Skip to main content
Glama
deenesjakoruzh
Guslaier

MCP-skill-library-dynamic

by Guslaier
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

MCP-skill-library-dynamic 🚀

Un servidor MCP (Model Context Protocol) de nivel empresarial que sirve archivos de habilidades y reglas desde un directorio local a agentes de IA bajo demanda. Permite a los agentes de IA listar y obtener dinámicamente instrucciones de habilidades específicas formateadas en Markdown sin sufrir de inflación de contexto.

✨ Características (v1.2.0)

  • TypeScript Native: 100% seguro de tipos, compilado a módulos ES optimizados.

  • Curated 200+ Core Skills Base: Conjunto de habilidades de alta calidad, deduplicado y estándar de la comunidad, preindexado en skills-base.json.

  • Deterministic Offline-First Downloader: Descargas por lotes rápidas y confiables directamente desde la lista base seleccionada usando npx skills add con reintentos de retroceso exponencial.

  • Smart Search & Filter: list_skills admite un parámetro opcional query (por ejemplo, list_skills({ query: "react" })) para filtrar habilidades directamente y ahorrar tokens.

  • Recursive Multi-File Rule Aggregation: fetch_skill_rule escanea y combina automáticamente todos los archivos Markdown anidados (por ejemplo, rules/*.md, references/*.md) sin omitir documentación más profunda.

  • Zero-Config Auto-Path Resolution: Resuelve inteligentemente .agents/skills en relación con la ubicación del servidor compilado, eliminando problemas de configuración manual de SKILLS_DIR.

  • Ghost Skill Elimination: Ignora automáticamente directorios vacíos y solo sirve carpetas con archivos de reglas .md verificados.

  • Memory-Safe Caching: Utiliza una caché TTL para el listado de directorios y E/S asíncrona para la lectura de archivos, garantizando 0% de probabilidad de fallos por falta de memoria (OOM), incluso con más de 100,000 habilidades.

  • Path Traversal Protection: Resolución de rutas con grado criptográfico para aislar estrictamente a la IA al directorio .agents/skills/.

  • Graceful Shutdown: Maneja adecuadamente SIGINT/SIGTERM y excepciones no capturadas para asegurar cierres limpios de los sockets MCP.

  • Token Diet Architecture (Cost Saving):

    • list_skills solo devuelve nombres de carpetas sin procesar (slugs), minimizando el contexto inyectado a solo ~1,500 tokens incluso con más de 1,000 habilidades.

    • fetch_skill_rule obtiene contenido estrictamente bajo demanda, una habilidad a la vez, previniendo alucinaciones de IA y facturas masivas de API.

Related MCP server: docubridge

📦 Instalación y compilación

  1. Clona o descarga el repositorio:

git clone https://github.com/Guslaier/MCP-skill-library-dynamic.git
cd skill-library-mcp

  1. Instala las dependencias:

npm install

  1. Compila el código fuente de TypeScript:

npm run build

🧠 Descarga y gestión de habilidades

Las habilidades se cargan en .agents/skills/ ubicado en la raíz del proyecto (o configurado mediante SKILLS_DIR).

Habilidades base seleccionadas (skills-base.json)

El descargador utiliza skills-base.json como la única fuente de verdad que contiene más de 200 habilidades seleccionadas y deduplicadas de repositorios oficiales y de primer nivel (anthropics/skills, obra/superpowers, affaan-m/ecc, browser-use, etc.).

Comandos CLI

Comando

Descripción

npm run download

Descarga e instala las 200+ habilidades base

npm run download -- <skill-name>

Descarga solo habilidades que coincidan con el filtro de nombre

Ejemplos

# Download all 200+ curated base skills
npm run download

# Download only specific skills matching 'caveman'
npm run download -- caveman

# Download all React / Frontend related skills
npm run download -- react

📁 Estructura de directorios

skill-library-mcp/
├── package.json
├── tsconfig.json
├── skills-base.json        # Curated index of 200+ skills (name, repo url, description)
├── src/
│   ├── index.ts            # MCP Server entry point
│   └── download-skills.ts  # Batch downloader from skills-base.json
├── dist/
│   ├── index.js
│   └── download-skills.js
└── .agents/
    └── skills/             # Local skill files served to AI agents
        ├── code-review/
        │   └── SKILL.md
        ├── test-driven-development/
        │   └── SKILL.md
        └── ...

🚀 Ejecutando el servidor

Inicia el servidor usando:

npm start

⚙️ Configuración de MCP

Para conectar este servidor con un cliente MCP (como Antigravity, Cursor, Roo Code o Cline), agrega la siguiente configuración al archivo de configuración de tu cliente:

{
  "mcpServers": {
    "skill-library": {
      "command": "node",
      "args": [
        "C:/path/to/skill-library-mcp/dist/index.js"
      ],
      "env": {
        "SKILLS_DIR": "C:/path/to/skill-library-mcp/.agents/skills"
      }
    }
  }
}

Importante: Reemplaza C:/path/to/skill-library-mcp con la ruta real de tu repositorio, apuntando a dist/index.js.

🤖 Prompt del sistema (Protocolo de base de conocimiento)

Agrega el siguiente prompt a las reglas de tu agente de IA (.clinerules, .cursorrules o Instrucciones personalizadas) para que el agente use automáticamente la Biblioteca de Habilidades:

# UNIVERSAL KNOWLEDGE BASE PROTOCOL
You are equipped with the Enterprise "Skill Library MCP". Before starting any architectural planning, refactoring, or feature implementation, you MUST:
1. Use `list_skills` (or `list_skills({ query: "keyword" })`) to check for relevant domain rules or coding standards.
2. If found, use `fetch_skill_rule({ skill_name: "..." })` to read the full context and nested rule guidelines.
3. Explicitly acknowledge the rules and apply them strictly to your code generation.

📜 Licencia

MIT

Available Tools

2 tools
fetch_skill_ruleA
Read-onlyIdempotent

Fetch the full markdown content and nested rule guidelines of a specific skill.

NameRequiredDescriptionDefault
skill_nameYesExact name of the skill folder (e.g., 'nestjs-best-practices')

Output Schema

NameRequiredDescription
filesNo
contentNo
skill_nameNo

TDQS

A4/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds value by specifying exactly what is returned (full markdown content and nested rule guidelines), which is beyond the annotations. It does not claim any side effects, and the read-only nature is consistent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, concise sentence of 12 words. It is front-loaded with the verb and clearly states the output. No unnecessary words or repetition; every word earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple one-parameter read tool, the description is quite complete given the presence of an output schema (which presumably explains the return format) and annotations covering safety. It does not mention error behavior (e.g., missing skill), but that is likely handled by the output schema. Overall, adequate for the tool's simplicity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, and the schema provides a clear description for skill_name. The tool description does not add any additional meaning to the parameter, so it relies on the schema. Baseline 3 is appropriate when the schema already documents the parameter fully.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the specific verb 'Fetch' and the resource (full markdown content and nested rule guidelines of a skill). It distinguishes this from list_skills, which likely only provides an overview. The purpose is unambiguous and distinct from its sibling.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The usage context is implied by the description and the presence of list_skills as a sibling, but it does not explicitly state when to use this tool versus list_skills. No exclusions or alternative conditions are mentioned, so guidance is only implicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

list_skillsA
Read-onlyIdempotent

List all available skills/rules in the knowledge base. Supports optional search query for token efficiency.

NameRequiredDescriptionDefault
queryNoOptional keyword to filter skills (e.g., 'react', 'python', 'review')

Output Schema

NameRequiredDescription
countNo
skillsNo

TDQS

A4.2/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and idempotentHint=true, and the description adds the behavioral context that it returns the full list unless filtered, plus the token-efficiency rationale. This supplements the annotations without contradicting them.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

A single sentence packs the core purpose and the optional usage hint with zero redundancy or filler. The most important information is front-loaded, and every word earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the simple nature of the tool, the presence of an output schema, and comprehensive annotations, the description covers the essential aspects. It does not explicitly address when to use fetch_skill_rule, but that is a minor omission for a list operation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% for the single optional 'query' parameter, so the description's addition of 'token efficiency' provides extra semantic value beyond the schema, explaining why one would use the filter. This meaningfully enhances the parameter's purpose.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool lists all available skills/rules in the knowledge base, using a specific verb ('List') and resource. It distinguishes from sibling fetch_skill_rule by semantic contrast (list vs fetch), making the purpose unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description mentions an optional search query for token efficiency, which hints at usage for large lists, but does not explicitly contrast with fetch_skill_rule or state when to use one over the other. The guidance is implied rather than explicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 2 tool updatesv1.0.0
    • First observedfetch_skill_rule
    • First observedlist_skills
Deploy Server
Shareable, User-Owned Context BackendPeople, applications, and agents read, write, and coordinate together in one context lake. Reach it over MCP, a CLI, a Python SDK, or REST.fulcradynamics.comAd

TDQS

A4.2/5.0

Scored across 2 tools

Disambiguation5/5

The two tools have completely distinct purposes: one lists available skills, the other fetches a specific skill's content. There is no overlap or ambiguity between them.

Naming Consistency5/5

Both tools follow the same verb_noun pattern (list_skills, fetch_skill_rule), making the naming predictable and consistent.

Tool Count3/5

With only 2 tools, the set is on the thin side, but it fits the narrow scope of a read-only skill library. It feels borderline rather than clearly inadequate.

Completeness4/5

For a read-only knowledge base, list and fetch cover the essential operations. The search option on list_skills adds flexibility. Minor gaps like versioning or metadata retrieval are not critical.

Maintenance

ActivityStale
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers