Real file from a public repo · synced Sep 3, 2026
arize-prompt-optimization
Optimizes, improves, and debugs LLM prompts using production trace data, evaluations, and annotations. Extracts prompts from spans, gathers performance signal, and runs a data-driven optimization loop using the ax CLI. Use when the user mentions optimize prompt, improve prompt, make AI respond better, improve output quality, prompt engineering, prompt tuning, or system prompt improvement.
Works with
Install in three steps
- 1
Download the ZIP
One file per agent, plus INSTALL.md with the exact paths below.
- 2
Claude Code: copy SKILL.md into your skills folder
.claude/skills/arize-prompt-optimization/SKILL.md # this project ~/.claude/skills/arize-prompt-optimization/SKILL.md # every project
- 3
Other agents: use the matching file
skill.mdc goes in Cursor’s .cursor/rules/. AGENTS.md works as GitHub Copilot instructions, a legacy .cursorrules, or a Codex / Gemini CLI instructions file.
More Debugging skills
All Debugging skills
diagnosing-bugsmattpocock/skillsDiagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.Debugging477.6k
explore-codelllllllama/rigorpilot-skillsRigor Improve implementation leaf skill for auditable candidate implementation in deep learning research repositories. Use when the researcher explicitly authorizes exploratory work on an isolated branch or worktree to transplant modules, adapt a backbone, add LoRA or adapter layers, replace a head, or stitch together meaningful low-risk migration ideas with rollback-aware records in explore_outputs/. Do not use for end-to-end exploration orchestration on top of current_research, trusted baseline reproduction, conservative debugging, environment setup, verified contribution claims, or default repository analysis.Debugging310.6ksafe-debuglllllllama/rigorpilot-skillsRigor Debug / Rigor Audit skill for deep learning research work. Use when the user pastes a traceback, terminal error, CUDA OOM, checkpoint load failure, shape mismatch, NaN loss symptom, or training failure and wants conservative diagnosis before any patching, with debug fixes clearly separated from research contributions. Do not use for broad refactoring, speculative adaptation, automatic exploratory patching, or general repository familiarization.Debugging310.5k
