Agent skill · product strategy · aradotso
agent-skills-context-engineering
agent-skills-context-engineering — an agent skill for coding agents.
Why this skill is useful
Adds multiple executable skills for context engineering and multi-agent architectures that enhance agent capabilities significantly.
What it needs
Requires claude, cursor installed locally. About 8k tokens when loaded. Last updated 2026-07-09. 70 stars on the source repository.
What this skill does
bash Register the marketplace /plugin marketplace add muratcankoylan/Agent-Skills-for-Context-Engineering Install individual plugin bundles /plugin install context-engineering-fundamentals@context-engineering-marketplace /plugin install agent-architecture@context-engineering-marketplace /plugin install agent-evaluation@context-engineering-marketplace /plugin install agent-development@context-engineering-marketplace /plugin install cognitive-architecture@context-engineering-marketplace bash git clone https://github.com/muratcankoylan/Agent-Skills-for-Context-Engineering.git Agent-Skills-for-Context-Engineering/ ├── .plugin/ │ └── plugin.json # Open Plugins manifest ├── skills/ │ ├── context-fundamentals/ # Context anatomy, token budgets │ ├── context-degradation/ # Failure modes and diagnostics │ ├── context-compression/ # Compression and summarization │ ├── context-optimization/ # Caching, masking, compaction │ ├── multi-agent-patterns/ # Orchestrator, peer, hierarchical │ ├── memory-systems/ # Short/long-term, graph memory │ ├── tool-design/ # Effective tool construction │ ├── filesystem-context/ # File-based context offloading │ ├── hosted-agents/ # Sandboxed background agents │ ├── evaluation/ # Agent evaluation frameworks │ ├── advanced-evaluation/ # LLM-as-a-Judge techniques │ ├── project-development/ # LLM project methodology │ └── bdi-mental-states/ # BDI cognitive architecture └── examples/ ├── digital-brain-skill/ # Personal OS for founders ├── x-to-book-system/ # Multi-agent X→book pipeline ├── llm-as-judge-skills/ # TypeScript evaluation tools └── book-sft-pipeline/ # Style transfer fine-tuning python The five components competing for attention budget context = { "systemprompt": "...", # Role, instructions, constraints "tooldefinitions": [...], # Available tools and schemas "retrieveddocuments": [...], # RAG results, memory lookups "messagehistory": [...], # Conversation turns "tooloutputs": [...], # Results from tool calls } Token budget allocation examp …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills aradotso/agent-skills-context-engineering