Claude skills and agent skills

wanshuiyinSkill

serverless-modal

wanshuiyin/Auto-claude-code-research-in-sleep/skills/skills-codex/serverless-modal/SKILL.md

Run GPU workloads on Modal — training, fine-tuning, inference, batch processing. Zero-config serverless: no SSH, no Docker, auto scale-to-zero. Use when user says \"modal run\", \"modal training\", \"modal inference\", \"deploy to modal\", \"need a GPU\", \"run on modal\", \"serverless GPU\", or needs remote GPU compute.

quarkusioSkill

scaffold-quarkus-mcp-server

quarkusio/skills/skills/scaffold-quarkus-mcp-server/SKILL.md

Scaffold a new Quarkus MCP server project with greeting tools, integration tests, and README. Use when the user wants to create, scaffold, or generate a Quarkus MCP server, mentions "quarkus mcp", "quarkus mcp server", "quarkiverse mcp", or asks to generate a Quarkus project with MCP tools.

parcadeiSkill

agentica-server

parcadei/Continuous-Claude/.claude/skills/agentica-server/SKILL.md

Agentica server + Claude proxy setup - architecture, startup sequence, debugging

asmamestSkill

mcp-server-development

asmamest/Nexus-Skills/skills/agentic-engineering/mcp-server-development/SKILL.md

Design, implement, and review Model Context Protocol servers exposing tools, resources, or prompts with clear schemas, least privilege, safe transport, and robust error handling.

blueman82Skill

mcp-server-enhancement

blueman82/ai-counsel/.claude/skills/mcp-server-enhancement/SKILL.md

Guide for safely adding new MCP tools to the AI Counsel server

KMaruthi2002Skill

mcp-server-development

KMaruthi2002/universal-llm-skills/skills/mcp-server-development/SKILL.md

Build, test, secure, and ship Model Context Protocol (MCP) servers and clients that expose tools, resources, and prompts to LLM applications: choosing between tools, resources, and prompts; picking a transport (stdio for local, HTTP-based for remote); designing tool names, input schemas, descriptions, and results; error handling; authentication and authorisation for remote servers; testing with inspector tools and real hosts; and limiting the blast radius of exposed actions. Use when someone wants to "build an MCP server", wrap an API or database for an AI assistant, connect a tool to an MCP-capable host, debug an MCP server that will not connect or whose tools the model misuses, or review an MCP server's security. For general tool and agent design use ai-agents-and-tool-use.

saurabhyadavzSkill

mcp-server-for-plugins

saurabhyadavz/publish-mcp-server-claude-chatgpt/skills/mcp-server-for-plugins/SKILL.md

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.

cwinvestmentsSkill

memstack-automation-hosted-mcp-catalog

cwinvestments/memstack/skills/automation/hosted-mcp-catalog/SKILL.md

Use when the user says 'what MCP servers', 'find an MCP for', 'hosted MCP', 'list MCP servers', 'MCP catalog', 'available MCP tools', or needs to discover zero-setup hosted MCP servers they can use immediately. Do NOT use for building MCP servers or configuring local MCP.

RandallLiuXinSkill

mcp-driver

RandallLiuXin/GodotMaker/skills/core/mcp-driver/SKILL.md

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).

carla-simulatorSkill

run-carla-server

carla-simulator/carla/Skills/ue4/run-carla-server/SKILL.md

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".

No other project uses it yet

andrometiqDeletes or force-pushesSkill

server-setup

andrometiq/sshgate/skills/server-setup/SKILL.md

This skill should be used when the user asks to bring a fresh or newly-provisioned server up to a working, hardened state through SSHGate — phrases like "set up nginx on web-1", "configure the new box", "harden staging", "create a deploy user on prod", "set up a systemd service for the app", "configure the firewall on host-gcp", "set the timezone and NTP", or "get the new server ready for the app". Teaches a discover-first method — read the whole current state, plan the ENTIRE write set, get ONE approval (run_batch tap or a scoped standing grant), then verify each stage — with hard stop-points for lockout-risking and irreversible steps.

openclosed-orgSkill

server-agent

openclosed-org/axum-harness/.agents/skills/server-agent/SKILL.md

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.

celigoSkill

building-mcp-servers

celigo/ai/skills/building-mcp-servers/SKILL.md

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.

kajisho5Skill

building-python-mcp-servers

kajisho5/ffmpeg-skill/.claude/skills/mcp-server-design/SKILL.md

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.

btriapitsynSkill

serve-sim

btriapitsyn/openchamber/.agents/skills/serve-sim/SKILL.md

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.

cheaper-inferenceReads credentialsSkill

cli-serve

cheaper-inference/OmniRoute/skills/cli-serve/SKILL.md

Start, stop, and restart the OmniRoute server from the CLI. Manage daemon mode, port configuration, auto-recovery, system tray integration, and the dashboard open shortcut.

isnow890Reads credentialsSkill

naver-search-mcp

isnow890/naver-search-mcp/skills/naver-search-mcp/SKILL.md

Use for Korean web search, Naver News, Blog, Cafe, Image, Knowledge iN, Encyclopedia, Local search, and Naver DataLab search-trend and shopping-insight analysis through the published npm MCP server.

fabricioctellesSkill

agent-ready-mcp-server-card

fabricioctelles/skills/skills/agent-ready-cloudflare/mcp-server-card/SKILL.md

Sub-skill de agent-ready-cloudflare: Implement MCP Server Card

BTMuliSkill

sentry-mcp

BTMuli/TeyvatGuide/.agents/skills/sentry-mcp/SKILL.md

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.

Model Context ProtocolDeletes or force-pushesSkill

test-servers

modelcontextprotocol/inspector/.claude/skills/test-servers/SKILL.md

Run a composable MCP test server by hand — pick the showcase config for a feature or bug, build it, and connect with the right protocol era. Use when a change, a PR or a smoke test needs a real server to exercise it; when reproducing a reported bug by hand; when choosing which fixture or protocol era to run; when a fixture keeps serving stale code after an edit; or when the config or preset you need does not exist yet.

No other project uses it yet