Stats
Actions
Tags
From prompt-engineering
Iteratively optimizes prompts using prompt-reviewer for issue detection, user input for ambiguities, and prompt-engineering for fixes until no issues remain. Use on prompt files needing refinement.
How this skill is triggered — by the user, by Claude, or both
Slash command
/prompt-engineering:auto-optimize-promptThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
**User request**: $ARGUMENTS
User request: $ARGUMENTS
Iteratively optimize a prompt until no issues remain.
Loop until prompt-reviewer finds no issues: review → resolve NEEDS_USER_INPUT with user → fix via prompt-engineering → repeat.
/tmp/auto-optimize-*.md during iterations; apply to original only when converged| Constraint | Why |
|---|---|
| Converge, don't cap | No iteration limits—run until no issues |
| Atomic output | Original unchanged until fully converged |
| DRY | Delegate review to prompt-reviewer, fixes to prompt-engineering |
| User-in-the-loop | NEEDS_USER_INPUT issues require user resolution (with context, options); skip if user declines |
Report: file path, iterations, issues fixed (auto vs user-resolved), issues skipped, summary of changes.
npx claudepluginhub doodledood/claude-code-plugins --plugin prompt-engineeringImproves prompts using Anthropic's 4-step workflow. Handles direct text, files, conversation context, iteration; adds XML, chain-of-thought, examples, clear formats.
Analyze and improve existing prompts for better performance
Creates, optimizes, and iteratively refines agent prompts, system prompts, and reusable templates. Handles prompt tuning, reliability improvements, and porting between OpenAI, Claude, or Gemini.