HomeProjectsArticlesPK BoardAbout
Explore Projects

Agent Skills for Context Engineering

Active
GitHub Python MIT

Description

A comprehensive collection of Agent Skills for context engineering, multi-agent architectures, and production agent systems. Use when building, optimizing, or debugging agent systems.

Key Features

  • Covers 15 context engineering skills from foundational concepts to advanced cognitive architectures for systematic AI agent knowledge building
  • Platform-agnostic design, applicable to Claude Code, Cursor, and any agent platform supporting custom instructions
  • Progressive disclosure architecture: loads only skill names and descriptions at startup, activating full content on demand
  • Covers context degradation pattern recognition, compression strategies, multi-agent coordination patterns, and memory system design
  • Cited in academic research papers from Peking University, CMU, Yale, and other top institutions
  • One-click installation via Claude Code plugin marketplace with automatic skill activation based on task context

Use Cases

💡 AI agent developers learning context management best practices to improve agent system performance
💡 Choosing appropriate coordination patterns and context isolation strategies when designing multi-agent architectures
💡 Diagnosing agent performance degradation in long sessions, such as the Lost-in-the-Middle phenomenon
💡 Building agent evaluation frameworks using LLM-as-a-Judge techniques for systematic assessment
💡 Guiding development teams to establish context engineering standards and improve AI project quality

Strengths & Limitations

✅ Strengths

  • • Actively maintained, recent updates
  • • High community interest (17.9k stars)
  • • Permissive open-source license (MIT)
  • • Responsive to issues, low backlog

Tags

agent multi-agent framework python tools

Categories

🧠 Multi-Agent ⚡ Agent Tools

Quick Start

In Claude Code, run /plugin marketplace add muratcankoylan/Agent-Skills-for-Context-Engineering to register the marketplace, then run /plugin install context-engineering@context-engineering-marketplace to install all 15 skills. Skills activate automatically based on your task context, or you can specify them manually.
Visit GitHub

Related Projects

GPTeam

1.7k · Python
Active A

An open-source multi-agent simulation platform where multiple LLM-powered agents collaborate on complex tasks in shared environments, with customizable roles, memory systems, and environment interaction for studying multi-agent collaboration.

pythonmulti-agentagent +3
  • · GPT-4 powered multi-agent simulation with autonomous collaboration on predefined goals
  • · Agent memory and reflection system inspired by Generative Agents research paper
  • · Spatial movement: agents move between locations and perform tasks in different environments
View on GitHub

MetaGPT

70.2k · Python
Stale B

The Multi-Agent Framework for building the first AI Software Company, enabling natural language programming with multi-role collaboration for automated requirement analysis, design, coding, and testing.

multi-agentframeworkpython +2
  • · Multi-role collaboration - Built-in product manager, architect, engineer roles simulating a full software company SOP pipeline
  • · Natural language programming - Input a one-line requirement to auto-generate user stories, competitive analysis, API design, and complete code
  • · Data Interpreter - Dynamic code generation and data analysis for CSV processing, visualization, and exploratory tasks
View full details → View on GitHub

Bindu

9.7k · Python
Active A

Turn any AI agent into a living microservice that is interoperable, observable and composable, enabling standardized agent communication and orchestration.

multi-agentpythonframework +2
  • · Identity, communication, and payments layer for AI agents via a single `bindufy()` function call
  • · Cryptographic DID-based identity with Ed25519 signatures for agent authentication
  • · Three-layer security by default: mTLS, OAuth2 via Hydra, and DID signature verification
View full details → View on GitHub

Ouroboros

5.8k · Python
Active A

Ouroboros is a spec-driven multi-agent framework that shifts from traditional prompting to specification-driven development, supporting multi-agent collaboration, MCP tool integration, and automated workflow orchestration for building high-quality agent systems.

multi-agentframeworkagent +4
  • · Spec-first workflow: Socratic interview → immutable seed spec → execution → evaluation
  • · Multi-runtime adapter supporting Claude Code, Codex CLI, OpenCode, Hermes, Gemini, Kiro, Copilot
  • · Three-layer architecture: Kernel (contract engine), Plugins (domain workflows), Shell (TUI cockpit)
View full details → View on GitHub

Related Articles

上下文工程长上下文RAG

Context Engineering: Context Decay and Recovery in Long-Conversation Agents

Long-conversation agents fail at context management, not model capability. A systematic comparison of sliding window, retrieval injection, and layered compression strategies with practical decay diagnosis and recovery patterns.

Read more →