trackbed:code:optimize
(experimental) Run repeatable, metric-driven optimization experiments when a measurable outcome needs variants instead of guess-and-check.
/trackbed:code:optimize [spec.yaml | optimization goal] [--auto]- Invocation: User
- Hosts: Claude Code, Codex (
$trackbed:code:optimizein Codex) - Category: Code Changes
- Source:
trackbed/skills/code:optimize/SKILL.md
Description
Section titled “Description”(experimental) Run metric-driven optimization experiments. Use when search relevance, clustering quality, prompt quality, build latency, ranking behavior, bundle size, or another measurable outcome needs repeatable variants instead of sequential guess-and-check. Requires a measurement command or judge rubric, persists baselines and experiment logs under .context/code-optimize/, and can use serial or worktree-isolated experiments. Not for ordinary one-shot performance fixes, implementation without a harness, or speculative optimization with no metric.
Related
Section titled “Related”- Refers to:
trackbed:pr:code-review,trackbed:verify:run