Scientific plugins

427 tagged Scientific, measured the same way as everything else here.

Browse within: prompt-engineering 31Science 30agents-md 30bioinformatics 24cyanheads 18academic-writing 15arxiv 12claude-plugin 10bun 8claude-skill 8machine-learning 8academic 6agentic-skills 6claude-code-skills 6

snowstorm-mcp-server

169

IHTSDO/snowstorm-mcp-server

Plugin Claude Code

Bundles 2 skills, 1 MCP server · 135 tokens together

Query SNOMED CT clinical terminology via Snowstorm and Snowstorm Lite backends. Lookup, search, validation, hierarchy navigation, and value set expansion across all SNOMED CT editions (International, US, UK, AU, etc.).

8 13d ago A tokens not measured original Apache-2.0

faostat-skills

171

berba-q/faostat-skills

Plugin Claude Code

Bundles 14 skills, 14 commands · 2,260 tokens together

Analysis skills for UN FAOSTAT food and agriculture data. Country profiles, commodity briefings, trade analysis, climate assessments, and data visualizations. Works with any AI assistant that supports the SKILL.md format.

7 4mo ago A tokens not measured original MIT

experiment-audit

176

SreeDharshan-GJ/experiment-audit

Plugin Claude Code

Bundles 1 skill · 276 tokens together

Scientific Research Reasoning Engine for evaluating experimental and empirical claims — auditing ML training runs, ablations, and sweeps; reviewing papers; checking reproducibility; and producing structured research reports. Optional Weights & Biases integration via the experiment-audit-mcp server.

7 +3 7d ago A tokens not measured original MIT

alkyl

180

Kdevos12/ALKYL

Plugin Claude Code

Bundles 27 skills · 1,690 tokens together

Computational chemistry and drug discovery plugin for Claude Code — RDKit, docking, MD, QM, FEP, generative design, and 23 domain skills.

6 5mo ago A tokens not measured original MIT

clinpharm-pmx-skills

182

malekokour/clinpharm-pmx-skills

Plugin Claude Code

Bundles 55 skills · 7,936 tokens together

Portable Agent Skills for clinical pharmacologists and pharmacometricians. Skills review, reconcile, and prepare evidence. They never select a dose, sign off, or submit.

6 19d ago A tokens not measured original MIT

WolframInstitute/ClaudePluginComputationalResearch

Plugin Claude Code

Bundles 21 skills, 23 commands, 1 hook · 2,433 tokens together

AI-assisted computational research with license-aware MCP-first Wolfram execution, wiki knowledge base, LaTeX/Typst paper scaffolding, Wolfram paclet development, symbol-page documentation bundled and publicly deployed on publish, dual-engine Markdown-to-notebook conversion that auto-detects a pinned rich converter…

6 12d ago A tokens not measured

music-analyzer

184

BENZEMA216/music-analyzer

Plugin Claude Code

Bundles 9 skills · 159 tokens together

Analyze local audio files, extract rhythm/emotion/timbre/tonality/lyrics features, output structured JSON, and map to Dreamina prompts and storyboards.

6 4mo ago A tokens not measured

kshana

185

ashfordeOU/kshana

Plugin Claude Code

Bundles 1 command, 2 MCP servers · 24 tokens together

Run the validated Kshana PNT-resilience engine from an AI agent — SGP4/SDP4, IAU frames, GNSS availability/DOP/ARAIM, Allan/MTIE timing, GNSS-INS fusion and quantum-sensor models. The agent calls the real, externally-validated engine instead of guessing the math. Requires the kshana-mcp server on PATH (cargo install…

6 6d ago A tokens not measured AGPL-3.0

sci-paper

188

skymanbp/sci-paper

Plugin Claude Code

Bundles 12 skills · 139 tokens together

Scientific paper writing, source-traced review, and de-AI rewriting for top-tier journals (ApJ/MNRAS/PRD/JCAP-class) and NSF/NIH proposals. Ships 12 skills and 35 tools under one typed standard: scientific-integrity blockers that cannot be waived as style preferences, a zero-target L0 lexicon, ranked advisories…

5 6d ago A tokens not measured

rebuttal-skills

190

yuangao-tum/rebuttal-skills

Plugin Claude Code

Bundles 2 skills · 287 tokens together

Two composable Claude Code skills for writing peer-review rebuttals: write-rebuttal (overall process — Parikh–Batra–Lee method, 18 tactics, AC-facing structure) and nlp-rebuttal (per-concern playbook — 28 reviewer-concern scenarios with answer templates).

5 1mo 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: