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.

syntx-ai-mcp-usage

721

ssm82/syntx-ai-mcp

Skill Claude CodeCodex

Operates the syntx.ai MCP tools (chat, ask, stream-message, files, design, audio, video, folders, auth, model catalog). Use when calling syntx-ai-mcp tools and the JSON schema alone is insufficient — long prompts that exceed the default ask timeout, model identifier selection, chat lifecycle (create / continue /…

not rated 11 changed 6d ago A 101 tokens original MIT

dbt-agent-readiness

722

GetCassis/dbt-agent-readiness

Plugin Claude Code

Bundles 1 skill · 126 tokens together

Audit a dbt project for what an AI agent will get wrong if you point it at the data today: wrong metric, wrong table, missed rows, broken joins. Produces one evidence-backed report with blockers, verification queries, and a safe starting perimeter.

not rated 11 2mo ago A tokens not measured original MIT

writing-prompts

723

ylxmf2005/Longrein

Skill Claude CodeCodex

A guide for writing, rewriting, and reviewing prompts and instructions for coding agents. It examines how each sentence affects what an AI model produces, including files such as AGENTS.md and skill instructions.

not rated 11 1mo ago A 66 tokens

fable-prompt-pass

724

mvresh/fable-prompt-pass

Plugin Claude Code

Bundles 1 skill · 117 tokens together

Adapt any prompt to fit Claude Fable 5 (claude-fable-5) without losing its meaning: optimize structure per Fable's prompting guidance, clarify legitimate intent to avoid false-positive refusals, and flag mechanical API incompatibilities.

not rated 10 +3 3mo ago A tokens not measured original MIT

job_health

725

DeepLink-org/probing

Skill Claude CodeCodex

Job-level health: cluster alive, step lag, slowdown proxy, comm trend.

not rated 10 13d ago A SkillSpector: pass 19 tokens original Apache-2.0

prompt

726

gpaiva00/pt-prompt

Skill Claude CodeCodex

Use when translating Brazilian Portuguese messages into English prompts for Claude Code — preserves intent, clarifies ambiguity, and surfaces urgency signals that colloquial Portuguese would lose.

not rated 10 4mo ago B 33 tokens

pytorch-train

727

Axect/pytorch_template

Skill Claude Code

Guide for training PyTorch models using this template's config-driven pipeline. Use this skill whenever the user wants to: train a model, create experiment configs (run.yaml / opt.yaml / best.yaml), run hyperparameter optimization (HPO) with Optuna, extract best parameters from an HPO study, set up a new experiment…

not rated 10 6mo ago A 127 tokens original MIT

notebookmd

728

minhlucvan/notebookmd

Skill Claude CodeCodex

Skill "notebookmd" from minhlucvan/notebookmd, covering notebookmd — ai agent data analysis skill, quick start, installation, when to use this skill and core concepts.

not rated 10 6mo ago A 0 tokens original MIT

ShayIsso/trajectory-auditor

Skill Claude CodeCodex

Safeguard LLM calls using adaptive/extended thinking against token truncation. Use this skill when configuring API parameters for reasoning models (like Claude 3.7 Sonnet), when structured JSON outputs are returned unparseable or incomplete, or when designing cost-sensitive pipelines that utilize LLM reasoning.

not rated 10 2mo ago A 68 tokens

jupyter

730

jrgleason/embeddings-demystified

MCP server Claude CodeCodexCursor +2

One of 3 in .mcp.json

MCP server "jupyter" as configured in jrgleason/embeddings-demystified. Runs in Docker (datalayer/jupyter-mcp-server:latest). Needs 2 environment variables to run.

not rated 10 5mo ago A tokens not measured

data-liberation

731

CUPIDS-Lab/data-liberation-skill

Skill Claude CodeCodex

Build Python data pipelines that liberate structured data from unstructured and semi-structured sources — government PDFs, FOIA releases, scanned reports, scraped HTML, panel-format spreadsheets — into tidy, documented, reproducible civic datasets. Works at six escalating levels, from a one-shot "just give me the CSV"…

not rated 10 4mo ago A 263 tokens original MIT

sloemo01/hermes-skills-bundle

Skill Claude CodeCodex

World-class prompt analyzer v3: multi-modal, predictive, self-improving, context-aware, with real-time cost estimation, counterfactual reasoning, cross-session learning, adversarial testing, and autonomous optimization.

not rated 10 3mo ago A 49 tokens original MIT

openrouter-mcp

734

physics91/openrouter-mcp

MCP server Claude CodeCodexCursor +2

A Model Context Protocol (MCP) server for OpenRouter API with Collective Intelligence - Multi-model consensus, ensemble reasoning, and collaborative problem solving. Runs locally from the @physics91/openrouter-mcp npm package.

not rated 10 1mo ago A tokens not measured original MIT

tiro

735

plato-corp/skills

Plugin Claude Code

Bundles 7 skills · 368 tokens together

LLM Wiki suite from the Tiro team — bootstrap, ingest, query, lint, socratic, sync. A persistent, agent-maintained personal knowledge base.

not rated 10 13d ago A tokens not measured original MIT

unified-ai-gateway

736

happy520ai/unified-ai-system

Skill Codex

Operate and evaluate Unified AI System through fifteen governed MCP tools, including provider-free prompt enhancement, while preserving fake-provider, authorization, and evidence boundaries.

not rated 10 changed 1mo ago A SkillSpector: warn 35 tokens original Apache-2.0

river

737

riverai-org/river-skills

Plugin Claude Code

Bundles 1 skill · 160 tokens together

Agent skills for the River API — write correct training scripts with the river-client Python package: LoRA fine-tuning, SFT, and RL/GRPO on River-hosted models.

not rated 10 1mo ago A tokens not measured original Apache-2.0

create-ai-provider

738

markconroy/markie

Skill Claude CodeCodex

Scaffolds a new AI Provider plugin for the Drupal AI module. Asks which operation types the provider supports (chat, embeddings, text-to-image, etc.), then generates the plugin class with the correct interface implementations, authentication setup, and model discovery.

not rated 10 4d ago A 55 tokens GPL-2.0

llm-app-patterns

739

bugrabilge/bilge-development-kit

Skill Claude CodeCodex

Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, AI assistant design, prompt management, LLMOps monitoring, conversational interfaces, and context management.

not rated 10 6mo ago A 42 tokens original MIT

ultralytics-mcp

740

amanharshx/ultralytics-mcp

MCP server Claude CodeCodexCursor +2

MCP server for Ultralytics Platform projects, datasets, training, prediction, exports, and models. Runs locally from the ultralytics-mcp npm package. Needs 2 environment variables to run.

not rated 10 2d ago A Socket: warn tokens not measured original MIT

upstage-ai

741

UpstageAI/upstage-extensions-hub

Plugin Claude Code

Bundles 9 skills · 1,011 tokens together

Official Upstage AI bundle for Claude Code — Solar models, document processing (OCR, parse, classify, extract), schema generation, Studio agent workflows, multi-API builder for webapps, and the BotMadang community client. One install activates all 9 skills with auto-trigger by description.

not rated 9 6mo ago A tokens not measured original MIT

dataproc-mcp-server

742

dipseth/dataproc-mcp

MCP server Claude CodeCodexCursor +2

A production-ready Model Context Protocol (MCP) server for Google Cloud Dataproc operations. Provides intelligent defaults, comprehensive tooling, and seamless integration with Roo (VS Code) for big data workflows. Runs locally from the @dipseth/dataproc-mcp-server npm package.

not rated 9 11mo ago A tokens not measured original MIT

aicontext-ingest

743

SophonMe/AIContext

Skill Claude CodeCodex

Implement data source ingestion for AIContext. Explore a user's data export, identify ingestible sources, and write DataSource classes to parse them.

not rated 9 6mo ago A 34 tokens original MIT

local-knowledge-rag

744

patakuti/local-knowledge-rag-mcp

MCP server Claude CodeCodexCursor +2

MCP server "local-knowledge-rag" as configured in patakuti/local-knowledge-rag-mcp. Runs /path/to/local-knowledge-rag-mcp/dist/mcp-server.js with node. Needs 3 environment variables to run.

not rated 9 27d 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: