Skip to content
Development
Command

/improve-prompt

Analyze and improve an AI prompt for clarity, specificity, and effectiveness.

From plugin
rohitg00-claude-code-toolkit
2.5k199 skills138 agents199 commands
Install
$ npx -y skills add rohitg00/awesome-claude-code-toolkit --agent claude-code

How it fires

How this command gets triggered: by you, by Claude, or both.

  • Fires itselfClaude auto-loads it when your prompt matches the work.
  • You can call itInvoke it directly when you want it.
  • Slash command/improve-prompt

Context preview

What this command does when you run it.

Analyze and improve an AI prompt for clarity, specificity, and effectiveness.

Command definition

improve-prompt.md
name: improve-prompt
description: Analyze and improve an AI prompt for clarity, specificity, and effectiveness.

Analyze and improve an AI prompt for clarity, specificity, and effectiveness.

Steps

1. Read the provided prompt or command definition. 2. Evaluate against prompt quality dimensions:

  • **Clarity**: Is the instruction unambiguous?
  • **Specificity**: Does it define the expected output format?
  • **Context**: Does it provide enough background information?
  • **Constraints**: Are boundaries and rules clearly stated?
  • **Examples**: Are there concrete examples of good output?

3. Identify common issues:

  • Vague verbs ("handle", "process", "manage") without specifics.
  • Missing edge case guidance.
  • No output format specification.
  • Contradictory instructions.
  • Missing success criteria.

4. Rewrite the prompt with improvements:

  • Add structured sections (Steps, Format, Rules).
  • Replace vague instructions with specific actions.
  • Add output format with examples.
  • Define explicit constraints and error handling.

5. Compare original vs improved versions side by side.

Format

Prompt Analysis:
  Clarity: <1-5>/5
  Specificity: <1-5>/5
  Context: <1-5>/5

Issues found:
  - <issue description>

Improved prompt:
  <rewritten prompt>

Changes made:
  - <what was improved and why>

Rules

  • Preserve the original intent; only improve clarity and structure.
  • Use imperative mood for instructions ("Run X" not "You should run X").
  • Every prompt should have Steps, Format, and Rules sections.
  • Limit prompts to under 50 lines; split complex workflows into sub-commands.
  • Test the improved prompt against the original to verify better results.
Read more
Ships withrohitg00-claude-code-toolkit

The most comprehensive toolkit for Claude Code -- 135 agents, 35 curated skills (+400,000 via SkillKit), 42 commands, 176+ plugins, 20 hooks, 15 rules, 7 templates, 15 MCP configs, 26 companion apps, 53 ecosystem entries, and more.

Get the whole plugin