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.

hajibabaie/combinatorial-optimization-skills

Plugin Claude Code

Bundles 76 skills · 9,357 tokens together

76 skills covering MILP modeling with Gurobi, decomposition methods (column generation, Benders, Lagrangian), all major metaheuristics (GA, PSO, SA, tabu, ALNS, BRKGA, ...), encodings and operators, classic problems (TSP, VRP, scheduling, knapsack, facility location), and optimization research workflows with numpy…

not rated 15 4mo ago A tokens not measured original MIT

arxiv-digest

578

tb5z035i/arxiv-digest

Skill Claude CodeCodex

Fetch daily arXiv announcements (cs.RO), filter by research relevance, generate a structured markdown digest, and sync matched papers to a Zotero collection with arXiv PDFs attached.

not rated 15 7mo ago A 42 tokens original MIT

arxiv

579

Ray0907/arXiv-mcp

MCP server Claude CodeCodexCursor +2

MCP server "arxiv" as configured in Ray0907/arXiv-mcp. Launched with uv --directory ${PLUGIN_ROOT} run arxiv-mcp.

not rated 15 1mo ago A tokens not measured original MIT

nnterp

580

ndif-team/skills

Plugin Claude Code

Bundles 3 skills · 232 tokens together

Architecture-agnostic interpretability with nnterp on nnsight 0.8 - one module vocabulary and standard values (layeroutput, attentionoutput, attentionprobabilities, ...) across 98 transformer families, the vision side of vision-language wrappers (model.vision, the tower blocks, the projector, imagetokenmask, image.

not rated 15 +1 2d ago A tokens not measured original MIT

paper-research-mentor

581

Lxy-hqu/-mcp-for-paper-read-based-on-AI-IDE

Skill Codex

A research-paper reading guide for understanding one or more academic papers in depth. It provides explanations linked to the source, discusses equations and experiments, and connects methods to new projects.

not rated 15 15d ago A 78 tokens

shidi

582

IcyCreamDAS/shidi-skill

Skill Claude CodeCodex

A research assistant workflow that turns a research idea into literature searches, experiment plans, figures, paper summaries, and organised data. It asks you to confirm important choices instead of making them on its own.

not rated 15 9d ago A 126 tokens original MIT

papersflow

583

papersflow-ai/papersflow-mcp

MCP server Claude CodeCodexCursor +2

Academic research MCP server for paper search, citation checks, graphs, and deep research. Remote server at doxa.papersflow.ai.

not rated 14 8mo ago A tokens not measured original MIT

audit-oe

584

htlin222/audit-oe-skill

Skill Claude CodeCodex

Audit OpenEvidence MCP citations with transitive citation detection, cross-citation contradiction scanning, provenance analysis, and multi-dimensional accuracy scoring.

not rated 14 6mo ago A 29 tokens original MIT

mcp-lammps

586

Chenghao-Wu/MCP_LAMMPS

MCP server Claude CodeCodexCursor +2

MCP server "mcp-lammps" as configured in Chenghao-Wu/MCPLAMMPS. Runs locally from the mcp-lammps Python package.

not rated 14 10mo ago A tokens not measured original Apache-2.0 archived

compound-science

587

James-Traina/compound-science

Plugin Claude Code

Bundles 20 skills · 1,701 tokens together

AI research assistant for quantitative social science. Ambient hooks detect research context and route to 10 specialized agents covering structural econometrics, causal inference, game theory, identification, Monte Carlo studies, and reproducible pipelines.

not rated 14 7mo ago A tokens not measured original MIT

korean-rnd-regs-mcp

588

smilemin07/korean-rnd-regs-mcp

MCP server Claude CodeCodexCursor +2

A local MCP server for reviewing South Korean national research-and-development regulations. MCP is a way for an AI agent to call an external tool.

not rated 14 2d ago A tokens not measured original Apache-2.0

opensci-skill

589

HughYau/opensci-skill

Skill Claude CodeCodex

Help an agent familiarize itself with any scientific Python library or codebase so it can write a high-quality opensci skill for that library. Use when creating, auditing, or refactoring opensci skills for published packages, source-only repositories, namespace packages, or mixed-layout projects. Content is optimized…

not rated 14 8mo ago A 0 tokens

experiment

590

hdu-ailab/EasyResearch

Skill Claude CodeCodex

Use when Experiment must build, run, compare, or record reproducible ML/AI paper experiments locally or through the Research Assistant-configured ssh-bash tool and verified SSHFS workspace, including baselines, datasets, controlled trials, multi-seed formal evidence, ablations, and results promotion. Examples: user…

not rated 14 changed 7d ago A SkillSpector: warn 171 tokens original MIT

LeiGao0203/R-Medical-Statistics-Skills

Skill Claude CodeCodex

An R-language guide for logistic regression, a statistical method for modeling outcomes such as yes/no results or categories from one or more predictors. It covers several logistic regression types and ways to interpret and assess the models.

not rated 14 3mo ago A 173 tokens

chuk-mcp-physics

592

IBM/chuk-mcp-physics

MCP server Claude CodeCodexCursor +2 ✓ vendor

MCP server for physics simulations and calculations using Rapier physics engine. Runs locally from the chuk-mcp-physics Python package.

not rated 14 1mo ago A tokens not measured original Apache-2.0 archived

idfkit-mcp

593

idfkit/idfkit-mcp

MCP server Claude CodeCodexCursor +2

An MCP server exposing EnergyPlus model authoring, validation, and simulation via idfkit. Runs locally from the idfkit-mcp Python package.

not rated 14 +1 yesterday A tokens not measured original MIT

Rezenders/scientific_writing_agent

Skill Claude CodeCodex

Use immediately after installing the scientific-writing workflow to interview the user, inspect the manuscript, and fill the .agents/context/ templates with project-specific facts before writing or review work begins.

not rated 14 17d ago A 41 tokens original Apache-2.0

audiogear

595

lIkesimba9/audiogear

Skill Claude CodeCodex

Annotate speech/TTS datasets with per-clip quality metrics (MOS, SNR, STOI, pitch, bandwidth, speaking rate, WER/CER, gender/emotion), multi-ASR consensus transcription and speaker labeling using the audiogear pipeline; then filter clips by quality and build listenable HTML QA reports. Use when asked to compute audio…

not rated 14 3mo ago B 103 tokens original MIT

paperpal

596

jerpint/paperpal

Plugin Claude Code

Bundles 1 skill, 1 MCP server · 88 tokens together

ML literature research for agents: top-tier venue search, arXiv / Hugging Face / Semantic Scholar, full-text verification, credibility scoring, and gdoc-ready notes.

not rated 14 +1 changed 23d ago A tokens not measured original MIT

materials-project-mcp

598

benedictdebrah/materials-project-mcp

MCP server Claude CodeCodexCursor +2

MCP server "materials-project-mcp" as configured in benedictdebrah/materials-project-mcp. Runs locally from the materials-project-mcp Python package.

not rated 13 5mo ago A tokens not measured original MIT

abaqus-sim

599

svd-ai-lab/sim-plugin-abaqus

Skill Claude CodeCodex

Use when the user asks Codex, Claude Code, ChatGPT-style coding agents, or another AI agent to automate, inspect, run, or debug Abaqus through sim-cli. Supports Abaqus/CAE noGUI workflows, batch jobs, model inspection, ODB diagnostics, bounded execution, artifact reporting, and troubleshooting. Requires a user-owned…

not rated 13 19d ago A 77 tokens original Apache-2.0 archived

LivXue/paper-search-with-citation

Skill Claude CodeCodex

Use when working with the Academic Paper Search and BibTeX Generation API, including searching papers, retrieving BibTeX citations, and monitoring API manager statistics.

not rated 13 3mo ago A 36 tokens

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: