freemcplab / Verzeichnis / Playground / Harness (Meta-skill)

● Community revfactory ⚡ Sofort

Harness (Meta-skill)

Name: Harness (Meta-skill) (Claude Skill)
Author: revfactory

A meta-skill: tell it your domain, it designs the agent team for you (roles, prompts, hand-offs) and saves the specs for reuse.

Harness treats agent design as a first-class workflow: you describe your domain (incident response, content review, code triage); it asks the right questions, then emits a documented team — roles, system prompts, when each takes over, and shared memory boundaries.

▶ Demo ansehen 📦 Installieren 💡 Anwendungsfälle

Warum nutzen

Hauptfunktionen

Interview-driven team design
Outputs role specs as Markdown
Defines hand-off rules between agents
Specifies shared vs private memory
Versioned team definitions
Reuse across projects

Live-Demo

In der Praxis

bereit

Installieren

Wählen Sie Ihren Client

~/Library/Application Support/Claude/claude_desktop_config.json · Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "harness-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/revfactory/harness",
        "~/.claude/skills/harness"
      ],
      "_inferred": true
    }
  }
}

Öffne Claude Desktop → Settings → Developer → Edit Config. Nach dem Speichern neu starten.

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "harness-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/revfactory/harness",
        "~/.claude/skills/harness"
      ],
      "_inferred": true
    }
  }
}

Cursor nutzt das gleiche mcpServers-Schema wie Claude Desktop. Projektkonfiguration schlägt die globale.

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "harness-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/revfactory/harness",
        "~/.claude/skills/harness"
      ],
      "_inferred": true
    }
  }
}

Klicken Sie auf das MCP-Servers-Symbol in der Cline-Seitenleiste, dann "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "harness-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/revfactory/harness",
        "~/.claude/skills/harness"
      ],
      "_inferred": true
    }
  }
}

Gleiche Struktur wie Claude Desktop. Windsurf neu starten zum Übernehmen.

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "harness-skill",
      "command": "git",
      "args": [
        "clone",
        "https://github.com/revfactory/harness",
        "~/.claude/skills/harness"
      ]
    }
  ]
}

Continue nutzt ein Array von Serverobjekten statt einer Map.

~/.config/zed/settings.json

{
  "context_servers": {
    "harness-skill": {
      "command": {
        "path": "git",
        "args": [
          "clone",
          "https://github.com/revfactory/harness",
          "~/.claude/skills/harness"
        ]
      }
    }
  }
}

In context_servers hinzufügen. Zed lädt beim Speichern neu.

claude mcp add harness-skill -- git clone https://github.com/revfactory/harness ~/.claude/skills/harness

Einzeiler. Prüfen mit claude mcp list. Entfernen mit claude mcp remove.

Anwendungsfälle

Praxisnahe Nutzung: Harness (Meta-skill)

Design an incident-response agent team

👤 Claude Code users ⏱ ~15 min intermediate

Wann einsetzen: You want multiple agents (triage, comms, scribe) cooperating on real incidents instead of one big system prompt.

Ablauf

Brief

Tell harness: "incident response, B2B SaaS, 3 specialists please."✓ Kopiert

→ Harness asks scope questions
Answer

Define escalation, channels, scribe duties.✓ Kopiert

→ Spec drafts emerge
Save

Save specs into /agents/incident/.✓ Kopiert

→ Reusable team def written

Ergebnis: Documented multi-agent team you can rerun next incident, not a one-off prompt.

Kombinationen

Mit anderen MCPs für 10-fache Wirkung

harness-skill + filesystem

Save designed teams alongside your project

Combine harness-skill with filesystem: Save designed teams alongside your project✓ Kopiert

Werkzeuge

Was dieses MCP bereitstellt

Werkzeug	Eingaben	Wann aufrufen	Kosten
design	(see docs)	Run the design interview	1 call
review	(see docs)	Critique an existing team for missing roles or unclear hand-offs	1 call

Kosten & Limits

Was der Betrieb kostet

API-Kontingent: N/A
Tokens pro Aufruf: Interview is moderate
Kosten in €: Free skill
Tipp: Reuse outputs as-is for next domain; don't redesign from scratch

Sicherheit

Rechte, Secrets, Reichweite

Minimale Scopes: fs-read fs-write

Credential-Speicherung: None

Datenabfluss: None

Fehlerbehebung

Häufige Fehler und Lösungen

Output too generic

Provide concrete examples (real past incidents) during the interview

Alternativen

Harness (Meta-skill) vs. andere

Alternative	Wann stattdessen	Kompromiss
Hand-rolled prompts	Single-agent flow	Doesn't scale to multi-agent

Mehr

Ressourcen

📖 Offizielle README auf GitHub lesen

🐙 Offene Issues ansehen

🔍 Alle 400+ MCP-Server und Skills durchsuchen