Stats
Actions
Tags
From prompt-refiner
Refine a user prompt into a structured task brief for Claude Code. Use when the user asks to "refine", "improve", "optimize", "structure", or "rewrite" a prompt, or when a prompt is vague and could benefit from context-aware clarification.
How this skill is triggered — by the user, by Claude, or both
Slash command
/prompt-refiner:refineThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Refine user prompts into structured, actionable task briefs before Claude processes them.
Refine user prompts into structured, actionable task briefs before Claude processes them.
# Interactive refinement
prf refine
# Refine a specific prompt
prf refine "fix the login bug"
# Pipe input
echo "fix the user creation endpoint" | prf refine
When installed as a Claude Code plugin, prompts are automatically intercepted and refined via the UserPromptSubmit hook. The user sees a comparison and can accept, edit, or use the original.
The plugin uses userConfig for API key and provider settings, configured during installation.
To change configuration manually:
prf config set
Prefix with /no-refine or /nr to skip refinement for a single prompt.
Guides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.
npx claudepluginhub hav1d/claude-code-prompt-refiner --plugin prompt-refiner