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

Installation

Repository des Autors · Offizielle Dokumentation zu Claude Skills

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