skills
25project-numina/numina-lean-agent
Plugin Claude Code
Bundles 6 skills · 138 tokens together
Lean 4 theorem proving tools: search, verification, LLM-assisted proving.
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
project-numina/numina-lean-agent
Plugin Claude Code
Bundles 6 skills · 138 tokens together
Lean 4 theorem proving tools: search, verification, LLM-assisted proving.
Plugin Claude Code
Bundles 4 skills, 1 agent · 498 tokens together
The official working package of MCP-for-Stata plugin, including mcp config and stata lsp.
krzysztofdudek/ResearcherSkill
Plugin Claude Code
Bundles 1 skill · 96 tokens together
Autonomous experimentation skill — your AI coding agent designs experiments, tests hypotheses, discards failures, keeps wins. Runs overnight while you sleep.
Plugin Claude Code
Bundles 1 skill · 199 tokens together
Drive SpliceCraft — a terminal plasmid-map viewer, sequence editor and molecular-cloning workbench — through its localhost agent API. Teaches Claude to connect (including attaching read-only to a session you already have open), the canvas-vs-library model, the 0-based forward-strand coordinate convention, the…
Plugin Claude Code
Bundles 3 skills, 2 commands, 6 agents, 1 MCP server · 173 tokens together
Scientific research agent extension - turns research goals into reproducible Jupyter notebooks with Python REPL, data analysis, and ML workflows.
Plugin Claude Code
Bundles 1 skill · 60 tokens together
Build healthcare AI services with HealthChain: FHIR gateways, validated FHIR resources, and typed agent tools.
Plugin Claude Code
Bundles 1 skill · 61 tokens together
Find, edit, and verify academic TikZ figures (icons, templates, examples) with the using-opentikz skill.
Plugin Claude Code
Bundles 1 skill, 11 commands, 4 agents, 3 hooks · 404 tokens together
Archon's modified Lean 4 plugin (draft, formalize, autoformalize, prove, autoprove, checkpoint, review, refactor, golf, learn, doctor) — forked from cameronfreer/lean4-skills.
franklee16/academic-research-skills
Plugin Claude Code
Bundles 12 skills · 1,022 tokens together
Agent skill stack for manuscripts targeted at Agricultural Systems — the leading international journal for the systems analysis of agricultural systems, published by Elsevier (ISSN 0308-521X), submitted via Editorial Manager under single-anonymized peer review (minimum two reviewers; editor decides). Agricultural…
Plugin Claude Code
Bundles 1 skill, 1 agent · 347 tokens together
Reasons from separating problem, model, and cost model (comparison, word-RAM, arithmetic, online) through exchange/matroid greedy proofs, subproblem-DAG dynamic programming, max-flow min-cut and Goemans–Williamson primal-dual rounding, Karp–Rabin fingerprinting, competitive ratio and Yao's principle, PTAS/FPTAS…
learningmatter-mit/AtomisticSkills
Plugin Claude Code
Bundles 133 skills · 4,580 tokens together
Agent skills for atomistic simulation: materials science, chemistry, drug discovery, and machine-learning interatomic potentials.
Plugin Claude Code
Bundles 1 skill · 61 tokens together
Guides users through a structured symptom interview, literature search, and evidence evaluation to prepare for medical appointments.
Plugin Claude Code
Bundles 1 skill · 74 tokens together
Claude Code Skill for creating mathematical animations using Manim Community Edition. Plan, code, render, and iterate on 3Blue1Brown-style videos.
Plugin Claude Code
Bundles 33 skills, 1 MCP server · 2,497 tokens together
Search PubMed/Europe PMC, fetch articles and full text (PMC/EPMC/Unpaywall), citations, MeSH terms.
jaccen/Awesome-Gaussian-Skills
Plugin Claude Code
Bundles 5 skills · 711 tokens together
Research cycle: read 3DGS papers, compare methods across 11 dimensions, plan CVPR/ICCV/SIGGRAPH experiments, write and review papers with the 955-method knowledge base, and run the nine-role research expert team (idea evaluation, innovation mining, simulated review, polishing, AIGC-trace hygiene, venue compliance…
Plugin Claude Code
Bundles 1 skill, 3 MCP servers · 34 tokens together
AI-powered 3D globe control for Claude Code — load tilesets, fly to locations, style layers, and query spatial data with natural language.
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.
Plugin Claude Code
Bundles 1 skill · 61 tokens together
Sabela notebook pairing skill — a typed compiled client (list, read, run, edit cells; pre-flight parse + security scan; provenance) over the Sabela AI bridge, plus an MCP stdio server (siza mcp) for any MCP client.
joshua-zyy/academic-paper-writer
Plugin Claude Code
Plugin marketplace listing 1 plugin: academic-paper-writer.
Plugin Claude Code
Bundles 1 skill · 62 tokens together
Agent Research Copilot for academic papers and theoretical-physics research workflows.
LGDiMaggio/predictive-maintenance-mcp
Plugin Claude Code
Bundles 8 skills, 3 commands, 2 agents · 786 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.
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.
cyanheads/clinicaltrialsgov-mcp-server
Plugin Claude Code
Bundles 33 skills, 1 MCP server · 2,497 tokens together
Search ClinicalTrials.gov trials, retrieve study details and results, and match patients to candidate trials via MCP. STDIO or Streamable HTTP.
Plugin Claude Code
Bundles 6 skills, 1 command, 1 hook · 452 tokens together
evsys-sdk usage skills for the autoresearch loop: read a project's goal and experiment history, decide the next experiment, scaffold and launch it, and read/write experiments, datasets, benchmarks, and metrics via the SDK.
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: