agentleFS

Claude skills and agent skills

Skills real projects publish on GitHub, most starred first. Each one says what it will make an agent do before you copy it.

Best matches · from page 17Worked for most · soon
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.

131d agoReviewMountCreate a free account to mount
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

113mo agoReviewMountCreate a free account to mount
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.

110d agoReviewMountCreate a free account to mount
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.

19d agoReviewMountCreate a free account to mount
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.

5.9k4d agoReviewMountCreate a free account to mount
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).

5557mo agoReviewMountCreate a free account to mount
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".

Steady5 mentions in 2 weeks

No other project uses it yet

15k21mo agoReviewMountCreate a free account to mount
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.

233d agoReviewMountCreate a free account to mount
GTStaggDeletes or force-pushesSkill

dev-server

GTStagg/project-eyas/.claude/skills/dev-server/SKILL.md

Use whenever you're about to start, restart, or kill the Next.js dev server, or whenever the dev server is "acting weird" (404s on routes that exist, broken UI after a code change, port conflicts, HMR not picking up edits, two dev servers fighting). Catches the stray-process + corrupt-.next + competing-instance failure modes that produce these symptoms. Trigger phrases include "restart the dev server", "kill stray dev servers", "clean dev boot", "the dev server is broken", "/config 404", "fresh dev restart", "is the dev server clean", "why is HMR weird".

22d agoReviewMountCreate a free account to mount
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.

486mo agoReviewMountCreate a free account to mount
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.

411d agoReviewMountCreate a free account to mount
openchamberSkill

serve-sim

openchamber/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.

Steady4 mentions in 2 weeks

4 projects use a version of this

13k1d agoReviewMountCreate a free account to mount
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.

13k8d agoReviewMountCreate a free account to mount
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.

Steady33 mentions in 2 weeks

3 projects use a version of this

88k26d agoReviewMountCreate a free account to mount
ngrokSkill

run-mcp-gateway

ngrok/agent-skills/skills/run-mcp-gateway/SKILL.md

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.

1847d agoReviewMountCreate a free account to mount
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.

8710d agoReviewMountCreate a free account to mount
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

13346d agoReviewMountCreate a free account to mount
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.

43412d agoReviewMountCreate a free account to mount
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

11k46d agoReviewMountCreate a free account to mount
MicrosoftReads credentialsSkill

ui-widget-developer

microsoft/work-iq/plugins/microsoft-365-agents-toolkit/skills/ui-widget-developer/SKILL.md

Build MCP servers for Copilot Chat using the OpenAI Apps SDK or MCP Apps SDK widget rendering support (any language). Use this skill when: - Creating MCP servers that integrate with M365 Copilot declarative agents - Building rich interactive widgets (React + Fluent UI) that render in Copilot Chat - Implementing tools that return structuredContent for widget rendering - Adapting an existing MCP server to support Copilot widget rendering - Setting up devtunnels for localhost MCP server exposure - Configuring mcpPlugin.json manifests with RemoteMCPServer runtime Do NOT use this skill for general agent development (scaffolding, manifests, deployment) — use declarative-agent-developer instead. This skill is ONLY for MCP server + widget development. Triggers: "MCP server for Copilot", "OpenAI Apps SDK", "Copilot widget", "structuredContent", "MCP plugin", "devtunnels MCP", "OAI app", "widget rendering", "UI widget"

3 projects use a version of this

1.1k3d agoReviewMountCreate a free account to mount
CLAUDE.md vs AGENTS.md

About skills

What is a Claude skill?

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.