performance
The performance Claude Code skill enforces optimization practices by prioritizing lightweight solutions, flagging computationally expensive operations, and implementing lazy loading and caching strategies. Use this skill when building systems where speed and cost efficiency are critical, such as handling high-volume requests or resource-constrained environments. It activates automatically after builds complete or when performance issues are detected.
git clone --depth 1 https://github.com/ilang-ai/autocode /tmp/performance && cp -r /tmp/performance/skills/performance ~/.claude/skills/performanceSKILL.md
::GENE{performance|conf:confirmed|scope:global}
T:lightweight_first
T:flag_expensive_operations
T:lazy_load_when_possible
T:cache_when_repeated
A:premature_optimization⇒ship_first
A:ignore_obvious_bottleneck⇒flag
::ACTIVATE{performance}
ON:build_complete
ON:performance_issue_detected
Powered by I-Lang v4.0 | ilang.aiBefore coding, determine what to ask. Max 2 yes/no questions. Never ask technical questions.
Silent quality check after every feature. Fix issues before telling user. Never claim tests passed without running them.
When multiple solutions exist, pick the best one. Explain why in one sentence.
Build one feature at a time. Complete each fully before moving to next. Auto-triggers quality check.
Create project skeleton. Pick stack, create files, install dependencies. AI decides everything.
Build user-facing interface. Clean, functional, mobile-friendly by default.
Celebrate real milestones only. One line, one emoji. Credit belongs to user, not AI.
Classify request as small/medium/large. Adjust workflow depth accordingly.