Data and AI

14,252 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.

jayll1303/AIEKit

Skill

Fine-tune and align LLMs locally with HuggingFace Trainer, TRL, PEFT. Use when configuring TrainingArguments, applying LoRA or QLoRA, running SFT/DPO/GRPO alignment, estimating VRAM requirements, debugging OOM errors, or setting up gradient checkpointing.

not rated 18 5mo ago A 68 tokens

shibuiwilliam/mcp-server-scikit-learn

MCP server Claude CodeCodexCursor +2

MCP server "mcp-server-scikit-learn" as configured in shibuiwilliam/mcp-server-scikit-learn. Runs locally from the mcp-server-scikit-learn Python package.

not rated 18 1y ago A tokens not measured original MIT

arckit.jsp-936

581

tractorjuice/arckit-codex

Command Claude Code

Generate MOD JSP 936 AI assurance documentation for defence AI/ML systems.

not rated 18 changed 10d ago A 14 tokens

goal-test

582

restarter/lets-workflow

Skill Claude Code

A local experiment for testing a goal command that keeps an AI coding session working until a stated condition is judged complete. It uses a separate language model to evaluate the conversation after each assistant turn.

not rated 17 3d ago A SkillSpector: warn 137 tokens original MIT

visionary-cli

583

xlight/deepseek-visionary

Skill Claude CodeCodex

Analyze images with DeepSeek's vision model via the visionary-server CLI. Use this whenever the user provides an image, photo, screenshot, or document with images - run vision to look at it rather than guessing.

not rated 17 5d ago A 46 tokens

promptheus

584

abhichandra21/Promptheus

MCP server Claude CodeCodexCursor +2

AI-powered prompt engineering CLI tool. Runs locally from the promptheus Python package. Needs 8 environment variables to run.

not rated 17 24d ago A tokens not measured original MIT

mcp-docs-rag

585

kazuph/mcp-docs-rag

MCP server Claude CodeCodexCursor +2

MCP server "mcp-docs-rag" as configured in kazuph/mcp-docs-rag. Runs locally from the @kazuph/mcp-docs-rag npm package.

not rated 17 1y ago A tokens not measured

PatrickGallucci/fabric-skills

Skill Claude CodeCodex

Diagnose and resolve Microsoft Fabric Dataflow Gen2 performance issues including slow refresh times, Fast Copy optimization, query folding failures, staging bottlenecks, gateway latency, incremental refresh tuning, capacity throttling, and data destination write performance. Use when troubleshooting dataflow refresh…

not rated 17 5mo ago A 118 tokens original MIT

forge

587

yz5e/agent-skills

Skill Claude CodeCodex

Forge a coding or agentic prompt optimized for Claude Opus 4.7 or GPT-5.5 (Codex CLI) by interviewing the user with structured multiple-choice questions, then writing a precise XML-tagged prompt and optional SPEC.md handoff. Use whenever the user asks to write a prompt, scope a coding task, design a system prompt for…

not rated 17 6mo ago A 0 tokens original MIT

fluentlc/shiny-skills

Skill Claude CodeCodex needs its repo

A prompt-writing guide that turns a simple image idea, visual style, and optional aspect ratio into a structured prompt for AI image generators.

not rated 17 5mo ago A 79 tokens original MIT

model-vision-skill

590

yan-stone-computer/ModelVisionSkill

Skill Codex

Give text-only LLMs (DeepSeek, Xiaomi MiMo, GLM-4.5, MiniMax, Llama 3.x, etc.) eyes by analyzing images, screenshots, UI captures, diagrams, charts, and OCR documents through free multi-modal APIs with automatic engine fallback and caching. Images are handled by the browser-driven web engines FIRST (Doubao, Kimi…

not rated 17 2mo ago A 235 tokens original MIT

prompts-mcp-server

591

tanker327/prompts-mcp-server

MCP server Claude CodeCodexCursor +2

MCP server for managing and providing prompts. Runs locally from the prompts-mcp-server npm package.

not rated 17 1y ago A tokens not measured original MIT

majia-guanyuan

592

maojiebc/majia-guanyuan

Skill Claude CodeCodex

A practical extension layer for Guandata BI, a business-intelligence platform used to query data, build charts, and publish dashboards. It covers advanced data-pipeline work and custom HTML, CSS, and JavaScript dashboards beyond the standard tools.

not rated 17 changed 4d ago A 275 tokens original MIT

model-ledger

593

block/model-ledger

MCP server Claude CodeCodexCursor +2 ✓ vendor

Developer-first model inventory and governance framework for SR 11-7, EU AI Act, and NIST AI RMF compliance. Runs locally from the model-ledger Python package.

not rated 17 1mo ago A tokens not measured original Apache-2.0

inference-sh

594

skills-101/superpowers

Plugin Claude Code

Bundles 86 skills · 9,995 tokens together

AI agent skills for models via inference.sh CLI - generate images with FLUX, create videos with Veo, call LLMs, search the web, and more.

not rated 17 3mo ago A tokens not measured fork

voltagent-skills

595

VoltAgent/skills

Plugin Claude Code

Bundles 4 skills · 97 tokens together

Skills for building AI applications with VoltAgent: project setup, best practices, core reference, and embedded docs lookup.

not rated 17 +1 9mo ago A tokens not measured original MIT

geo-infer

596

ActiveInferenceInstitute/GEO-INFER

Skill Claude CodeCodex

Geospatial Active Inference framework with 45 modules for ecological, civic, and commercial spatial analysis. Use when working with geospatial data, Active Inference, Bayesian modeling, H3 hexagonal indexing, spatial statistics, or any domain-specific geographic analysis (agriculture, health, economics, risk, climate…

not rated 17 changed 1mo ago A 76 tokens

Jill0099/causal-inference-mixtape

Skill Claude CodeCodex

This skill should be used when the user asks to "implement a DiD regression", "run a staggered difference-in-differences", "set up an event study", "implement IV / 2SLS", "run a regression discontinuity design", "build synthetic control", "do propensity score matching", "test parallel trends", "run Honest DiD", "wild…

not rated 17 2mo ago A 209 tokens original MIT

langgraph-rag-mcp

598

pedarias/langgraph-rag-mcp

MCP server Claude CodeCodexCursor +2

MCP server "langgraph-rag-mcp" as configured in pedarias/langgraph-rag-mcp. Runs locally from the langgraph-rag-mcp Python package.

not rated 17 +1 1mo ago A tokens not measured

rd-author

600

Merck/ReactiveDynamics.jl

Skill Claude CodeCodex

Phase 2 of an rd-study — compile a decision brief into a ReactiveDynamics model document (.rdj.json), one file per experimental arm, and iterate to zero validation diagnostics. Covers places, transitions, arcs, the three modality axes, structured tokens, expression nodes, and the host.jl registry seam. Use after…

not rated 17 25d ago A 75 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: