217,908 that install into Codex. Same mod, same page, whichever agent you run: a URL per tool would split one page into five that compete.
Skill Claude CodeCodex
Use when an unopim-mcp tool call fails or returns an unexpected error. Decodes the enriched error format, points at the right next step for each failure class, and prevents the common rabbit-hole of blaming MCP for what's actually a backend or input issue.
Skill Claude CodeCodex
Guides Claude to act as an expert ERP security analyst using SyntaAI ERP Security MCP tools. Enables comprehensive SAP security audits, compliance assessments, and user access reviews through natural conversation.
Skill Claude CodeCodex
Analyze a chart — set up symbol/timeframe, add indicators, scroll to key dates, annotate, and screenshot. Use when the user wants technical analysis or chart review.
Skill Claude CodeCodex
Programmatic canvas toolkit for creating, editing, and refining Excalidraw diagrams via MCP tools with real-time canvas sync. Use when an agent needs to (1) draw or lay out diagrams on a live canvas, (2) iteratively refine diagrams using describescene and getcanvasscreenshot to see its own work, (3) export/import…
j0k3r-dev-rgl/navigation-agent-mcp
Skill Claude CodeCodex
Trigger: MCP navigation, code discovery, symbol lookup, traceflow, tracecallers, endpoints. Use navigation-agent MCP before reading workspace code.
Skill Claude CodeCodex
Security scanner and runtime guard for OpenClaw skills, MCP servers, and AI agent workflows. Detects prompt injection, identity hijacking, memory poisoning, A2A contagion, secret leaks, supply-chain abuse, and dangerous tool calls with 364 static threat patterns across 35 threat categories plus 27 runtime checks. Use…
Skill Claude CodeCodex
Use this skill when you need to find code in a local checkout or Git source by behavior, intent, symbol, file path, related implementation, or indexed chunk context. Use it before broad file reads or grep-style sweeps for exploratory codebase questions, architecture tracing, call-site discovery, and "where/how is X…
Skill Claude CodeCodex
Scan multiple symbols for setups, patterns, or strategy performance. Use when comparing across instruments or screening for opportunities.
Skill Claude CodeCodex
You have full control over Unity Editor via 24 MCP tools. This skill teaches you how to use them effectively.
Skill Claude CodeCodex
Delegate full plan→implement→review work to FirePass (Kimi K2.6 Turbo via Fireworks AI). The trio runs researcher, then worker, then reviewer in one MCP call, with a bounded fix loop-back when the reviewer says NEEDS-FIXES. Use INSTEAD OF stitching the three single-role tools yourself.
Skill Claude CodeCodex
Score a piece of text for AI-detection risk and produce a concrete, line-by-line fix list. Use when the user pastes text and asks to "analyze for AI tells", "score this for AI", "check AI detection risk", "is this AI-detectable", "what makes this sound AI", "which words flag this as AI", "compare these two drafts"…
Skill Codex
Design, implement, review, debug, optimize, or migrate professional FiveM resources targeting GTAV Enhanced. Use for fxmanifest.lua, client/server/shared scripts, Lua, JavaScript, TypeScript, C#, NUI, natives, events, OneSync, state bags, resource structure, security, compatibility, profiler/resmon investigations, and…
Skill Claude CodeCodex
Run an 8-axis GDPR/AI-Act compliance audit against an @kajaril/audit-event-mcp event store.
Skill Claude CodeCodex
Musical context for the DeepMind 12: what parameters interact, why they matter sonically, and non-obvious techniques. Use when designing sounds or exploring the synth beyond basic parameter setting.
Skill Claude CodeCodex
A skill for managing TickTick, a task and to-do list service, through the dida command-line tool. It covers tasks, lists, tags, habits, and folders.
Skill Claude CodeCodex
Use psamvault MCP server: credential vault, browser login, API key injection, .env secret protection. MCP tools keep secrets out of the agent's context window.
Skill Codex
Use the local ImageForge MCP server to generate raster images with 22 first-party providers, discover provider capabilities, generate from supported reference images, edit existing images with OpenAI, and save results locally. Use whenever the user requests raster image generation, visual creation, image variation…
petersenmatthew/waterloo-learn-mcp
Skill Claude CodeCodex
Connect the waterloo-learn MCP server to a web chat app (ChatGPT or Claude.ai) via Tailscale Funnel. Use when the user wants to register, install, or wire this MCP server into ChatGPT or Claude.ai, or asks why LEARN tools don't show up there. For the local Claude Desktop app, use connect-claude-desktop instead.
Skill Claude CodeCodex
Control Houdini 3D software from the terminal. Use when: Creating, modifying, or querying Houdini nodes and networks Executing Houdini Python (hou module) code Querying scene information (selected nodes, frame range, hip file) Triggers: "houdini", "hou module", "create node", "scene info", "hip file", "geometry"…
Skill Claude CodeCodex
Memoria persistente CORTEX v3.2 (local-first). Cold start automático inyecta contexto del proyecto + perfil del operador. Hook post-turno obligatorio con quickobserve. 22 tools.
Skill Claude CodeCodex
A Chinese-language description of a WebChat AI skill for automating WeChat on a Windows computer. It covers private and group messages, monitoring, speech-to-text, image recognition, and voice or video calls.
dwightpeaster/littlebird-obsidian-mcp
Skill Codex
Use when the user asks to check global knowledge, global directory, Obsidian memory, project history, company context, people notes, decisions, tasks, open loops, or anything that should be searched in the configured Obsidian vault.
njoppi2/playwright-mcp-humanized
Skill Claude CodeCodex
Use this skill when the user wants to configure Codex, Claude Code, or Gemini CLI to use playwright-mcp-humanized through MCP, including extension-first setup, token wiring, and local skill install commands.
Skill Claude CodeCodex
A skill for managing Kubernetes, the system used to run containerized applications across a cluster of machines, through an MCP server.
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: