muratcankoylan /Agent-Skills-for-Context-Engineering
A comprehensive collection of Agent Skills for context engineering, multi-agent architectures, and production agent systems. Use when building, optimizing, or debugging agent systems that require effective context management.
★ 18,350⑂ 1,512👁 98⑃ 115● 23▤ 3
+5
日增长
+55
周增长
+200
月增长
18,350
stars
1,512
forks
98
watchers
115
prs
23
issues
3
releases
README
Agent Skills for Context Engineering A comprehensive, open collection of Agent Skills focused on context engineering and harness engineering principles for building production-grade AI agent systems. These skills teach the art and science of curating context, designing agent operating loops, and evaluating agent behavior across any agent platform. What is Context Engineering? Context engineering is the discipline of managing the language model's context window. Unlike prompt engineering, which focuses on crafting effective instructions, context engineering addresses the holistic curation of all information that enters the model's limited attention budget: system prompts, tool definitions, retrieved documents, message history, and tool outputs. The fundamental challenge is that context windows are constrained not by raw token capacity but by attention mechanics. As context length increases, models exhibit predictable degradation patterns: the "lost-in-the-middle" phenomenon, U-shaped attention curves, and attention scarcity. Effective context engineering means finding the smallest possible set of high-signal tokens that maximize the likelihood of desired outcomes. Recognition This repository is cited in academic research as foundational work on static skill architecture: "While static skills are well-recognized [Anthropic, 2025b; Muratcan Koylan, 2025], MCE is among the first to dynamically evolve them, bridging manual skill engineering and autonomous self-improvement." 1. Meta Context Engineering via Agentic Skill Evolution, Peking University State Key Laboratory of General Artificial Intelligence (2025) 2. Agent Harness Engineering: A Survey, CMU, Yale, JHU, NEU, Tulane, UAB, OSU, Virginia Tech, and Amazon (2026) Skills Overview Foundational Skills These skills establish the foundational understanding required for all subsequent context engineering work. | Skill | Description | |-------|-------------| | context-fundamentals | Understand what context is, why it matters, and the anatomy of context in agent systems | | context-degradation | Recognize patterns of context failure: lost-in-middle, poisoning, distraction, and clash | | context-compression | Design and evaluate compression strategies for long-running sessions | Architectural Skills These skills cover the patterns and structures for building effective agent systems. | Skill | Description | |-------|-------------| | multi-agent-patterns | Master orchestrator, peer-to-peer, and hierarchical multi-agent architectures | | long-horizon-prompting | NEW Write pseudo-formal task briefs for long-running autonomous agents and parallel orchestrations: exact success predicates, non-counting outcomes, audit-gated return conditions, per-worker handoff contracts, effort floors, and diversity policies, modeled on the published GPT-5.6 Sol Ultra Cycle Double Cover prompt and Sakana AI's MASS workflow contracts | | memory-systems | Design short-term, long-term, and graph-based memory
Top issues
#1Warehouse cooperation5 comments · 2025-12-22#35Proposal: Add context-benchmarking Skill and CI Example2 comments · 2026-01-20#108Stale researcher-OS baseline numbers in README.md and AGENTS.md1 comments · 2026-07-14#107Research loop fails on Windows due to Unix-only fcntl import1 comments · 2026-07-14#106API loops and judge examples lack cost / rate-limit safeguards1 comments · 2026-07-14#105Hosted-agents Modal example uses shell injection and unsafe secret handling1 comments · 2026-07-14#104Project-development pipeline is vulnerable to path traversal / arbitrary file deletion1 comments · 2026-07-14#114Plugin manifest at .plugin/plugin.json is not read — skills are namespaced by commit SHA0 comments · 2026-07-31
Latest release
v2.3.0 — Measured Router Benchmark + Corpus-Wide Skill Hardening v2.3.0 2026-05-22The first release with measured benchmark results across four frontier models via the Cursor SDK, a corpus-wide hardening pass across all 15 published skills, and the first full-body Stage 3 effectiveness result. The correction in this release is important: we did not stop at the three descriptions that the router benchmark complained about. Every skill body was audited against the same standard, and the machine-readable substrate moved with it: mechanisms, claims, corpus index, activation fixtures, validators, template, docs, PR/release narrative. Pull request: 87 Full inventory: CHA