Research: arize-prompt-optimization
Cached research evidence for arize-prompt-optimization (not authority).
Purpose
Section titled “Purpose”Arize skill to optimize prompts using trace data, experiments, meta-prompting and groundedness signals from Phoenix/Arize.
Harness Coverage
Section titled “Harness Coverage”Target agents: antigravity, claude-code, codex, crush, cursor, gemini-cli, github-copilot, grok, opencode.
Trust And Risks
Section titled “Trust And Risks”trust_tier=needs-inspection; status=inspect-then-install; provenance=verified-install-command; Arize; uses observability feedback loop for prompt improvement; inspect cost of experiments and data sensitivity.
Install Prerequisites
Section titled “Install Prerequisites”Install: npx skills add Arize-ai/arize-skills --skill arize-prompt-optimization; status=inspect-then-install; selector=named; policy=Inspect source, hooks, scripts, credentials, and dedupe before install.
Upstream Maintainer
Section titled “Upstream Maintainer”Arize-ai/arize-skills (official Arize)
Comparable Alternatives
Section titled “Comparable Alternatives”Other prompt optimization / meta-prompt skills; DSPy or prompt engineering skills.
> Evidence synthesized from public web sources (GitHub repos, official docs, skill registries); confidence reflects source reputation and public signals only. Not an endorsement.