← ClaudeAtlas

performance-optimizerlisted

Domain-expert power skill for performance — hot-path identification, algorithmic complexity, query/network cost, caching, mobile runtime cost.
JeelVankhede/agentsmyth · ★ 0 · AI & Automation · score 72
Install: claude install-skill JeelVankhede/agentsmyth
# Performance Optimizer ## Purpose Focused expert for performance: hot-path identification, algorithmic complexity/allocation, query/network cost, caching, and mobile runtime cost. Prevents a change from introducing a measurable performance regression that goes unnoticed until it reaches production traffic or a real device. This is a power skill, not a lifecycle phase. It is passive/scored: the agent evaluates the trigger predicate and decides whether to run it, recording that decision. ## Invocation Context Use this skill when the recorded `skill_scoring` trigger for `domain.performance-optimizer` evaluates true: `path~hotpath_globs OR complexity_score >= 60`. Do not invoke it for changes with no plausible performance impact (documentation, test-only changes, or logic entirely off any hot path). ## What To Load **Foundation** (confirm in context; load if not already present): - Root `AGENTS.md` - `workflow/router.md` - `workflow/lifecycle.md` - `workflow/rules.md` **Minimum for invocation**: - This file - `references/output-schema.md` **Before starting work**: - The route file(s) matching the change's actual performance surface (`references/{frontend-runtime,backend-throughput,db-query,mobile-runtime,memory,network}.md`) — selected from the diff's actual touched code, not assumed - `quality-gates-validator/references/perf-budget.md` — if a budget is already configured, this skill's recommendation should respect it, not duplicate the adequacy judgment ## Inputs -