Scientific

16,357 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.

tuoxie2046/claude-code-research-skills

Skill Codex

Human-in-the-loop research-paper framework figure workflow from S0-PAPER-FOUNDATION through terminal S5-CANDIDATE-IMAGE. Use for paper-grounded architecture, pipeline, method overview, agent workflow, system/data-flow, and mechanism figures with generated raster first-round/formal candidates, reviewer-first-glance…

not rated 5 4mo ago A 258 tokens

manna

962

NSF-Simons-CosmicAI-Institute/manna

MCP server Claude CodeCodexCursor +2

MANNA — MCP Architecture for NOIRLab, NRAO, and Additional Archives. Runs locally from the manna-mcp Python package. Needs 4 environment variables to run.

not rated 5 9d ago A Socket: warn tokens not measured original MIT

braina

963

brainets/braina

Plugin Claude Code

Bundles 5 skills, 1 hook · 647 tokens together

AI-agent-assisted analysis of neural interactions using information-theoretical measures (Frites + HOI) on electrophysiological data (fMRI, MEG, EEG, LFP, MUA).

not rated 5 1mo ago A tokens not measured original BSD-3-Clause

ieee-mcp

964

danieltyukov/ieee-mcp

MCP server Claude CodeCodexCursor +2

MCP server "ieee-mcp" as configured in danieltyukov/ieee-mcp. Runs locally from the ieee-xplore-mcp npm package. Needs 3 environment variables to run.

not rated 5 +2 3d ago A Socket: pass tokens not measured original MIT

iket-profiling

965

humanfia/iket-profiling-skill

Skill Claude CodeCodex

Profile inside a CuTe DSL (cutlass.cute) kernel with IKET (In-Kernel Event Tracing) and the run-iket profiler. Use when developing or tuning a CuTe DSL kernel and you need per-warp timelines of kernel phases (setup, mainloop, epilogue), producer/consumer (TMA/MMA) activity, or time spent in pipeline and mbarrier…

not rated 5 1mo ago A 134 tokens original Apache-2.0

notebook-editing

967

jsamuel1/jupyter-editor-mcp

Skill Claude CodeCodex

Edit Jupyter Notebooks (.ipynb) with the jupyter-editor MCP tools - read, insert, replace, delete, search, batch-edit, merge, split, validate, and manage metadata without a running Jupyter server. Use when the user asks to inspect or change a .ipynb file, refactor notebook cells, clean outputs before a commit, or…

not rated 5 14d ago A 88 tokens original MIT

ztx-exp-manager

968

ztxtech/ztxexp

Skill Codex

Manage ML/LLM experiment workflows with ztxexp. Use when the agent needs to build parameter configurations, run experiments, validate run artifacts, analyze results, or troubleshoot failed runs.

not rated 4 3d ago A 42 tokens original MIT

gis

969

matbel91765/GIS-MCP-Server

MCP server Claude CodeCodexCursor +2

MCP Server for geospatial operations - geocoding, routing, spatial analysis. Runs locally from the locusync-server Python package.

not rated 4 4mo ago A tokens not measured original MIT

lino-veusz-sci-plot

972

LINoone516/lino-agent-skills

Skill Claude CodeCodex

An automation guide for Veusz, a free scientific charting program similar to Origin, using Python scripts.

not rated 4 3mo ago A 71 tokens original MIT

seurat-skill

973

Agents365-ai/seurat-skill

Skill Claude CodeCodex

Comprehensive Seurat v5 (R) guide for single-cell RNA-seq and multimodal analysis. Covers installation, standard workflows (Normalize/SCTransform), clustering, integration (CCA/RPCA/Harmony), differential expression (FindMarkers/FindAllMarkers), visualization (DimPlot/FeaturePlot/VlnPlot/DoHeatmap), spatial…

not rated 4 6mo ago A 167 tokens original MIT

model-reviewer

974

MrSGSA/math-modeling-skill-dify

Skill Codex

An independent red-team review for mathematical models and the code and evidence behind them. Red-team review means actively looking for failures rather than only confirming the author's claims.

not rated 4 3mo ago A 117 tokens original MIT

PaulClawX/research-agent

Skill Codex

Use this skill when the user wants to review, verify, or revise a TeX or PDF research paper by checking whether claims, tables, figures, citations, and conclusions are actually supported by code, experiment runs, logs, and reproducible evidence. The manuscript must not be more confident than the experiments.

not rated 4 5mo ago A 67 tokens

themis

976

arsenelupin14/THEMIS

Skill Claude CodeCodex

Use when the user needs structured research synthesis, literature review planning, cross-domain scientific critique, citation auditing, adversarial review, research dossier generation, or evidence-grounded decision support. Themis creates a research workroom with dynamic specialist agents, citation firewalling, peer…

not rated 4 4mo ago A 71 tokens original MIT

unit-converter

977

khshanovskyi/custom-agent-skills

Skill Claude Code

Converts values between units of measurement across categories: length (km, miles, feet, inches), weight (kg, lbs, oz, stone), temperature (Celsius, Fahrenheit, Kelvin), volume (liters, gallons, cups, ml), area (m², acres, ft²), speed (km/h, mph, knots), time (seconds to years), data storage (bytes to petabytes)…

not rated 4 5mo ago A 110 tokens

elnora

978

Elnora-AI/elnora-plugins

Plugin Claude Code

Bundles 10 skills, 1 command · 1,158 tokens together

AI-powered bioprotocol generation and lab workflow management. Connect to the Elnora AI Platform to generate, optimize, and manage bioprotocols for wet-lab experiments.

not rated 4 changed 10d ago A tokens not measured original Apache-2.0

workbench-sim

979

svd-ai-lab/sim-plugin-workbench

Skill Claude CodeCodex

Use when the user asks Codex, Claude Code, ChatGPT-style coding agents, or another AI agent to connect to Ansys Workbench through sim-cli. Supports Workbench journal execution, project inspection, persistent sessions, Mechanical handoff, bounded execution, artifact reporting, and troubleshooting. Requires a user-owned…

not rated 4 changed 26d ago A 70 tokens copy · 88% Apache-2.0 archived

wiki-experiment

982

crcresearch/llm-wiki-memory-template

Skill Claude Code

File experiment results to the wiki following the SCHEMA Ingest procedure. Use after an experiment run produces metrics, ablations, or comparisons worth keeping as durable project memory.

not rated 4 22d ago A 38 tokens

Rebell-Leader/SpatialAI_MCP

Cursor rule Cursor

Author or modify a Viash component (config.vsh.yaml + script) for an OpenProblems method, especially a taskistpreprocessing stage. Use when the user wants to add/implement a spatial method, scaffold a component, or fix a config.vsh.yaml.

not rated 4 4mo ago A 55 tokens original Apache-2.0

physlibsearch

984

Kernel-Science/physlibsearch-skill

Skill Claude CodeCodex

Semantic search over Physlib, a formal Lean 4 library of physics theorems and definitions. Use when asked to find Lean 4 declarations related to physics or mathematics, look up formal proofs, retrieve theorem signatures, or browse the Physlib module hierarchy.

not rated 4 6mo ago A 56 tokens

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: