Skip to main content

​
/refine — Prompt Optimizer

Transform any brief, draft, or one-liner into a production-ready structured prompt.

​
When to Use

  • User wants to improve a prompt or brief
  • User references /refine with text or a file path
  • An agent needs to optimize a prompt before dispatching it

​
Modes

​
File Mode

Reads the target file, optimizes it, and overwrites in place.

​
Text Mode

Optimizes the text and writes to /tmp/prompts/<slug>.md.

​
Flow

  1. Detect mode — argument starts with @ → file mode; otherwise → text mode.
  2. Read input — file mode reads the target file; text mode uses the raw argument.
  3. Spawn refiner subagent — system prompt = the Prompt Optimizer, input = user text.
  4. Receive output — the subagent returns the optimized prompt body only.
  5. Write output — file mode overwrites source; text mode writes to /tmp/prompts/.
  6. Report — print the path of the written file.

​
Prompt Type Detection

The optimizer classifies prompts and applies type-specific patterns:

​
Core Patterns

The optimizer applies these structural patterns:
  • D/I/V (Discovery / Implementation / Verification) — task decomposition with rollback points
  • Success/Failure Boundaries — concrete criteria with pass/fail markers
  • Concrete Examples — code samples over descriptions
  • Scope Controls — explicit boundaries to prevent scope creep

​
Rules

  • Never add wrapper text or commentary to the output file
  • Never execute the prompt — only rewrite it
  • Single-turn execution only — no clarification loops
  • File mode overwrites in place
  • Text mode always writes to /tmp/prompts/