serve-model
NVIDIA/deepops/skills/serve-model/SKILL.md
Use when serving a cached model on one GPU with vLLM, checking a local completion endpoint, or diagnosing startup and inference failures in the single-node quickstart.
Skills real projects publish on GitHub, most starred first. Each one says what it will make an agent do before you copy it.
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
NVIDIA/deepops/skills/serve-model/SKILL.md
Use when serving a cached model on one GPU with vLLM, checking a local completion endpoint, or diagnosing startup and inference failures in the single-node quickstart.
github/awesome-copilot/skills/mcp-copilot-studio-server-generator/SKILL.md
Generate a complete MCP server implementation optimized for Copilot Studio integration with proper schema constraints and streamable HTTP support
No other project uses it yet
nickjwells/skills-workspace/.claude/skills/local-server/SKILL.md
Run Claude orchestrator locally with Cloudflare tunneling. Use when user asks to run locally, start local server, or test webhooks locally.
Mindrally/skills/serverless/SKILL.md
Serverless and microservices development guidelines covering FastAPI, cloud-native patterns, API gateways, and best practices for scalable serverless architectures.
BankrBot/openclaw-skills/polygraph/SKILL.md
Behavioral trust grades (A–F) for MCP servers. Use when an agent needs to check whether an MCP server is safe before using it, verify an onchain attestation before trusting or paying a server, look up a server's published grade, get a project graded, or understand why a server received a grade. Polygraph connects to an MCP server the way an agent would, fingerprints its exact tool surface, and runs behavioral probes — prompt-injection (C-01), permission/egress overreach (C-02), sensitive-data leak (C-03), and adversarial-input handling (C-04) — then publishes a reproducible grade as an onchain EAS attestation on Base. Triggers on mentions of MCP server safety, is this MCP server safe, tool poisoning, prompt injection, data leak, permission overreach, unexpected egress, trust grade, attestation, verify before paying, polygraph, litmus, grade my MCP server, adversarial input, robustness, crash, jailbreak, CI gate, fail the build, GitHub Action, gate my skill.
1 project uses a version of this
clockworklabs/SpacetimeDB/skills/typescript-server/SKILL.md
SpacetimeDB TypeScript server module SDK reference. Use when writing tables, reducers, or module logic in TypeScript.
Steady11 mentions in 2 weeks
No other project uses it yet
seaavey/SRouter/skills/srouter-server/SKILL.md
Use when editing `server/` — the SRouter Rust crate (axum 0.8, tokio, sqlx/SQLite, specta). Covers HTTP routes and router layering, middleware, `APIError` and `constants.rs` wire copy, provider drivers and registries, SQLite stores and migrations, SSE streaming, and the integration test harness. Trigger on changes under `server/src`, `server/tests`, or `server/migrations`, or when a task mentions a provider, executor, gateway route, or upstream.
grupoplustech/skills/skills/agent-ops/stdio-mcp-server-builder/SKILL.md
Guide and boilerplate for developing stdio Model Context Protocol (MCP) servers in Node.js and Python. Covers JSON-RPC 2.0 framing, stdin/stdout buffering, and avoiding log contamination.
mizukaizen/hive-doctrine-skills/skills/mcp-server-from-scratch/SKILL.md
Use when building an MCP server from zero. Step-by-step guide to creating Model Context Protocol servers.
tim-osterhus/millrace-skills/skills/build-mcp-server-sdk-v2/SKILL.md
Guardrail for building MCP servers on the v2 split-package TypeScript SDK with v2 APIs, schema discipline, transport choices, and validation.
Blaizzy/mlx-vlm/skills/skills/server-inference/SKILL.md
Use this skill when the user wants to run or debug MLX-VLM server inference, including uv run mlx_vlm.server, /v1/models, /v1/chat/completions, /v1/responses, streaming, OpenAI-compatible clients, health checks, metrics, model unload/reload, adapters, trust-remote-code, and server request/response failures.
johannschopplich/skills/skills/servers/SKILL.md
The user's Hetzner servers – web (Kirby sites) and dev (remote Claude Code and T3 Code): provisioning, patching, debugging, and adding or deploying a site.
ryanportfolio/Harness-Firmware/.agents/skills/servers/SKILL.md
After starting a dev server, or user asks what's running, which port is which, why browsers or node.exe are open, or to close old servers and browsers.
ryanportfolio/Harness-Firmware/.claude/skills/servers/SKILL.md
/servers, after starting a dev server, or user asks what's running, which port is which, why browsers or node.exe are open, or to close old servers and browsers.
Aradotso/mcp-skills/skills/mcp-servers-reference/SKILL.md
Navigate and install from 50+ curated MCP servers for Claude, Gemini, and Codex with verified commands and security best practices
InjectiveLabs/agent-skills/skills/injective-mcp-servers/SKILL.md
Set up and run Injective MCP servers. Needed by multiple Injective skills which perform MCP tool calls.
openai/php2shell-checker/skills/phpcheck-server/SKILL.md
Check PHP2Shell patch status with local or server access.
1 project uses a version of this
kreuzberg-dev/tree-sitter-language-pack/.agents/skills/mcp/SKILL.md
Use tree-sitter-language-pack mcp reference documentation.
Often used withcli
purpleeddy/cladding/skills/serve/SKILL.md
Boot cladding as an MCP server over stdio. Use only when the user wants to expose cladding's tools, resources, and persona prompts to a separate MCP client. Most users don't run this directly — the plugin's .mcp.json launches it automatically. Activate only when the connected project contains spec.yaml or the user explicitly names Cladding; ignore ordinary requests in uninitialized projects.
Aradotso/devtools-skills/skills/godot-devtool-mcp-server/SKILL.md
MCP server for AI-assisted Godot 4 project inspection, editing, validation, and runtime automation via WebSocket bridge
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.
Copy the folder into your project's .claude/skills/ directory, or into your own skills folder to use it everywhere.
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.
Open a skill to see its discussion. Reports from people and their agents are coming.