Data and AI

16,304 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.

gemma-trainer

98

google-gemma/gemma-skills

Skill Claude CodeCodex

Trigger this skill when the user wants to train, fine-tune, or adapt Gemma models (e.g. SFT, DPO, RLHF, Reward Modeling) on local hardware. Covers TRL, Unsloth, dataset preparation, validation, and GGUF/LiteRT conversion.

not rated 980 +2 1mo ago A 65 tokens original Apache-2.0

YouMind-OpenLab/ai-image-prompts-skill

Skill Claude CodeCodex

Recommend curated prompts from a 10,000+ real-world image generation prompt library. Works with ANY AI image model — Nano Banana Pro, Nano Banana 2, Seedream 5.0, GPT Image 1.5, Midjourney, DALL-E 3, Flux, Stable Diffusion, and more. Use this skill when users want to: Find proven image generation prompts (any model)…

not rated 964 +47 changed today A 137 tokens copy · 89% MIT

d6tflow CLAUDE.md

100

d6t/d6tflow

Instructions file

Instructions for d6t/d6tflow, covering claude.md, what this is, layout, architecture notes that bite and logging (dev notes).

not rated 947 +1 2mo ago A 3,950 tokens original MIT

hf-mem

101

alvarobartt/hf-mem

Skill Claude CodeCodex

Hugging Face CLI to estimate the required memory to load Safetensors or GGUF model weights for inference from the Hugging Face Hub.

not rated 939 1mo ago A 32 tokens copy · 95% MIT

synalinks

102

SynaLinks/synalinks-skills

Skill Claude CodeCodex

Use for anything involving the Synalinks neuro-symbolic LM framework (Keras-inspired) — DataModel/Field/Input, JSON operators (+ & | ^ ), synalinks.ops, LanguageModel/EmbeddingModel and provider prefixes (openai/anthropic/ollama/groq/openrouter/bedrock/...); the Program class and its four building APIs…

not rated 907 12d ago A 290 tokens original Apache-2.0

pdd AGENTS.md

103

promptdriven/pdd

Instructions file CodexOpenCode

Instructions for promptdriven/pdd, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.

not rated 862 +7 11d ago A 604 tokens original MIT

prompt-factory

104

alirezarezvani/claude-code-skill-factory

Skill Claude CodeCodex

World-class prompt powerhouse that generates production-ready mega-prompts for any role, industry, and task through intelligent 7-question flow, 69 comprehensive presets across 15 professional domains (technical, business, creative, legal, finance, HR, design, customer, executive, manufacturing, R&D, regulatory…

not rated 856 +1 9mo ago A 118 tokens original MIT

vllora-data-agent

105

vllora/vllora

Agent

Agent "vllora-data-agent" from vllora/vllora, covering role, workflow, standard analysis (default), light-touch by default and decide focus (based on user intent).

not rated 811 2mo ago A 0 tokens

KylinMountain/TradingAgents-AShare

Skill Claude CodeCodex

A multi-agent analysis tool for stocks listed on China's Shanghai and Shenzhen exchanges, known as A-shares. It combines technical, company, market-sentiment, money-flow, economic, and game-theory analysis into a structured trading view.

not rated 809 +4 2d ago A 138 tokens

enjalot/latent-scope

Instructions file CodexOpenCode

Instructions for enjalot/latent-scope, covering agents.md — driving latent scope for a user, what it is, golden path: run it for a user, the steps in detail and choosing an embedding model.

not rated 792 15d ago A 4,169 tokens original MIT

genai-sdk

108

GoogleCloudPlatform/vertex-ai-samples

Skill Claude CodeCodex

Guides the usage of Gemini API on Google Cloud Vertex AI with the Gen AI SDK. Use when the user asks about using Gemini in an enterprise environment or explicitly mentions Vertex AI. Covers SDK usage (Python, JS/TS, Go, Java, C#), capabilities like Live API, tools, multimedia generation, caching, and batch prediction.

not rated 784 +4 today A 73 tokens original Apache-2.0

team-wiki-codebase

109

Tencent/teamai-cli

Skill Claude CodeCodex ✓ vendor

A codebase-analysis tool that maps large projects across multiple repositories and microservices into structured knowledge, using architecture analysis, code parsing, and a relationship graph.

not rated 788 +73 today A 217 tokens

rag-perf

110

NVIDIA-AI-Blueprints/rag

Skill Claude CodeCodex

Performance benchmarking for a deployed NVIDIA RAG Blueprint server: profiling pass + aiperf load test driven by a single YAML config. Not for accuracy / RAGAS scoring (use rag-eval) or for deploying / repairing services (use rag-blueprint).

not rated 757 +2 yesterday A 56 tokens original Apache-2.0

clawhub

111

MigoXLab/dingo

Skill Claude CodeCodex

Dingo: A Comprehensive AI Data, Model and Application Quality Evaluation Tool.

not rated 753 +3 yesterday A 0 tokens original Apache-2.0

external-repo-setup

112

mims-harvard/AutoScientists

Skill Claude CodeCodex

Protocol for GPU agents to clone external GitHub repos, install their dependencies, download pretrained weights, and integrate them as featurizers or models inside a focus-area train.py. Use this when a proposal references a GitHub repo or pretrained checkpoint that is not already present in the focus-area workspace.

not rated 737 +5 3mo ago A 65 tokens

ima2

113

lidge-jun/ima2-gen

Skill Claude CodeCodex

Use the ima2-gen CLI/server to generate, edit, inspect, and manage local AI image generation jobs.

not rated 739 +16 changed yesterday A 25 tokens original MIT

inference-sh

114

inference-sh/skills

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 724 +6 1mo ago A tokens not measured

PostHog/posthog-foss

Skill Claude CodeCodex

Implement and extend PostHog Data warehouse import sources. Use when adding a new source under products/warehousesources/backend/temporal/dataimports/sources, adding datasets/endpoints to an existing source, or adding incremental sync, resumable imports, webhook ingestion, pagination, credentials validation, and…

not rated 712 +4 changed yesterday A 69 tokens original MIT

yolo-master-agent

116

Tencent/YOLO-Master

Skill Claude CodeCodex ✓ vendor

Use when the user wants to train, validate, predict, track, export, benchmark, tune, inspect, or orchestrate YOLO-Master / Ultralytics experiments in this repository, including LoRA, MoE, multimodal inference/evaluation, and solutions workflows.

not rated 707 +8 today A 60 tokens AGPL-3.0

hailo-optimize

117

hailo-ai/hailo_model_zoo

Skill Claude CodeCodex

Optimize and quantize a parsed Hailo HAR using the Hailo Dataflow Compiler (DFC). Auto-loads a matching ALLS model script from the Model Zoo, prepares calibration data (with the correct normalization alignment), runs optimization on GPU when available, and gates on the post-optimize SNR.

not rated 703 +1 yesterday A 67 tokens original MIT

nuyoah-xiezhen-prompt

118

nuyoah-ai-works/nuyoah-xiezhen-prompt

Skill Claude CodeCodex

A Chinese-language prompt-writing guide for AI portrait photography, including recreating a photo series with a different person and breaking reference images into usable instructions.

not rated 698 +16 9d ago A 97 tokens original MIT

cursorrules

119

DataScienceUIBK/Rankify

Cursor rule Cursor

You are an expert in developing information retrieval, re-ranking, and retrieval-augmented generation (RAG) systems using Python, with a focus on PyTorch and state-of-the-art NLP models.

not rated 681 +1 4mo ago A 1,099 tokens

RAGLight CLAUDE.md

120

Bessouat40/RAGLight

Instructions file

Claude Code instructions for Bessouat40/RAGLight, covering claude.md, commands, install dependencies, run all tests and run a single test module.

not rated 673 +1 2d ago A 983 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: