Creates, optimizes, and iteratively refines agent prompts, system prompts, developer prompts, and reusable prompt templates. Use when asked to improve a prompt, optimize a system prompt, rewrite an agent prompt, tune prompt wording, make a prompt more reliable, port prompts between OpenAI, Claude, or Gemini, or build prompt evals.
Permissions
Files
Creates, optimizes, and iteratively refines agent prompts, system prompts, developer prompts, and reusable prompt templates. Use when asked to improve a prompt, optimize a system prompt, rewrite an agent prompt, tune prompt wording, make a prompt more reliable, port prompts between OpenAI, Claude, or Gemini, or build prompt evals.
Optimize prompts with evals. Keep every instruction, example, and external context reference causal.
| Need | Read |
|---|---|
| New prompt | references/core-patterns.md, references/model-family-notes.md, references/transformed-examples.md |
Version history
| Existing prompt | references/meta-optimization-loop.md, references/core-patterns.md, references/model-family-notes.md |
| Model-family port | references/model-family-notes.md, references/core-patterns.md |
| Repeated failures | references/meta-optimization-loop.md, references/core-patterns.md |
| Weak or ambiguous draft | references/transformed-examples.md |
| Provenance | SOURCES.md |
Record before editing:
system, developer, user, tool descriptions, examples, schemasIf success criteria or examples are missing, create a small eval set first. If the bottleneck is model choice, retrieval, tool schema, or missing evals, say so before rewriting.
For repo or agent prompts, list stable context by exact path:
| Context type | Examples |
|---|---|
| Agent rules | AGENTS.md, CLAUDE.md |
| Specs | specs/*.md, docs/api.md |
| Policies | SECURITY.md, docs/releasing.md |
| Examples | examples/, tests/fixtures/ |
Rules:
loaded, referenced, or out of scope.Read references/model-family-notes.md.
Read references/core-patterns.md.
system or developer.Read references/meta-optimization-loop.md for refinements.
Return:
TargetSuccess CriteriaExternal ContextOptimized PromptAdapter NotesEval SetOptimization LogResidual RisksFor existing prompts, include a concise diff-style note of the main behavioral changes.
In these kits
Works with
Claude, Codex, Cursor & more