Scientific

15,199 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.

nice-figures

601

Mapika/nice-figures

Plugin Claude Code

Bundles 1 skill · 183 tokens together

Generate matplotlib figures in a soft-pastel, warm-earth, research-blog visual register — bold sans-serif display titles, scatter overlaid with smoothed trends and shaded confidence bands, signature rounded bars, minimal axes, and '↓better' badges. White background by default (conference-ready), with an opt-in warm…

not rated 10 3mo ago A tokens not measured original MIT

ampl-tuner

603

marcos-dv/ampl-agents

Skill Claude CodeCodex needs its repo

Expert in AMPL/MP solver options across all supported solvers. Recommends and configures lim:time, mip:gap, threads, IIS, barrier, and solver-specific knobs. Fetches official option pages from dev.ampl.com before citing names. Use when tuning solve performance, setting optimality gaps, choosing LP/MIP/NLP algorithms…

not rated 10 20d ago A SkillSpector: pass 99 tokens original MIT

creating-figures

604

isomoes/skills

Skill Claude CodeCodex

Creates publication-quality scientific figures for academic papers using TikZ. Use when creating block diagrams, system architectures, flowcharts, or technical illustrations for papers and theses. Always render a temporary PNG/JPG preview and self-verify visual quality before finalizing figure files.

not rated 10 4mo ago A 57 tokens original MIT

zeroplot

605

blackblue-labs/zeroplot

Skill Claude CodeCodex

Create editable charts, diagrams, figures, posters, or slides from intent, data, or references.

not rated 10 1mo ago A 24 tokens original MIT

Shoko-official/Claude-Science-System-Prompts

Skill Claude CodeCodex

Conduct rigorous, reproducible multi-step scientific work with literature, databases, local files, Python, R, shell, artifacts, reviewers, and approved compute. Use for evidence synthesis, data or statistical analysis, machine learning, simulation, study design, scientific figures or manuscripts, reproduction audits…

not rated 10 1mo ago A 99 tokens original Apache-2.0

plaxis

607

Sompote/plaxisMCP

Skill Claude CodeCodex

Drive PLAXIS 2D V20 via the MCP server in this repo — connect, build geometry/materials/boreholes, set BCs, mesh, configure phases (K0/Plastic/Safety), calculate, and read results. Use when the user asks anything about PLAXIS, embankments, soft clay, factor of safety, settlement, soil materials, boreholes, staged…

not rated 10 4mo ago A 159 tokens

optimize-report

608

TaoELi/FermiLink

Skill Claude CodeCodex

Generate a Sphinx-ready report bundle (plots, RST, contract, per-accepted-commit pages) from a completed fermilink optimize workspace. Use when the user asks to visualize, export, or publish optimization results from a .fermilink-optimize directory, or wants to prepare material for the Project Optimization website.

not rated 10 8d ago A 73 tokens AGPL-3.0

wind-sim

609

NanxiiChen/wind-simulation-GPU

Skill Claude CodeCodex

Stochastic wind field simulation library (JAX / PyTorch / NumPy) with stationary and nonstationary support. Use this skill whenever working in this repository — it covers both usage (running simulations, benchmarks, validation) and development (architecture, adding backends, modifying the algorithm, config system).…

not rated 10 1mo ago A 98 tokens GPL-3.0

coqtail-mcp

610

park-sunho/Coqtail-mcp

Plugin Claude Code

Bundles 1 skill, 4 agents · 443 tokens together

Drive a live Rocq/Coq proof session through coqtail-mcp. Bundles the skill (server mechanics + proof recipes) and four named subagents (proof-repair, admitted-filler-deep, axiom-auditor, proof-golfer).

not rated 10 1mo ago A tokens not measured

research-mentor

611

zjgxuzhou-prog/Claude-Research-Menntor

Skill Claude CodeCodex

A Chinese-language research mentor for PhD students working in deep learning and artificial intelligence. It covers research from choosing a topic and designing experiments through writing papers and responding to reviews.

not rated 10 4mo ago A 379 tokens

jupyter

612

jrgleason/embeddings-demystified

MCP server Claude CodeCodexCursor +2

One of 3 in .mcp.json

MCP server "jupyter" as configured in jrgleason/embeddings-demystified. Runs in Docker (datalayer/jupyter-mcp-server:latest). Needs 2 environment variables to run.

not rated 10 3mo ago A tokens not measured

mxl-driver-dftbplus

613

TaoELi/MaxwellLink

Skill Claude CodeCodex

This skill should be used when users want to couple MaxwellLink to the MaxwellLink-aware DFTB+ fork via the MaxwellLinkSocket block, including real-time Ehrenfest dynamics, VelocityVerlet Born-Oppenheimer MD, dipole-derivative choices, build/install, and TCP/UNIX socket connection patterns.

not rated 10 5d ago A 75 tokens GPL-2.0

du-par/pharma-invest-skills

Skill Claude CodeCodex

A framework for evaluating pharmaceutical drug-development projects across biology, drug design, clinical and regulatory plans, and commercial conditions. It also classifies projects by how differentiated their innovation is.

not rated 10 4mo ago A 189 tokens original MIT

NVIDIA/digital-health-skills

Skill Claude CodeCodex ✓ vendor

Stage 4 of the Clinical ASR Flywheel. Use when priority KER is above 0.3 to run stock NeMo SFT on Parakeet TDT v2 and offline cycle N+1 re-eval. NOT for generic word boosting (use /finetune-asr).

not rated 10 2mo ago A 72 tokens

zemax-python-connect

616

Hao-xl/zemax-python-connect

Skill Claude CodeCodex

A focused guide for connecting Python to Zemax OpticStudio, optical design software, through its ZOS-API programming interface. It checks installation paths, required files, licenses, connection modes, and the active optical system.

not rated 10 2mo ago A 77 tokens original MIT

nf-core

617

jonasscheid/claude-nfcore-plugin

Plugin Claude Code

Bundles 4 skills, 6 agents, 2 hooks · 529 tokens together

Comprehensive Claude Code plugin for nf-core Nextflow pipeline development. Includes skills for pipeline creation, module management, linting, testing, and release preparation following nf-core best practices.

not rated 10 3mo ago A tokens not measured original MIT

physionet-mcp

618

rafiattrach/physionet-mcp

MCP server Claude CodeCodexCursor +2

Lean BigQuery-only MCP server for PhysioNet datasets. Runs locally from the physionet-mcp Python package.

not rated 10 8mo ago A tokens not measured original MIT

black-yt/skills

Skill Claude CodeCodex

A Chinese-language guide for writing and revising artificial-intelligence research papers for academic conferences.

not rated 10 16d ago A 68 tokens

autoresearch-create

620

ergenekonyigit/cursor-autoresearch

Skill Claude CodeCodex

Set up and run an autonomous experiment loop for any optimization target. Gathers what to optimize, then starts the loop immediately. Use when asked to "run autoresearch", "optimize X in a loop", "set up autoresearch for X", or "start experiments".

not rated 10 +1 7d ago A SkillSpector: warn 59 tokens original MIT

math-modeling

621

Hjdd14/math-modeling

Skill Claude CodeCodex

A multi-stage workflow for mathematical modelling competitions and similar problems using documents and spreadsheet data. It covers problem review, model selection, code, charts, validation, reproducibility, and writing handoff materials.

not rated 10 +1 changed today A 114 tokens original MIT

iso-17025-de

622

cleverlab-ai/iso-17025-skill

Skill Claude Code

Fachberater für DIN EN ISO/IEC 17025:2018 — die internationale Norm für die Kompetenz von Prüf- und Kalibrierlaboratorien. Verwenden Sie diesen Skill wenn: (1) Vorbereitung auf Akkreditierungs- oder Überwachungsaudits der DAkkS, (2) Aufbau oder Überprüfung von Qualitätsmanagementsystemen für Laboratorien, (3)…

not rated 10 +1 6mo ago A 231 tokens original MIT

chanlun-engine-skill

623

adsorgcn/chanlun-engine-skill

Skill Claude CodeCodex

A Chinese-language stock-analysis skill based on Chan theory, a method for interpreting price-chart structures such as turning points and trading ranges.

not rated 10 +2 16d ago A 128 tokens original MIT

WolframResearch/system-modeler-ai-toolkit

Skill Claude CodeCodex

Simulate and analyze Modelica models from within Wolfram Language / a notebook (WSM SystemModel functions, WSMRealTimeSimulate) — extract numerical results and make custom plots. Use this skill whenever the user wants to work with a Modelica model inside WL / a notebook — running parameter sweeps, pulling time series…

not rated 10 21d ago A SkillSpector: pass 252 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: