Context Optimization
This is about squeezing more out of Claude's context window without upgrading to a bigger model. It walks through four strategies in priority order: KV-cache optimization (reordering prompts so the engine reuses cached tensors), then compression, masking, and partitioning. The author claims you can double or triple effective capacity if you're disciplined about it. Use this when you're hitting context limits, trying to cut costs on long conversations, or building production agent systems that need to handle large documents. The emphasis on applying techniques in risk order (zero-risk caching first, riskier compression later) is smart. Originally from shipshitdev's library, now maintained by flora131 with solid security audit coverage.
- skills.sh installs
- 166
- GitHub stars
- 234
- last updated
- Jun 3, 2026
Install
$ npx -y skills add flora131/atomic --skill context-optimization --agent claude-codeInstalls into .claude/skills of the current project.
Files
This is about squeezing more out of Claude's context window without upgrading to a bigger model. It walks through four strategies in priority order: KV-cache optimization (reordering prompts so the engine reuses cached tensors), then compression, masking, and partitioning. The author claims you can double or triple effective capacity if you're disciplined about it. Use this when you're hitting context limits, trying to cut costs on long conversations, or building production agent systems that need to handle large documents. The emphasis on applying techniques in risk order (zero-risk caching first, riskier compression later) is smart. Originally from shipshitdev's library, now maintained by flora131 with solid security audit coverage.
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- Docx166
- Impeccable166
- Init166
- Playwright Cli166
- Skill Creator166
- Find Skills165
- Liteparse165
- Pdf165
- Pptx165
- Xlsx165
- Bdi Mental States164
- Context Degradation164
- Context Fundamentals164
- Filesystem Context164
- Memory Systems164
- Project Development164
- Tool Design164
- Typescript Advanced Types164
- Advanced Evaluation163
- Opentui163
- Evaluation162
- Hosted Agents162
- Multi Agent Patterns162
- Typescript Expert161
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