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.
Mirannonarbitrable290/agentic-kaggle-skill
Skill Claude CodeCodex
AI Agent-driven Kaggle competition workflow. Learn from real competition experience: score stabilization patterns, submission troubleshooting, kernel workflows, GPU task delegation, and the spec-driven development approach that achieved top leaderboard positions. Use when: working on any Kaggle competition, analyzing…
Skill Claude CodeCodex
Translate between NLPCore and NARS through BrainClient/ModelMux while preserving an immutable Hermes transcript CID and its CoreNLP sentence/dependency record.
MCP server Claude CodeCodexCursor +2
A locally running retrieval-augmented generation (RAG) service. RAG helps an AI find relevant information from a knowledge collection before answering.
pixeltable/mcp-server-pixeltable-developer
MCP server Claude CodeCodexCursor +2
MCP server "mcp-server-pixeltable-developer" as configured in pixeltable/mcp-server-pixeltable-developer. Runs locally from the mcp-server-pixeltable-developer Python package. Needs 2 environment variables to run.
MCP server Claude CodeCodexCursor +2
MCP server "danbooru-rag-mcp" as configured in Zaozaotvk40/danbooru-rag-mcp. Runs locally from the danbooru-rag-mcp Python package.
Plugin Claude Code
Bundles 16 skills, 25 commands, 1 agent, 1 hook · 2,493 tokens together
AI/LLM development toolkit - 16 skills, 1 agent, 25 commands for AI-native development patterns.
Skill Claude CodeCodex
Use Chutes.ai from Hermes for model discovery, routing, account/API-key guidance, and OpenAI-compatible inference. Prefer the live models endpoint for current availability and capabilities.
Skill Claude CodeCodex
Process large volumes of requests using Gemini Batch API via scripts/. Use for batch processing, bulk text generation, processing JSONL files, async job execution, and cost-efficient high-volume AI tasks. Triggers on "batch processing", "bulk requests", "JSONL", "async job", "batch job".
Cursor rule Cursor
Before generating or modifying any prompt.
Skill Claude CodeCodex
Guard and improve prompts before expensive Codex, IDE, or CLI agent work. Use when a prompt is vague, broad, risky, costly, or should be optimized before implementation.
Skill Claude CodeCodex needs its repo
Configure and deploy Workload Variant Autoscaler (WVA) for llm-d inference deployments. Guides users through namespace selection, WVA repo location, configuration (with presets or custom values), deployment via Makefile + kubectl apply, and verification. Produces a reusable deployment script.
aeren23/image-processing-skills
Skill Claude CodeCodex
YOLO detection, segmentation, classification, and pose estimation setup, training workflow, evaluation metrics, and XAI verification.
pluginagentmarketplace/custom-plugin-data-engineer
Plugin Claude Code
Bundles 21 skills, 7 commands, 6 agents · 733 tokens together
Comprehensive data engineering plugin with 6 agents and 21 skills covering Python, SQL, ETL, big data, cloud platforms, machine learning, and MLOps.
Skill Claude CodeCodex
A team workflow for solving mathematical modelling problems with code, including analysis, model selection, computation, plots, and reproducibility notes.
Skill Claude Code
Automatically refines every user prompt into a structured, actionable version, then immediately executes the optimized prompt. When triggered explicitly with "/optimize {prompt}", "optimize:", or "optimize prompt:", outputs the refined prompt as text instead.
Skill Claude CodeCodex
Build AI agents with structured access to Sanity content via Sanity Context. Use when setting up a Sanity-powered chatbot, connecting an AI assistant to Sanity content, or adding client-side tools to an agent. Covers MCP endpoint setup in the Context app or with the Sanity CLI (GROQ mode over a dataset, or Knowledge…
k-vaca/prompt-engineering-skill
Skill Claude CodeCodex
Write, review, and optimize professional prompts for large language models. Use this skill whenever the user asks to write, draft, design, improve, fix, debug, review, or optimize a prompt, system prompt, prompt template, meta-prompt, or agent instructions; asks why a prompt "isn't working" or gives inconsistent…
MCP server Claude CodeCodexCursor +2
MCP server for Google's Gemini 2.5 Flash Image generation API with cross-platform support. Runs locally from the nano-banana-mcp npm package.
stevengonsalvez/promptregistry-mcp
MCP server Claude CodeCodexCursor +2
A Model Context Protocol server for managing prompts via stdio. Runs locally from the mcp-promptregistry npm package.
Plugin Claude Code
Bundles 8 skills · 532 tokens together
Materialization skills for PostgreSQL, Snowflake, BigQuery, Redshift, Databricks, ClickHouse, HubSpot, and any destination connector.
Skill Claude CodeCodex needs its repo
Kedro deployment guidance for Databricks. Use when choosing between Git folders, Databricks Connect and Declarative Automation Bundles (DABs, formerly Databricks Asset Bundles), packaging a Kedro project as a wheel, generating or editing a bundle with kedro-databricks, getting conf and environments onto Databricks…
Plugin Claude Code
Bundles 1 skill, 2 commands, 2 agents, 2 hooks · 363 tokens together
Multimodal RAG, video search, image similarity search, agent memory, and embeddings stored with your data. Tables, computed columns, vector search, and video, audio, image, and document pipelines.
stefanskiasan/togetherai-image-mcp-server
MCP server Claude CodeCodexCursor +2
MCP server "togetherai-image-server" as configured in stefanskiasan/togetherai-image-mcp-server. Runs locally from the togetherai-image-server npm package.
samibajwaisking/Token-Optimizer-Skill
Skill Claude CodeCodex
Maximize Claude's output quality while minimizing input token usage. Use this skill whenever a user wants to compress prompts, reduce token consumption, extract maximum output from Claude, write high-density instructions, optimize system prompts, or improve AI communication efficiency. Trigger on phrases like…
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: