/ Verzeichnis / Playground / Context Engineering Kit
● Community NeoLabHQ ⚡ Sofort

Context Engineering Kit

von NeoLabHQ · NeoLabHQ/context-engineering-kit

Hand-crafted Claude Code skills for higher-quality agent results.

A curated set of context-engineering skills: when to compress, when to summarize, when to spawn a subagent, how to checkpoint long sessions. Built and battle-tested by NeoLab. Compatible with OpenCode, Cursor, Antigravity, Gemini CLI.

Warum nutzen

Hauptfunktionen

Live-Demo

In der Praxis

context-engineering-kit-skill.replay ▶ bereit
0/0

Installation

Repository des Autors · Offizielle Dokumentation zu Claude Skills

Anwendungsfälle

Praxisnahe Nutzung: Context Engineering Kit

Keep a multi-hour coding session from blowing the context window

👤 Engineers on long agent sessions ⏱ ~15 min intermediate

Wann einsetzen: You're 3 hours into a coding loop and the model is starting to drop context.

Voraussetzungen
  • Server/skill installed and authenticated — See repo README
Ablauf
  1. Checkpoint
    Use the context-engineering skill's 'checkpoint' to summarize what we've done into a tight handoff doc.✓ Kopiert
    → A handoff doc Claude can re-read instead of full history
  2. Resume
    Compact the conversation and resume from the handoff doc.✓ Kopiert
    → Session continues with fresh context

Ergebnis: Sessions that don't degrade as they grow.

Fallstricke
  • Checkpointing too often loses fine-grained context. The kit suggests every ~30 turns or before any /compact. — Checkpointing too often loses fine-grained context. The kit suggests every ~30 turns or before any /compact.

Kosten & Limits

Was der Betrieb kostet

API-Kontingent
See provider docs for rate limits
Tokens pro Aufruf
Varies by tool
Kosten in €
See repo README for pricing details
Tipp
Cache tool results and avoid repeated identical calls.

Sicherheit

Rechte, Secrets, Reichweite

Credential-Speicherung: Use environment variables; never commit secrets
Datenabfluss: Tool calls go to the provider's API as documented

Fehlerbehebung

Häufige Fehler und Lösungen

checkpoint doc too long

Tune the skill's max-length; default is ~1500 tokens. Anything bigger and the doc itself eats context.

Prüfen: wc -w on the checkpoint
subagent doesn't have enough context

The skill's spawn template requires a 'mission' block — fill it explicitly, don't let it default.

Prüfen: Read the spawn doc the skill produces

Alternativen

Context Engineering Kit vs. andere

AlternativeWann stattdessenKompromiss
obra/superpowersYou want a broader skill libraryDifferent opinions on workflow

Mehr

Ressourcen

📖 Offizielle README auf GitHub lesen

🐙 Offene Issues ansehen

🔍 Alle 400+ MCP-Server und Skills durchsuchen