Context Degradation
This is a diagnostic framework for when your agent starts acting weird during long conversations. It breaks down context failures into five specific patterns (lost-in-middle, poisoning, distraction, confusion, and clash) rather than treating everything as random breakage. The core insight is treating the attention U-curve as a design constraint: stuff in the middle of your context window gets 10-40% less attention, so you architect around it. Most useful when you're debugging production agents that work fine for three turns then fall apart, or when you're trying to figure out why retrieved facts aren't being used even though they're clearly in context. Comes from muratcankoylan's agent skills collection, adapted by flora131.
- skills.sh installs
- 164
- GitHub stars
- 234
- last updated
- Jun 3, 2026
Install
$ npx -y skills add flora131/atomic --skill context-degradation --agent claude-codeInstalls into .claude/skills of the current project.
Files
This is a diagnostic framework for when your agent starts acting weird during long conversations. It breaks down context failures into five specific patterns (lost-in-middle, poisoning, distraction, confusion, and clash) rather than treating everything as random breakage. The core insight is treating the attention U-curve as a design constraint: stuff in the middle of your context window gets 10-40% less attention, so you architect around it. Most useful when you're debugging production agents that work fine for three turns then fall apart, or when you're trying to figure out why retrieved facts aren't being used even though they're clearly in context. Comes from muratcankoylan's agent skills collection, adapted by flora131.
Browse the repository on GitHubSponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageDetails
- Repository
- github.com/flora131/atomic
- First seen
- Jun 3, 2026
More from flora131/atomic
All 39- Context Fundamentals164
- Filesystem Context164
- Memory Systems164
- Project Development164
- Tool Design164
- Typescript Advanced Types164
- Advanced Evaluation163
- Opentui163
- Evaluation162
- Hosted Agents162
- Multi Agent Patterns162
- Typescript Expert161
- Typescript React Reviewer160
- Workflow Creator146
- Ado Commit116
- Ado Create Pr115
- Research Codebase182
- Explain Code176
- Gh Commit172
- Prompt Engineer171
- Gh Create Pr170
- Context Compression168
- Create Spec168
- Sl Commit168
Recommended
cavemanjuliusbrussee/cavemanUltra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels618.3Kskills.sh installs
improveshadcn/improveSurvey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on s40Kskills.sh installs
systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes326.7Kskills.sh installs
karpathy-guidelinesforrestchang/andrej-karpathy-skillsBehavioral guidelines to reduce common LLM coding mistakes through explicit assumptions, simplicity, and verifiable success criteria.17.9Kskills.sh installs
find-skillsvercel-labs/skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express int4.3Mskills.sh installs