xai-grok
721Skill Claude Code
Access xAI's Grok APIs through the MCP server.
not rated 1 7mo ago A 101 tokens
qmcp-manager
722Skill Claude CodeCodex
Qdrant MCP Server management and diagnostics skill. Use whenever working with the qmcp (QDrant MCP Server) project for semantic code search. Activates on queries about: Qdrant database state, collections, or indexed content Cleaning up vector database (orphans, stale vectors, missing files) Understanding what's…
not rated 1 5mo ago A 146 tokens
original Apache-2.0
vision-router
723Skill Claude CodeCodex
Analyze images through the vision-router MCP server using a user-selected BYOK cloud vision model (Gemini, Qwen VL / DashScope, SiliconFlow, OpenRouter, or any OpenAI-compatible vision API), then reason over the structured result. Use whenever an answer depends on image content and the current model cannot see images…
not rated 1 1mo ago A 69 tokens
original MIT
glm-vision
724Skill Claude CodeCodex
A skill that gives text-only AI models access to image understanding through the GLM-4.6V-Flash vision model. It can work with images, screenshots, charts, scanned pages, documents, and image URLs.
not rated 1 1mo ago A 159 tokens
vision-extension
725Skill Claude CodeCodex
Use this skill for ANY interaction with vision-extension (the open-source vision pack at github.com/loudMore/vision-extension, containing the vision-extension MCP server) — installing/configuring it, calling its tools (mcpvision-extensiondescribeimage, mcpvision-extensioncompareimages, mcpvision-extensionextracttext)…
not rated 1 2mo ago B 273 tokens
original MIT
Unity-Billal-mesloub/mcp-documentation-server
Skill Claude CodeCodex
Use when you need to store, retrieve, search, or manage documents in a local knowledge base with semantic search and hybrid (vector + full-text) retrieval. Also use when interacting with the documentation server web interface, managing uploads, or performing AI-powered document analysis. Use this instead of MCP-native…
not rated 1 17d ago A 71 tokens
Skill Claude CodeCodex
Use this skill whenever the user is doing ML experiment work in a projtool-managed repo — that is, requests involving training, runs, manifests, reports, mutagen sync, AutoDL instances, GPU provisioning, experiment branches, worktrees, image builds, research threads / lineage / the docs registry, or projtool tool…
not rated 1 29d ago A 206 tokens
original MIT
Maha-Strategies/maha-mcp-bridge
Skill Claude CodeCodex
Pre-inference prompt compression middleware that reduces document and prompt token payloads by 74% prior to calling LLMs. Use this tool when prompt context exceeds 10,000 tokens to cut LLM input token costs on Base Mainnet.
not rated 1 1mo ago A 55 tokens
original MIT
omni-inference
729Skill Claude CodeCodex
The core OpenAI-compatible inference endpoints: chat completions, embeddings, images, audio (TTS/STT), moderations, rerank, and the Responses API. The primary integration surface for AI agents.
not rated 1 today A 47 tokens
original MIT
guardian-mcp
730Skill Claude CodeCodex
Use Guardian MCP tools to monitor, intervene, and analyze ML training. Covers 35 tools across monitoring, checkpoint analysis, recovery, dashboard config, and cross-experiment queries. Use when the user asks about training status, anomalies, checkpoints, experiments, model analysis, or when Guardian MCP server is…
not rated 1 16d ago A 65 tokens
original MIT
JayceVane/visual-understanding
Skill Claude Code
Multi-provider visual understanding tool for images, videos, and documents. Supports captioning, OCR, visual Q&A, document analysis, and object grounding (bounding-box localisation) through configurable providers (Zhipu GLM-V, OpenAI GPT-4o, Anthropic Claude, or any OpenAI-compatible endpoint). Use when the user wants…
not rated 1 25d ago A 103 tokens
original MIT
Skill Claude CodeCodex
Use this skill when reviewing an ML experiment, benchmark, ablation, or training run.
not rated 1 14d ago A 0 tokens
original MIT
zipai-optimizer
733Skill Claude CodeCodex
Skill "zipai-optimizer" from nickdesi/ZipAI, covering zipai: ultra-dense token optimizer, rules, 1. zero filler, 2. ambiguity and 3. prompt caching.
not rated 1 13d ago A 4 tokens
original MIT
john-walkoe/pinecone_assistant_mcp
Skill Claude CodeCodex
Delegation and answer evaluation workflows for the Pinecone Assistant. Uses assistantchat as a sub-agent (Pinecone handles retrieval and synthesis internally) and evaluateanswer to validate answer correctness and completeness against ground truth. Use when Claude's context window is the primary constraint or when…
not rated 1 6mo ago A 128 tokens
original MIT
poyo-ai-models
735Skill Codex
Discover, price, and execute PoYo chat and media-generation models through PoYo MCP or CLI. Use when Codex needs to choose a PoYo model, inspect its input schema, run non-streaming chat, stream chat through the CLI, submit image/video/audio/3D generation, poll a task, or report credits and failures.
not rated 1
changed yesterday A 74 tokens
original MIT
Skill Claude CodeCodex
Pre-inference prompt compression middleware that reduces document and prompt token payloads by 74% prior to calling LLMs. Use this tool when prompt context exceeds 10,000 tokens to cut LLM input token costs on Base Mainnet.
not rated 1 yesterday A 55 tokens
context-repo-mcp
737Skill Claude CodeCodex
Search, retrieve, version, and persist prompts, documents, and collections through the hosted Context Repo MCP. Use this skill whenever the user mentions Context Repo, saved prompts, prompt templates, stored documents, collections, semantic search, or hierarchical document navigation.
not rated 1 13d ago A 56 tokens
original MIT
feishu-memory
738Skill Claude CodeCodex
A Chinese-language skill for saving, searching, updating, and deleting information across conversations through a Feishu memory service. Feishu is a collaboration platform, and RAG is a way to retrieve relevant stored documents or notes for an agent.
not rated 1 2mo ago A 44 tokens
original MIT
neurarch-skill
739Skill Claude CodeCodex
Run an evidence-gated edit loop over a Neurarch model graph through the neurarch-mcp MCP server. Use when an agent needs to inspect, explain, audit, extend, refactor, or debug a neural-network architecture stored as a .neurarch.json graph; summarize a model; locate parameter or compute hotspots; trace dependencies and…
not rated 1 2d ago A 125 tokens
original MIT
Skill Claude CodeCodex
Enriches local food producer agents on the Lokal platform with verified public data. Runs hourly to improve data quality across 1000+ agents. Includes quality filters to remove non-local businesses.
not rated 1 today C 44 tokens
original MIT
graphify
741Skill Claude CodeCodex
Use for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community…
not rated 1
+1 today B 76 tokens
copy · 92% Apache-2.0
Skill Claude CodeCodex
Create, edit, and build Observable Notebooks using Notebook Kit. Use when working with .html notebook files, generating static sites from notebooks, querying databases from notebooks, or using data loaders (Node.js/Python/R) in notebooks. Covers notebook file format, cell types, CLI commands, database connectors, and…
not rated 0 7mo ago A 71 tokens
Skill Claude Code
Use this skill when a source schema change has broken, or is about to break, a downstream transformation and the user wants a fix they can merge — not a summary. Triggers on: "a column was renamed, fix the dbt model", "this field is gone downstream", "schema drift", "our model still selects the old column", "generate…
not rated 0 1mo ago A 140 tokens
original Apache-2.0
Skill Codex
Use when a user asks to integrate with APIAny, choose or compare APIAny models, estimate APIAny credits or pricing, migrate OpenAI-compatible clients to APIAny, generate APIAny model usage examples, or run confirmed APIAny image and video tasks through the APIAny MCP server.
not rated 0 2mo ago A 62 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: