Skills for Real Engineers. Straight from my .agents directory.
context-degradation
Agent skill frommuratcankoylan/Agent-Skills-for-Context-Engineering
This skill should be used for diagnosing and mitigating context degradation: lost-in-middle failures, context poisoning, context clash, context confusion, attention-pattern issues, and agent performance degradation caused by accumulated or conflicting context.
How to install context-degradation
npx skills add muratcankoylan/Agent-Skills-for-Context-Engineering# or add only this skill to Claude Code: copy the folder
skills/context-degradation/
# into
~/.claude/skills/context-degradation/ (all projects)
.claude/skills/context-degradation/ (one project)
1# Context Degradation Patterns23Diagnose and fix context failures before they cascade. Context degradation is not binary — it is a continuum that manifests through five distinct, predictable patterns: lost-in-middle, poisoning, distraction, confusion, and clash. Each pattern has specific detection signals and mitigation strategies. Treat degradation as an engineering problem with measurable thresholds, not an unpredictable failure mode.45## When to Activate67Activate this skill when:8- Agent performance degrades unexpectedly during long conversations9- Debugging cases where agents produce incorrect or irrelevant outputs10- Designing systems that must handle large contexts reliably11- Evaluating context engineering choices for production systems12- Investigating "lost in middle" phenomena in agent outputs13- Analyzing context-related failures in agent behavior1415Do not activate this skill for adjacent work owned by other skills:16- Explaining foundational context mechanics without an active failure: `context-fundamentals`.17- Applying token-efficiency tactics after the failure pattern is known: `context-optimization`.18- Designing a compression or handoff summary strategy: `context-compression`.19- Persisting large outputs, logs, or scratch state outside the prompt: `filesystem-context`.2021## Core Concepts22…
Excerpt shown under the repository's MIT license.
More skills in Agent-Skills-for-Context-Engineering
Similar skill repositories
An agentic skills framework & software development methodology that works.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Public repository for Agent Skills
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
Production-grade engineering skills for AI coding agents.
