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.

psu-efd/pyHMT2D

Cursor rule Cursor

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

not rated 134 2mo ago A 0 tokens original MIT

research-superpower

218

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 131 1y ago A tokens not measured original MIT

distribution-search

219

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 130 5mo ago A 58 tokens

proof-checker

220

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 130 5mo ago A 90 tokens

opendatalab/Sciverse-Agent-Tools

Skill Claude CodeCodex

Sciverse academic paper retrieval: metadata search across papers, authors, sources and patents, semantic chunk retrieval for RAG, and character-range content reading (offsets in Unicode code points). For agent workflows that need citation-grade scientific literature.

not rated 129 +1 changed 3d ago A 0 tokens

energyplus

222

LBNL-ETA/EnergyPlus-MCP

MCP server Claude CodeCodexCursor +2

One of 2 in mcp.json

MCP server "energyplus" as configured in LBNL-ETA/EnergyPlus-MCP. Runs energyplus_mcp_server.server with /workspace/energyplus-mcp-server/.venv/bin/python. Needs 1 environment variable to run.

not rated 125 +1 2d ago A tokens not measured

spectral

223

spectral-mcp/spectral

MCP server Claude CodeCodexCursor +2

Spectral Python (SPy) is a Python module for hyperspectral image processing. Runs locally from the spectral Python package.

not rated 124 +3 7mo ago A tokens not measured original MIT

autoresearch

224

Factory-AI/factory-plugins

Skill Claude CodeCodex

Autonomous experiment loop for optimization research. Use when the user wants to: Optimize a metric through systematic experimentation (ML training loss, test speed, bundle size, build time, etc.) Run an automated research loop: try an idea, measure it, keep improvements, revert regressions, repeat Set up autoresearch…

not rated 123 +2 yesterday A 100 tokens

genggng/hermes-arxiv-agent

Skill Claude CodeCodex

Use this skill inside a Hermes conversation when a user wants Hermes to deploy hermes-arxiv-agent end to end in either local/Feishu mode or optional GitHub Pages mode, including cloning the appropriate repo, installing Python dependencies, generating the correct cron prompt, and creating a daily cron job.

not rated 123 +1 2d ago A 67 tokens

aut-sci-ppt

226

ShZhao27208/Aut_Sci_ppt

Skill Claude CodeCodex

Use when converting academic paper PDFs or structured text into professional, high-standard PowerPoint (PPTX) presentations for defense or seminars.

not rated 122 3mo ago A 33 tokens original MIT

fangyuanopus/literature-report-ppt-builder

Skill Codex

Use this skill for Chinese academic literature-report PPTs, research slides, journal-club decks, thesis-defense slides, slide page images, or paper-to-PPT workflows based on real paper/SI figures. It enforces an Image2 availability gate: only an Image2-style native 16:9 full-slide image backend may create…

not rated 121 3mo ago A SkillSpector: warn 163 tokens original MIT

by-campaign-manager

229

001TMF/blatant-why

Skill Claude Code

Plan, execute, monitor, and assess protein/antibody design campaigns. This skill governs how to size a campaign, track run state, coordinate multi-run efforts, estimate cost and time on each compute target (local GPU, HPC, Tamarind), monitor progress, and evaluate campaign health.

not rated 119 22d ago A SkillSpector: warn 4 tokens original MIT

ledidi

230

jmschrei/ledidi

Skill Claude CodeCodex

Use for any task involving the ledidi library — gradient-based design of minimal edits to categorical sequences (DNA/RNA/protein) so that a frozen oracle model predicts a desired output. Triggers on designing or editing a sequence, inserting or knocking out a motif or binding site, hitting a target model output, cell…

not rated 119 changed 1mo ago A SkillSpector: pass 126 tokens original Apache-2.0

sematyp

231

QSong-github/DrugClaw

Skill Claude CodeCodex

SemaTyP combines two data sources into a knowledge graph for drug discovery / repositioning.

not rated 118 2mo ago A 0 tokens

cumcm-b-problem

232

liufanshan11/cumcm-b-problem-lfs

Skill Codex

A guide for solving B problems in the China Undergraduate Mathematical Contest in Modeling, a national student competition. It covers reading the question, choosing a mathematical model and algorithms, checking results, and preparing the final paper.

not rated 118 2mo ago A 160 tokens

siza

233

DataHaskell/sabela

Plugin Claude Code

Bundles 1 skill, 1 MCP server · 61 tokens together

Pair with a running Sabela notebook. Bundles the siza MCP server (list, read, run, edit cells; discover APIs; try code; verify claims) plus a short pairing skill.

not rated 117 changed 17d ago A tokens not measured original MIT

paper-to-cn-patent

235

snipp-zha/Paper-to-patent-Skill

Skill Claude CodeCodex

Convert scientific papers, theses, technical reports, source code, figures, or research manuscripts into evidence-grounded Chinese invention patent drafts. Use when an AI agent must extract patentable technical contributions, map every claimed feature to source evidence, preserve core formulas as editable Office Math…

not rated 116 +1 4mo ago A 102 tokens

arc

236

tririver/arc

Plugin Claude Code

Bundles 1 skill · 62 tokens together

Agent Research Copilot for academic papers and theoretical-physics research workflows.

not rated 114 +1 changed 23d ago A tokens not measured original MIT

EtaYang10th/spark-skills

Skill Claude CodeCodex

Solve day-ahead energy market what-if studies on MATPOWER-style network JSON using DC-OPF with spinning reserve co-optimization, compare base vs counterfactual transmission scenarios, and write a validator-friendly report.json.

not rated 109 4mo ago A 54 tokens

LGDiMaggio/predictive-maintenance-mcp

Plugin Claude Code

Bundles 8 skills, 3 commands, 2 agents · 820 tokens together

Industrial-grade predictive maintenance skills, agents, and workflows for the predictive-maintenance-mcp server. Provides domain expertise for vibration analysis, bearing/gear fault diagnosis, anomaly detection, ISO 20816-3 compliance, and diagnostic report generation.

not rated 109 +3 changed 7d ago A tokens not measured original MIT

mjlab-skillkit

239

cmjang/mjlab-skillkit

Skill Codex

Use when asked to migrate IsaacLab projects to mjlab, compare IsaacLab and mjlab APIs, import meshes into mjlab tasks, or author new mjlab-native tasks/components directly from local or bundled mjlab docs and examples. This skillkit includes an IsaacLab Migration Skill and an mjlab Native Skill. Prefer mjlab public…

not rated 106 +1 8mo ago A 85 tokens original MIT

sci-brain

240

QuantumBFS/sci-brain

Plugin Claude Code

Bundles 17 skills · 575 tokens together

Scientific research brainstorming partner: survey the literature, find good problems, and shape concrete research ideas together.

not rated 106 changed 2mo 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: