578 tagged Scientific, measured the same way as everything else here.
Browse within: LLM 118prompt-engineering 104agentic-ai 102Science 97agents-md 97claude-code-plugin 34bioinformatics 32mcp-server 31academic-writing 24codex-plugin 22github-copilot 21matlab 21ai-tools 18matlab-mcp-server 18
Plugin Claude Code
Bundles 15 skills, 9 agents · 301 tokens together
Multi-agent workflow framework for building, testing, and shipping statistical software packages.
Plugin Claude Code
Bundles 20 skills, 4 agents, 1 hook · 960 tokens together
mcp-stata - an agentic toolkit for empirical researchers. Gives AI agents native control over a local Stata installation, allowing agents to run do-files, inspect data, check stored results, and export graphs.
pymc-labs/python-analytics-skills
Plugin Claude Code
Bundles 6 skills, 1 hook · 747 tokens together
Python analytics skills — PyMC and marimo.
Plugin Claude Code
Search Lean 4 declarations through the hosted LeanExplore MCP server.
Plugin Claude Code
Bundles 85 skills, 4 agents · 8,466 tokens together
Mechanist — AI Systems as Scientific Instruments for Understanding the Mechanisms of Intelligence.
Plugin Claude Code
Search Lean 4 declarations through the hosted LeanExplore MCP server.
HeshamFS/materials-simulation-skills
Plugin Claude Code
Bundles 23 skills · 2,695 tokens together
Every materials-simulation domain skill.
Plugin Claude Code
Bundles 10 skills · 1,149 tokens together
Senior power-engineer mitigation playbooks: voltage violations, thermal overloads, contingency (N-1/N-2) findings, dynamic-stability problems, operations/planning infeasibilities, convergence failures, short-circuit duty, frequency response, interconnection impacts, and DER hosting capacity. Issue-driven and…
Plugin Claude Code
Bundles 8 skills · 2,015 tokens together
A collection of five skills for searching and working with academic research papers. They use the scimaster-cli search tool and state that citations are based on real searches.
Plugin Gemini CLI
Shared, verifiable memory for AI agents. Two layers, one trust surface. Earth-scale fact substrate: every patch of ground gets a 64-bit address (cell64, about 9.55 m), and every measurement at that cell is a signed fact keyed by (cell, band, tslot), ed25519-signed by the responder over the blake3 of its canonical CBOR.
Plugin Claude Code
Bundles 1 skill · 173 tokens together
Agentic GIS / geospatial workflows: source discovery and provenance (from open data sources first), vector/raster/point-cloud pipelines, CRS and metric analysis, spatial SQL, QGIS projects, tile generation, and web maps — compiled into reproducible projects.
Plugin Claude Code
Bundles 1 skill, 11 commands · 132 tokens together
Open Science Skills (oss). 43 Claude Code skills for experimental social science and computational text analysis. Orchestration and delegation: orchestrate (a multi-model workflow led by the session's Fable or Opus model, sending menial tool calls to Haiku and judgment work to Opus at a per-task effort, with --lead…
Plugin Claude Code
Bundles 13 skills · 367 tokens together
Scientific literature search skills for Claude using Valyu API - PubMed, arXiv, ChEMBL, DrugBank, bioRxiv, medRxiv, and more.
Plugin Claude Code
Bundles 23 skills, 4 agents · 2,055 tokens together
Claude Code skills and domain-expert reviewer subagents for AI-assisted scientific computing.
Plugin Claude Code
Bundles 1 skill · 39 tokens together
Search academic papers via OpenAlex — find papers by keyword, look up details by DOI, with pagination and sorting.
Plugin Claude Code
Bundles 10 skills, 2 hooks · 1,471 tokens together
Integrate DTensor-based context parallelism (CP) into a custom co-folding / structure-prediction model — sharding the O(N²) pair and attention tensors across a multi-GPU device mesh via explicit ring/transpose collectives. A top-level cpizemodelworkflow conductor prioritizes, sequences, and gates the whole effort end.
Plugin Claude Code
Bundles 1 skill, 1 command · 269 tokens together
A deep-research workflow that combines academic searches and web research into a cited, structured report with a reusable evidence record.
Plugin Claude Code
Bundles 1 skill · 68 tokens together
MCP tools for LTspice/ngspice circuit simulation and LTspice .asc schematic editing. Structured results include per-device operating points (gm/gds/vth) by device name, without parsing raw files. Tracks the latest ltspice-mcp release on PyPI.
Plugin Claude Code
Bundles 6 skills, 1 MCP server · 241 tokens together
LLM-driven RF control and analysis — "Claude Code for RF". Survey spectrum, build and run receivers, simulate scenes, and run closed-loop TX/RX experiments through natural language, leaving a reproducible RF project behind.
Plugin Claude Code
Bundles 1 skill · 101 tokens together
Falsifiable research planning for AI agents: pressure-test claims, freeze evaluators, use AI-lab and medical evidence patterns, build proof ladders, and maintain proof ledgers.
Plugin Claude Code
Bundles 9 skills · 616 tokens together
Academic research agents — hypothesis generation, experiment design, paper drafting, peer review simulation, and more.
Plugin Claude Code
Bundles 1 skill · 156 tokens together
Agent-native Stata bridge for Claude Code. Drive DiD/IV/RDD and publication-ready esttab tables in plain language, then cross-validate each estimate against StatsPAI. Bundles an MCP server (21 tools, 14 workflow prompts, token-economy result schema, typed errors, multi-session) and an agent skill with an on-demand…
Plugin Claude Code
Bundles 38 skills · 4,666 tokens together
An AI-agent skill package for 五运六气, a traditional Chinese medicine system that studies relationships between calendar cycles, climate, and health. It includes tools and routing files for calculations, medical-pattern analysis, classical texts, and interpretation.
neuromechanist/research-skills
Plugin Claude Code
Bundles 8 skills, 1 agent · 1,269 tokens together
Publication-quality figures plugin. Eight skills + one QA agent. figure-bible: scaffolds and validates the per-project theme.json (palette, typography, text limits, Codex model settings) that every other skill reads. ai-full-figure: gpt-image-2 through the Codex CLI (or the OpenAI Images API) renders single panels or…
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: