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.
PSkinnerTech/brainlift-writer-skill
Skill Codex
Guide for drafting, revising, and evaluating BrainLifts: AI-ready knowledge documents that move from purpose and scope to experts, DOK 2 knowledge trees, DOK 3 insights, and DOK 4 spiky points of view. Use when asked to create a BrainLift, improve BrainLift writing style, transform notes or research into structured AI…
DanielTomaro13/sportsdata-agents
Skill Claude CodeCodex
The general model-building method for ANY market — framing, sample-size discipline, feature selection (user priors + data-driven), baselines, leakage-safe validation, calibration, persistence.
sfc-gh-chathomas/streaming-log-analytics-vhol
Skill Claude CodeCodex
Build the Snowmart real-time log analytics pipeline for the Snowpipe Streaming + Dynamic Tables VHOL. Loads the exact object model, naming, and DDL patterns so short prompts produce consistent objects. Use when: building the streaming pipeline, Bronze/Silver/Gold, semantic view, SRE agent, or dashboard for this lab.…
Skill Claude CodeCodex
Drive the 启智 platform (qz.sii.edu.cn) from the command line — log in via CAS, browse projects/workspaces, enumerate legal compute-group/spec/image options, validate and submit training jobs, and list/inspect/stop jobs. Use whenever a task involves submitting or managing jobs on qz.sii.edu.cn, or reading its compute…
Skill Claude CodeCodex
Use the local LLM endpoint proxy (localhost:18090) — or your own gated public deployment — to route Claude Code / Claude SDK through custom providers (OpenRouter, Moonshot, Groq, ZAI) via an Anthropic-compatible gateway. Covers adapter-specific behaviors, auth patterns, proxy codenames, and common failure modes.
MCP server Claude CodeCodexCursor +2
x402 pay-per-use MCP server for IBM Granite AI — chat, code, embeddings, analysis, and time-series forecasting. Pay USDC on Solana per call. No IBM Cloud account required. Runs locally from the @three-ws/ibm-x402-mcp npm package. Needs 9 environment variables to run.
gbeyrouti/seedance-prompting-claude-skill
Skill Claude CodeCodex
Expert prompt engineering pour Seedance 2.5 (ByteDance / Dreamina / Jimeng / Doubao), modèle vidéo 30 s en une passe, audio natif, 50 références max. Utiliser dès que l'utilisateur veut écrire, optimiser ou déboguer un prompt Seedance (2.5 ou 2.0), générer une vidéo avec Seedance/Dreamina/Jimeng, faire du…
Skill Claude CodeCodex
Use when improving prompts for any LLM. Applies proven prompt engineering techniques to boost output quality, reduce hallucinations, and cut token usage.
Plugin Claude Code
Bundles 1 skill, 1 command, 1 MCP server · 67 tokens together
Local hybrid-RAG (BM25 + vector + rerank) over files and folders on your machine. Indexing and search run locally; answers are written by a hosted model through OpenRouter, so a question and its retrieved passages leave the device.
Skill Claude CodeCodex
Navigate SAP's AI technology landscape and guide implementation of AI use cases on SAP BTP. Use when someone asks which AI approach to use on SAP, how to build AI apps, agents, or ML models on SAP BTP, or needs guidance on SAP AI Core, Joule, Generative AI Hub, HANA Cloud ML, RPT-1, Document AI, or Joule Skills. Also…
Plugin Claude Code
Bundles 23 skills, 1 command, 1 agent · 2,838 tokens together
Professional AI/ML research-engineer workflow: research papers first, pick the best method for each problem (computer vision, medical imaging, NLP/LLM, tabular, time-series, audio and speech, recommendation, generative, reinforcement learning, graph, multimodal, video, 3D, and anomaly detection), train and fine-tune…
Cursor rule Cursor
When creating prompts for AI tools, follow this structure.
comeonzhj/comeonzhj-claude-plugins
Plugin Claude Code
Bundles 2 commands · 41 tokens together
A set of tools for analysing AI projects. Its description says it examines how open-source projects design prompts and skills.
jamesgray-ai/handsonai-plugins
Plugin Claude Code
Bundles 16 skills · 2,254 tokens together
Everything you need to design, build, and document AI workflows. The AI Workflow Framework as executable skills, plus your business knowledge graph, an AI registry, and a feature-spec toolkit.
Plugin Claude Code
Bundles 6 skills, 23 commands · 703 tokens together
Cross-domain knowledge graph framework. Extract structured knowledge from any document corpus. Pre-built domains: drug discovery (biomedical literature), contract analysis (vendor contracts), clinical trials (ClinicalTrials.gov v2 + PubChem enrichment via --enrich), and FDA product labels (Structured Product Labeling.
Skill Claude CodeCodex
A skill for examining images with GLM-4V Flash, an AI model that can recognize image content and read text.
MCP server Claude CodeCodexCursor +2
MCP server "mcp-emtrafesa" as configured in georgegiosue/mcp-emtrafesa. Launched with bun src/index.ts.
MCP server Claude CodeCodexCursor +2
MCP Server for LightRAG with smart document upsert capabilities. Runs locally from the mcp-lightrag Python package.
MCP server Claude CodeCodexCursor +2
MCP server for Apache Flink SQL Gateway. Runs locally from the flink-mcp Python package.
MCP server Claude CodeCodexCursor +2
Symbol-aware, staleness-tracking RAG over a codebase, exposed over MCP; layers on rag-timetravel. Runs locally from the codebase-rag Python package.
Skill Claude CodeCodex
Health-check the LLM Wiki and offer fixes for each category of finding. Use when the user says "lint the wiki", "audit the wiki", "check wiki health", "clean up the wiki", or after a batch of ingests. Categories covered - orphans, broken links, stale sources, missing pages, tag drift, index parity.
Plugin Claude Code
Bundles 18 skills, 8 agents, 1 hook, 1 plugin · 1,676 tokens together
A retrieval architecture that pre-projects sources to task domains at ingestion time. Runtime becomes lookup, not reshape. Ships skills for ingesting sources under a 9-pass source-only protocol, retrieving via two-layer indexes (corpus catalogue + per-task distillation indexes), and a PreToolUse hook that enforces…
MCP server Claude CodeCodexCursor +2
MCP server for vLLM - expose vLLM capabilities to AI assistants. Runs locally from the vllm-mcp-server Python package.
Youchu-lawhub/legal-kb-builder
Skill Claude CodeCodex
A tool for turning legal documents and other source material into a searchable local knowledge base. It supports sources such as PDF, DOCX, images, Markdown, and question-and-answer sets.
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: