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.
captain-marketing/persona-synthetique
Plugin Claude Code
Bundles 6 skills · 759 tokens together
Transforme tes données clients en personas vivants, simulables et évolutifs. Crée, valide, simule et affine des personas synthétiques à partir de transcriptions AI Notetaker et données clients réelles.
Skill Claude CodeCodex
Use when user asks to improve, refine, or rewrite a prompt for an AI system, or when framing a request that feels vague, overloaded, or logically unsound. Triggers: "improve my prompt", "rewrite this prompt", "make this prompt better", "help me ask this question properly", "this prompt feels off".
dianaprior/kaggle-competition-agent-skill
Skill Claude Code
Run a TabPFN classification baseline, generate the first submission, rapidly probe features, then optimize with GBT ensembles, threshold tuning, and calibration. Use after tabpfn-explore has prepared the data and CV folds.
gquattromani/prompt-best-practices
Cursor rule Cursor
Prompt Best Practices, structure an underspecified prompt before executing it. 7 components, 3 tiers, smallest sufficient prompt.
Plugin Claude Code
Bundles 1 skill · 55 tokens together
haystack-skills. A curated collection of AI agent skills for the Haystack ecosystem.
dungnotnull/ai-coastal-erosion-monitoring-agent-skill
Skill Claude CodeCodex
AI-Based Coastal Erosion Monitoring & Alert — Production-grade harness for Coastal Erosion Remote Sensing & AI Monitoring evidence-backed analysis with 6-step workflow (requirements→evidence→core analysis→knowledge→synthesis→quality gate). Use for shoreline change detection, beach/dune erosion analysis, storm impact…
isabela-valonni/prompt-evaluator
Plugin Claude Code
Bundles 1 command · 13 tokens together
A quiet prompting coach. Scores how you ask, names one thing to sharpen, and remembers your recurring patterns across sessions so the feedback compounds. Works for anyone using AI — not tied to any one domain.
Command Claude Code
Evaluate a prompt for clarity and effectiveness.
Skill Claude CodeCodex
Reference portfolio demonstrating Azure data engineering patterns, Medallion architecture, and end-to-end analytics solutions.
dungnotnull/mangrove-forest-ai-conservation-agent-skill
Skill Claude CodeCodex
AI-Based Mangrove Forest Monitoring & Conservation — Professional-grade harness for evidence-backed mangrove forest analysis with remote sensing, deforestation detection, health assessment, blue carbon estimation, and restoration planning. Use this skill when users mention mangrove forests, coastal ecosystems…
Plugin Claude Code
Bundles 1 skill · 241 tokens together
Autonomous biomedical data analysis using a multi-agent pipeline inspired by BioMedAgent (Nature Biomedical Engineering, 2026). Handles omics, precision medicine, machine learning, statistics, and visualization from natural language instructions.
MCP server Claude CodeCodexCursor +2
Model Context Protocol (MCP) server for PyTorch Lightning. Runs locally from the lightning-mcp Python package.
Plugin Claude Code
Bundles 4 commands, 1 hook · 47 tokens together
Rescues messy, typo-ridden, or half-formed prompts so Claude understands you the first time. Confirms its reading with a one-line '✓ understood · …' and keeps reviewable history and stats.
MCP server Claude CodeCodexCursor +2
A locally run MCP-based retrieval-augmented generation service. Retrieval-augmented generation, or RAG, lets an AI use information retrieved from a separate knowledge source when generating answers.
adrunkhuman/marimo-opencode-skill
Skill Claude CodeCodex
Author interactive reactive Python notebooks with marimo. Covers interactive cell execution, reactive UI, SQL, state management, deployment, and export. For interactive notebooks, NOT Cell.run() API.
MCP server Claude CodeCodexCursor +2
MCP server "mcp-prompt-manager" as configured in Tae4an/mcp-prompt-manager. Runs locally from the mcp-prompt-manager npm package.
MCP server Claude CodeCodexCursor +2
MCP server for retrieving context from a Qdrant vector database. Runs locally from the mcp-server-qdrant Python package. Needs 4 environment variables to run.
MCP server Claude CodeCodexCursor +2
MCP server for Venice AI - chat, images, TTS, embeddings, and account management. Runs locally from the venice-mcp npm package.
Plugin Claude Code
Bundles 26 skills · 1,734 tokens together
Agent user-scale for user vector search: scaling, performance optimization, search quality, monitoring, deployment, model migration, version upgrades, and SDK usage.
MCP server Claude CodeCodexCursor +2
MCP server exposing 60+ open data providers to LLM clients via intelligent metadata routing. Runs locally from the meta-data-mcp Python package.
MCP server Claude CodeCodexCursor +2
Academic paper knowledge-base MCP tool with ingest, retrieval and chat over your document corpus. Runs locally from the scholar-rag-mcp Python package. Needs 4 environment variables to run.
maddataanalyst/knowledge-graph-extract
Plugin Claude Code
Bundles 1 skill · 64 tokens together
Extract knowledge graphs (subject-relation-object triplets) from document folders, with schema enforcement, resumable chunked extraction, and Cypher generation for Neo4j/Memgraph.
topprismdata/cultivating-ml-agent
Skill Claude CodeCodex
A guide for running Kaggle competitions, an online platform where people build models against shared datasets, and organizing research in a searchable NotebookLM knowledge base.
DefaultHQ/build-support-agent-skill
Skill Claude Code
Plan and build a production customer-support agent — a RAG product-Q&A bot that drafts replies, posts them for human review, and graduates to controlled autonomy. Use when someone wants to build an in-house support agent, a Slack-native or support-platform AI bot, a ticket-answering / customer-Q&A agent, or wants to…
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: