qual-performance
Domain: qual · Model class: cheap
Description
Section titled “Description”Use this skill when the user wants to work on Reviewing code for performance hotspots, token efficiency, inference cost, and latency. Triggers include “analyze performance”, “find performance hotspots”, “optimize token usage”. Do NOT use when analyze overall code structure (use core-code-analysis).
Purpose
Section titled “Purpose”Reviewing code for performance hotspots, token efficiency, inference cost, and latency. This skill provides structured guidance, references, and worked examples to help produce high-quality, actionable outputs.
Trigger Phrases
Section titled “Trigger Phrases”- “analyze performance”
- “find performance hotspots”
- “optimize token usage”
- “reduce inference latency”
- “measure AI workflow cost”
Anti-Triggers
Section titled “Anti-Triggers”- analyze overall code structure (use core-code-analysis)
- design for scalability (use core-scalability-design)
Intake Questions
Section titled “Intake Questions”- What is the user’s goal and current state?
- What constraints (time, team, compliance) apply?
- Are there existing artifacts (specs, code, benchmarks) to reference?
Output Contract
Section titled “Output Contract”- quality findings
- evidence-grounded issues
- prioritized fixes
- verification guidance