Design or review the tools of a remote MCP server so both ChatGPT's plugin review and Claude's connector review accept it and both models actually call it - Streamable HTTP at /mcp, verb_first tool names, titles, all four annotation hints set explicitly, output schemas with structured content, error results that say what to do, a per-result size budget, and server instructions that make ChatGPT use your tool instead of its own built-in features. Use when building or auditing an MCP server for ChatGPT or Claude, when a test prompt gets answered without your tool being called, when a review flags annotations or descriptions, or when tool results are too large.
Builds robust Python MCP (Model Context Protocol) servers with FastMCP — tool design, error contracts, event-loop-safe blocking work, subprocess/CLI wrapping, single-file vs packaged distribution, global-state-free testing, and prompt-injection awareness. Use when writing an MCP server, exposing a tool or CLI to an LLM client, debugging tool registration/packaging, or testing MCP tools.
5.9k3d agoReviewMountCreate a free account to mount
Runtime debugging and live project inspection via godot-mcp. Use when headless tools cannot diagnose the problem: code compiles but runtime behavior is wrong, tests pass but the game does not work as expected, or you need to inspect live state (node tree, console output, rendering). Escalation trigger: a task has failed 2+ times through the headless path (headless-build, gdunit-driver), or the issue is inherently runtime-only (visual glitches, input not responding, physics behaving unexpectedly at runtime). DO NOT use for: syntax/compile errors (use headless-build), unit test failures (use gdunit-driver), API lookups (use godot-api). Requires: godot-mcp MCP server registered as "godot" (@coding-solo/godot-mcp).
5557mo agoReviewMountCreate a free account to mount
Launches a CARLA RPC server a carla.Client can connect to, working out for itself what you pointed it at — a downloaded/extracted release, a package cooked inside a checkout, or a source checkout run through the UE4 editor — headless or windowed, and shuts it down cleanly. ROS2=1 starts it with the native ROS 2 interface active (--ros2, --rmw=fastdds/cyclonedds/zenoh, --ros-domain-id). Use when the user asks to "run/start the CARLA server", "boot CARLA headless", "launch CARLA with a window", "run the CARLA I downloaded", "start CARLA with ROS2 enabled", or "serve a packaged CARLA build".
Steady5 mentions in 2 weeks
No other project uses it yet
15k21mo agoReviewMountCreate a free account to mount
Maintains servers, handlers, routes, middleware, and sync entrypoints. Owns servers/bff/**, servers/gateway/**, servers/internal-rpc/**. Use when changing HTTP handlers, routes, middleware, API composition, server entrypoints, request/response adaptation, or protocol integration. Does protocol adaptation and API composition only — never owns core domain logic or long-running transaction semantics.
486mo agoReviewMountCreate a free account to mount
Build Celigo MCP server resources -- endpoints that expose Tools and builder-mode APIs to external AI agents and MCP clients. Use when creating MCP servers, linking tools or APIs, or configuring annotations and overrides.
Use when working with the OpenChamber iOS Simulator app without opening Xcode - boot/install/launch the Capacitor iOS app, start a browser stream, tap/type/gesture/rotate, inspect accessibility, or hand a simulator URL to the user.
Use when working with the OpenChamber iOS Simulator app without opening Xcode - boot/install/launch the Capacitor iOS app, start a browser stream, tap/type/gesture/rotate, inspect accessibility, or hand a simulator URL to the user.
13k7d agoReviewMountCreate a free account to mount
Expose an in-development MCP (Model Context Protocol) server for remote testing against AI model providers like Claude and OpenAI, with per-provider authentication and traffic inspection. Puts a cloud endpoint in front of your local MCP server, authenticates each provider with its own bearer token via Vaults, and forwards to your server kept off the public internet. Use when the user is building or testing an MCP server and needs a remote AI client to reach it. Use when the user says "test my MCP server", "expose my MCP server to Claude", "connect my MCP server to OpenAI", or "front door for my MCP server". Not for connecting ngrok's own MCP server - use ngrok-setup.
1846d agoReviewMountCreate a free account to mount
Connect to, diagnose, and use the official remote Sentry MCP server for TeyvatGuide production errors. Use for MCP setup or authentication failures, missing Sentry tools, Sentry issue or event URLs and IDs, stack traces, crash triage, regression checks, release health, affected-user analysis, or validating whether a deployed fix stopped recurring errors.
43412d agoReviewMountCreate a free account to mount
Universal MCP client for connecting to any MCP server with progressive disclosure. Wraps MCP servers as skills to avoid context window bloat from tool definitions. Use when interacting with external MCP servers (Zapier, Sequential Thinking, GitHub, filesystem, etc.), listing available tools, or executing MCP tool calls. Triggers on requests like "connect to Zapier", "use MCP server", "list MCP tools", "call Zapier action", "use sequential thinking", or any MCP server interaction.
81910mo agoReviewMountCreate a free account to mount
Use when serving NeMo Agent Toolkit workflows, exposing workflows through FastAPI, configuring MCP clients or servers, or troubleshooting transport and server setup.
Steady2 mentions in 2 weeks
No other project uses it yet
2.7k15mo agoReviewMountCreate a free account to mount
End-to-end workflow for adding or changing Overmind MCP tools, resources, prompts, authentication, or result contracts — server layers, catalog registration, MCP-impact classification, contract versioning and required tests. Use when adding, changing, or removing an MCP tool, resource, prompt, auth rule, or CallToolResult contract.
Use MCP (Model Context Protocol) servers from bash with `shelley mcp`. Use when the user mentions MCP, asks to add or connect an MCP server, or a task needs an external service that may be reachable through a registered MCP server.
Guide for building GraphQL servers with Apollo Server 5.x. Use this skill when: (1) setting up a new Apollo Server project, (2) writing resolvers or defining GraphQL schemas, (3) implementing authentication or authorization, (4) creating plugins or custom data sources, (5) troubleshooting Apollo Server errors or performance issues.
1 project uses a version of this
12310mo agoReviewMountCreate a free account to mount
A folder with a SKILL.md file: a name, a description of when to use it, and instructions. Claude loads a skill only when the task matches its description.
How do I use one I find here?
Copy the folder into your project's .claude/skills/ directory, or into your own skills folder to use it everywhere.
What do the warnings mean?
We read each file for commands that read secrets, delete things or pipe downloads into a shell, and say so before you copy it. No warning is not a promise that a file is safe.
Which skills worked for people?
Open a skill to see its discussion. Reports from people and their agents are coming.