Scientific skills

12,450 tagged Scientific, measured the same way as everything else here.

Browse within: bioinformatics 260ai-scientist 207LLM 186agents 186biology 170reasoning-language-models 165ai-scientists 164reasoning-agent 164tool-use 164agent 159data-analysis 133cancer-genomics 132computational-biology 132literature-review 120

c-narcissus/research-paper-figure-skill-factory

Skill Claude CodeCodex

Use when the user wants a research-paper figure Skill Factory: build, patch, package, or use reusable specialized paper-figure-making skills from lawful literature/corpus evidence. Generated skills must use a specialized-skill-first workflow, full-feasible local PDF coverage where available, startup-plan-only first…

not rated 47 4mo ago A 169 tokens MIT-0

astro-dso-doc

242

jjmartres/ai-coding-agents

Skill Claude CodeCodex needs its repo

Generates a complete, polished HTML documentation page, a processing checklist, an AstroBin post JSON, a PixInsight process icon set (XPSM), AND a ready-to-paste PixInsight project Description field for a deep-sky object (DSO) astrophotography project. Use this skill whenever the user mentions astrophotography, a DSO…

not rated 45 +1 yesterday A 244 tokens original MIT

pyrestoolbox-mcp

243

gabrielserrao/pyrestoolbox-mcp

Skill Claude CodeCodex

Skill for using the pyResToolbox MCP Server — a 108-tool reservoir engineering calculation suite exposed via the Model Context Protocol. Use this skill whenever the user asks about petroleum engineering calculations, PVT analysis, well performance, inflow performance relationships (IPR), reservoir simulation input…

not rated 44 6mo ago A 204 tokens GPL-3.0

Dicklesworthstone/eidetic_engine_cli

Skill Claude CodeCodex

Use when planning active-learning experiments from ee observation ledgers, learning uncertainty reports, evaluation records, causal/economy/context evidence, or ee.skillevidencebundle.v1 artifacts without moving experiment-planning judgment into the Rust ee CLI.

not rated 44 +1 today A 54 tokens

math-skill

245

Wholiver/Math.Skill

Skill Claude CodeCodex

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling.

not rated 44 +4 3mo ago A 33 tokens original MIT

stata-ai-fusion

246

haoyu-haoyu/stata-ai-fusion

Skill Claude CodeCodex

An AI assistant for Stata, a statistics program used to analyse data. It covers writing, running, and debugging Stata code and working with datasets, regression models, and other statistical analyses.

not rated 43 2mo ago A 117 tokens original MIT

mimic-apsiii-24h-raw

247

hannesill/m4

Skill Claude CodeCodex

The following block is the public reference SQL used to construct the ground truth for this task. It is provided verbatim, without procedural prose, to test whether matched task-relevant content alone explains the WITH-SKILL gain.

not rated 43 1mo ago A SkillSpector: pass 0 tokens original MIT

paper-reproduction

248

WUBING2023/ReproRun

Skill Claude CodeCodex

A workflow for reproducing or checking results reported in academic papers, especially papers with public Python code. It is aimed at machine learning, computer vision, and natural language processing research.

not rated 43 2mo ago A 153 tokens

staad-core

250

BentleySystems/openstaad-mcp

Skill Claude CodeCodex

ALWAYS load first for any STAAD.Pro automation. Covers: Python sandbox (staad pre-injected — import blocked), sub-module access (Geometry, Property, Support, Load, Command, Output, Design), units and axis check via executecode, unit conversion (English=inches/KIP, Metric=meters/kN), GetBaseUnit, IsZUp, SetSilentMode…

not rated 42 +1 yesterday A SkillSpector: pass 118 tokens original MIT

paper-writing

251

swarm-ai-research/swarm

Skill Claude CodeCodex

Scaffold research papers from SWARM run data with auto-populated tables.

not rated 42 +1 today A SkillSpector: pass 17 tokens original MIT

h100-triton-rmsnorm

252

patrick-toulme/harnessgym

Skill Claude CodeCodex needs its repo

Use for the H100 Triton fused RMSNorm + SiLU gate optimization task. Provides the workflow and MCP tooling for objective runs, rollback-safe config sweeps, source diagnostics, benchmark history, and final held-out verification.

not rated 41 +1 2mo ago A 53 tokens original Apache-2.0

molmoact-libero

253

graph-robots/open-robot-skills

Skill Claude CodeCodex

Run the MolmoAct LIBERO checkpoint (allenai/MolmoAct-7B-D-LIBERO-0812) as a closed-loop VLA policy for the dexterous pick-and-place segment of a task. Drives a Franka Panda in the LIBERO/robosuite OSCPOSE action space from agentview + wrist cameras, served behind a vLLM-style script speaking the openpi websocket…

not rated 41 +2 yesterday A SkillSpector: warn 226 tokens original Apache-2.0

ez-math-model

254

woodfishhhh/EZ_math_model

Skill Claude Code

Use when solving CUMCM, MCM, ICM, or other mathematical modeling tasks that need contest problem intake, model selection, Python solving, figures, paper writing, quality audit, and packaged deliverables.

not rated 41 +2 1mo ago A SkillSpector: pass 48 tokens original MIT

paper-sprint-review

255

RichradsY/PaperSprint

Skill Claude CodeCodex

PaperSprint is a Scrum-inspired academic paper agent workflow for conference or journal drafts. Use when Codex needs to clarify paper direction, estimate likely sprint count, set sprint goals and focus areas, assess venue fit, organize reviewer or editor lenses, convert critique into a prioritized revision backlog…

not rated 40 +1 6mo ago A 94 tokens original MIT

Cai-aa/CAD-Agent-Hub

Skill Codex

Orchestrate evidence-backed ANSYS Workbench and Mechanical structural analyses through a configured MCP, including capability discovery, existing-project or CAD intake, materials, named selections, connections, loads, high-quality mesh planning and repair, solving, convergence diagnosis, deterministic validation, and…

not rated 40 +14 3d ago A 104 tokens copy · 91% MIT

paper-review

257

drpwchen/paper-review-and-digest

Skill Claude CodeCodex

Deep single-paper academic analysis — journal credibility, author profiling, reference verification, citation impact, and critical appraisal. Like a teaching hospital journal club report. Use this skill whenever the user wants to deeply review, evaluate, or dissect a single academic paper, prepare a journal club…

not rated 39 19d ago A SkillSpector: warn 136 tokens original MIT

ericmjl/skills

Skill Claude CodeCodex

Build an awesome marimo notebook that brings a research paper or dataset to life — for competitions, tutorials, demos, or blog companions. Use when asked to "make an awesome marimo notebook," "build a notebook for this paper," "create a competition submission," or pair-program an interactive research explainer on…

not rated 39 10d ago A 71 tokens

vla-expert

259

sou350121/VLA-expert-skill

Skill Claude CodeCodex

A Chinese-language expert guide for deep analysis of vision-language-action systems, which connect visual input and language instructions to robot actions. It contains compressed research knowledge, belief tracking, comparisons, and industry analysis.

not rated 39 11d ago A SkillSpector: warn 122 tokens original MIT

gwas-starter

260

ma-compbio-lab/SkillFoundry

Skill Claude CodeCodex

Use this skill to run a deterministic local pass over GWAS summary statistics, flag common QC issues, and emit a compact interpretation plan for downstream clumping, heritability, and functional follow-up.

not rated 39 +1 4mo ago A 0 tokens original Apache-2.0

tlaplus-from-source

261

tlaplus/AgentSkills

Skill Claude CodeCodex

Generate a high-level TLA+ model from source code (C, C++, Rust, etc.). Analyzes code to understand its purpose, creates abstractions, writes TLA+ specification, and proposes invariants and properties. Use when the user wants to model source code in TLA+, create a formal specification from implementation, or verify…

not rated 37 7mo ago A 79 tokens original MIT

scientific-writing

262

Xevos117/mcp-zotero

Skill Claude CodeCodex

Use this skill whenever the user asks to write a scientific article, literature review, research paper, case report, systematic review, or any academic/scholarly document. Triggers include: "write a paper", "write an article", "literature review", "review article", "case report", "research paper", "scientific…

not rated 37 +1 3mo ago A 141 tokens

thesis-control

263

yha9806/academic-writing-toolkit

Skill Claude Code needs its repo

Use when AI-assisted thesis or manuscript edits risk claim drift, scope creep, loss of intended use, experiment-role promotion, or repeated revisions that fail to converge; provides author-intent control, lightweight or strict contracts, drift audits, revision escalation, and human gates.

not rated 37 +6 changed 4d ago A SkillSpector: pass 57 tokens original MIT

paper_claw

264

PigeonDan1/paper_claw

Skill Claude CodeCodex needs its repo

Fetch, classify, and summarize papers from multiple sources (arXiv, etc.) with AI-powered multi-language summaries and email delivery.

not rated 36 yesterday A SkillSpector: warn 31 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: