freemcplab / الدليل / الملعب / Context Engineering Kit

● مجتمع NeoLabHQ ⚡ فوري

Context Engineering Kit

Name: Context Engineering Kit (Claude Skill)
Author: NeoLabHQ

بواسطة 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.

▶ شاهد العرض 📦 التثبيت 💡 حالات الاستخدام

لماذا تستخدمه

الميزات الأساسية

Subagent-driven development pattern
Test-driven development with rigid red/green loops
Branch-finishing skill (review → cleanup → merge)
Context-window budget management
Multi-agent compatibility

عرض مباشر

كيف يبدو في الممارسة

context-engineering-kit-skill.replay ▶ جاهز

0/0

التثبيت

مستودع المؤلف · وثائق Claude Skills الرسمية

حالات الاستخدام

استخدامات عملية: Context Engineering Kit

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

👤 Engineers on long agent sessions ⏱ ~15 min intermediate

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

المتطلبات الأساسية

Server/skill installed and authenticated — See repo README

الخطوات

Checkpoint

Use the context-engineering skill's 'checkpoint' to summarize what we've done into a tight handoff doc.✓ تم النسخ

→ A handoff doc Claude can re-read instead of full history
Resume

Compact the conversation and resume from the handoff doc.✓ تم النسخ

→ Session continues with fresh context

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

المزالق

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.

التكلفة والحدود

تكلفة التشغيل

حصة API: See provider docs for rate limits
الرموز لكل استدعاء: Varies by tool
التكلفة المالية: See repo README for pricing details
نصيحة: Cache tool results and avoid repeated identical calls.

الأمان

الصلاحيات والأسرار ونطاق الأثر

تخزين بيانات الاعتماد: Use environment variables; never commit secrets

نقل البيانات الخارجي: Tool calls go to the provider's API as documented

استكشاف الأخطاء

الأخطاء الشائعة وحلولها

checkpoint doc too long

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

تحقق: 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.

تحقق: Read the spawn doc the skill produces

البدائل