Tooluck logoTooluck
SKILL.md

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

install context-degradation
# install the Agent-Skills-for-Context-Engineering pack with the skills CLI
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)

skills/context-degradation/SKILL.md

MITFull file
1# Context Degradation Patterns
2
3Diagnose 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.
4
5## When to Activate
6
7Activate this skill when:
8- Agent performance degrades unexpectedly during long conversations
9- Debugging cases where agents produce incorrect or irrelevant outputs
10- Designing systems that must handle large contexts reliably
11- Evaluating context engineering choices for production systems
12- Investigating "lost in middle" phenomena in agent outputs
13- Analyzing context-related failures in agent behavior
14
15Do 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`.
20
21## Core Concepts
22…

Excerpt shown under the repository's MIT license.

More skills in Agent-Skills-for-Context-Engineering

Keep exploring

Similar skill repositories

thedotmack /

claude-mem
116k

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

CCCXGHGM+135 skills

Newsletter

Join the Community

Subscribe to our newsletter for the latest news and updates