. Search PubMed, screen papers, extract data, traverse citations, and synthesize findings from scientific literature.

not rated 123 10mo ago A tokens not measured 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: