Exécutez n'importe quel Skill dans Manus
en un clic

Exécutez n'importe quel Skill dans Manus en un clic

mcp-builder

Étoiles3

Forks2

Mis à jour1 juin 2026 à 07:31

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

Installation

Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.

Exécuter dans Manus

Source

sweetcornna

sweetcornna/corlinman

Ouvrir le dépôt GitHub Voir les dépôts du créateur

Téléchargement

Exécuter dans Manus

Métiers associésSOC

Basé sur la classification professionnelle SOC

Développeurs de logicielsProfessions informatiques et mathématiques·SOC 15-1252

SKILL.md

readonly

name	mcp-builder
description	Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
emoji	🔌

Judge an MCP server by whether its tools help an LLM accomplish real tasks.

Four phases:

Research & plan — study the MCP spec and the SDK (Python FastMCP or Node/TS), analyze the target API, and balance broad coverage vs. a few specialized workflow tools.
Implement — set up the project, then core infra (API client, error handling, response formatting), then each tool with input/output schemas, clear descriptions, good error messages, and annotations (read-only / destructive / idempotent / open-world).
Review & test — remove duplication, cover errors and types, build, and exercise the server via the MCP Inspector.
Evals — write ~10 complex, independent, read-only, verifiable questions and run them against the server.

Prefer fewer high-leverage tools with great descriptions over a thin 1:1 wrapper of every API endpoint.

Source: github.com/anthropics/skills (Apache-2.0). Condensed + attributed for the corlinman marketplace; see ../../ATTRIBUTION.md.

Plus depuis ce dépôt

même dépôt

brainstorming

sweetcornna/corlinman

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

2026-06-013

conventional-commits

sweetcornna/corlinman

Write git commit messages that follow the Conventional Commits v1.0.0 specification.

2026-06-013

frontend-design

sweetcornna/corlinman

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications. Generates creative, polished UI that avoids generic AI aesthetics.

2026-06-013

skill-creator

sweetcornna/corlinman

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance, or optimize a skill's description for better triggering accuracy.

2026-06-013

systematic-debugging

sweetcornna/corlinman

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

2026-06-013

test-driven-development

sweetcornna/corlinman

Use when implementing any feature or bugfix, before writing implementation code

2026-06-013

name	mcp-builder
description	Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
emoji	🔌

Judge an MCP server by whether its tools help an LLM accomplish real tasks.

Four phases:

Research & plan — study the MCP spec and the SDK (Python FastMCP or Node/TS), analyze the target API, and balance broad coverage vs. a few specialized workflow tools.
Implement — set up the project, then core infra (API client, error handling, response formatting), then each tool with input/output schemas, clear descriptions, good error messages, and annotations (read-only / destructive / idempotent / open-world).
Review & test — remove duplication, cover errors and types, build, and exercise the server via the MCP Inspector.
Evals — write ~10 complex, independent, read-only, verifiable questions and run them against the server.

Prefer fewer high-leverage tools with great descriptions over a thin 1:1 wrapper of every API endpoint.

Source: github.com/anthropics/skills (Apache-2.0). Condensed + attributed for the corlinman marketplace; see ../../ATTRIBUTION.md.