Skip to main content
Glama
deenesjakoruzh
Guslaier

MCP-skill-library-dynamic

by Guslaier
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

MCP-skill-library-dynamic 🚀

Ein Enterprise-tauglicher MCP-Server (Model Context Protocol), der Skill- und Regeldateien aus einem lokalen Verzeichnis auf Abruf an KI-Agenten bereitstellt. Er ermöglicht es KI-Agenten, spezifische, in Markdown formatierte Skill-Anweisungen dynamisch aufzulisten und abzurufen, ohne unter Context Bloat zu leiden.

✨ Funktionen (v1.2.0)

  • TypeScript-nativ: 100 % typsicher, kompiliert zu optimierten ES-Modulen.

  • Kuratierte Basis mit 200+ Kern-Skills: Hochwertiger, deduplizierter und community-standardisierter Skill-Satz, vorindexiert in skills-base.json.

  • Deterministischer Offline-First-Downloader: Schnelle, zuverlässige Batch-Downloads direkt aus der kuratierten Basisliste mit npx skills add und exponentiellen Backoff-Wiederholungen.

  • Intelligente Suche & Filter: list_skills unterstützt den optionalen Parameter query (z. B. list_skills({ query: "react" })), um Skills direkt zu filtern und Tokens zu sparen.

  • Rekursive Multi-Datei-Regelaggregation: fetch_skill_rule scannt und kombiniert automatisch alle verschachtelten Markdown-Dateien (z. B. rules/*.md, references/*.md), ohne tiefere Dokumentation zu überspringen.

  • Automatische Pfadauflösung ohne Konfiguration: Löst .agents/skills intelligent relativ zum kompilierten Server-Speicherort auf und eliminiert manuelle SKILLS_DIR-Einrichtungsprobleme.

  • Beseitigung von Geister-Skills: Ignoriert automatisch leere Verzeichnisse und stellt nur Ordner mit verifizierten .md-Regeldateien bereit.

  • Speichersicheres Caching: Verwendet einen TTL-Cache für die Verzeichnisauflistung und asynchrones I/O für das Lesen von Dateien, um eine 0%ige Wahrscheinlichkeit von Out-of-Memory-Abstürzen (OOM) zu garantieren, selbst bei 100.000+ Skills.

  • Schutz vor Pfad-Traversal: Kryptografisch abgesicherte Pfadauflösung, um die KI strikt auf das Verzeichnis .agents/skills/ zu beschränken.

  • Sanftes Herunterfahren: Behandelt SIGINT/SIGTERM und unbehandelte Ausnahmen ordnungsgemäß, um saubere MCP-Socket-Schließungen zu gewährleisten.

  • Token-Diät-Architektur (Kostenersparnis):

    • list_skills gibt nur rohe Ordnernamen (Slugs) zurück und minimiert den injizierten Kontext auf nur ~1.500 Tokens, selbst bei 1.000+ Skills.

    • fetch_skill_rule ruft Inhalte strikt on-demand ab, jeweils einen Skill nach dem anderen, und verhindert so KI-Halluzinationen und massive API-Rechnungen.

Related MCP server: docubridge

📦 Installation & Build

  1. Klonen oder laden Sie das Repository herunter:

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

  1. Abhängigkeiten installieren:

npm install

  1. TypeScript-Quellcode kompilieren:

npm run build

🧠 Herunterladen & Verwalten von Skills

Skills werden in .agents/skills/ im Projektstamm geladen (oder über SKILLS_DIR konfiguriert).

Kuratierte Basis-Skills (skills-base.json)

Der Downloader verwendet skills-base.json als einzige Quelle der Wahrheit, die 200+ kuratierte und deduplizierte Skills aus offiziellen und erstklassigen Repositories enthält (anthropics/skills, obra/superpowers, affaan-m/ecc, browser-use usw.).

CLI-Befehle

Befehl

Beschreibung

npm run download

Alle 200+ Basis-Skills herunterladen und installieren

npm run download -- <skill-name>

Nur Skills herunterladen, die dem angegebenen Namensfilter entsprechen

Beispiele

# 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

📁 Verzeichnisstruktur

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
        └── ...

🚀 Server starten

Starten Sie den Server mit:

npm start

⚙️ MCP-Konfiguration

Um diesen Server mit einem MCP-Client (wie Antigravity, Cursor, Roo Code oder Cline) zu verbinden, fügen Sie die folgende Konfiguration zur Einstellungsdatei Ihres Clients hinzu:

{
  "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"
      }
    }
  }
}

Wichtig: Ersetzen Sie C:/path/to/skill-library-mcp durch Ihren tatsächlichen Repository-Pfad, der auf dist/index.js zeigt.

🤖 System-Prompt (Knowledge-Base-Protokoll)

Fügen Sie den folgenden Prompt zu Ihren KI-Agenten-Regeln hinzu (.clinerules, .cursorrules oder Custom Instructions), damit der Agent automatisch die Skill-Bibliothek verwendet:

# 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.

📜 Lizenz

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