Skip to main content
skill CX Codex

prompt-improver · happycapy-ai — Claude Code skill: prompt editing and installation

The prompt-improver skill turns underspecified requests into clearer prompts and explains the edits. Use it when you want to adapt a prompt for coding, writing, or image generation.

MIT ★ 138 updated 2026-09-03

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add happycapy-ai/Happycapy-skills --skill prompt-improver -a claude-code
Open on GitHub

What prompt-improver does

The skill asks what platform the prompt is for, which outcome matters most, and what context is missing. It then points out ambiguities, drafts a revised prompt, and describes the main changes. AskUserQuestion handles the clarifying questions.

In the regular flow, it can ask whether you want further edits. The “quick improve” path skips those questions and notes its assumptions, so the result depends on them. Choose “Aristotelian” or “first principles” to have the skill write instructions for another model to reason from basic axioms; the skill does not perform that reasoning itself.

What it helps with

  • Clarify a vague request for an AI
  • Add missing constraints and context to a prompt
  • Adapt a prompt to a platform and chosen priority
  • Draft instructions for first-principles reasoning

Example prompts for the agent

  • Improve this prompt for Claude Code: “Find the cause of this project error”
  • Make my request more precise; correctness matters most: “Write tests for this API”
  • Rewrite this request in Aristotelian mode: “Plan a database migration”

How to install prompt-improver

1Skills CLI (Vercel)

npx skills add happycapy-ai/Happycapy-skills --skill prompt-improver -a claude-code

2Manually: put the files in place

~/.claude/skills/prompt-improver/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/prompt-improver/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about prompt-improver

How do I install prompt-improver in Claude Code?

Run npx skills add happycapy-ai/Happycapy-skills --skill prompt-improver -a claude-code. The skill file is at ~/.claude/skills/prompt-improver/SKILL.md.

What does prompt-improver do?

It reviews a request for ambiguity, produces a revised prompt, and explains the main edits. In its regular flow, it also asks about the target platform, priorities, and missing context.

What does Aristotelian mode change?

It writes a prompt directing another model to reason from first principles and check its answer against the stated axioms. The skill does not do that reasoning itself.

Source text

SKILL.md · MIT
---
name: prompt-improver
description: Optimize prompts for better AI responses. Use when user asks to improve a prompt, refine a prompt, make a prompt better, optimize prompting, review their prompt, or says "/improve-prompt". Transforms vague requests into clear, specific, actionable prompts.
---

# Prompt Improver

Transform vague prompts into clear, specific, actionable ones for better AI responses.

## Workflow

1. **Gather context** - Use AskUserQuestion to clarify:
   - Target platform (Claude Code, ChatGPT, API, image gen)
   - Priority (accuracy, speed, depth, creativity)
   - Missing context (technical stack, constraints, examples)

2. **Analyze** - Identify what's unclear, missing, or ambiguous

3. **Improve** - Apply the framework (see references/framework.md)

4. **Present** - Show improved prompt with key changes explained

5. **Refine** - Ask if user wants adjustments

## AskUserQuestion Templates

**Initial clarification:**
```
questions:
  - header: "Platform"
    question: "What will you use this prompt for?"
    options:
      - label: "Claude Code"
        description: "Coding, file ops, terminal"
      - label: "ChatGPT/Claude.ai"
        description: "General conversation"
      - label: "API/Automation"
        description: "Programmatic use"
      - label: "Image gen"
        description: "DALL-E, Midjourney, etc."
  - header: "Priority"
    question: "What matters most?"
    options:
      - label: "Accuracy"
        description: "Correctness is critical"
      - label: "Speed"
        description: "Quick, concise"
      - label: "Depth"
        description: "Comprehensive"
      - label: "Creativity"
        description: "Novel approaches"
```

**Post-improvement:**
```
header: "Refine"
question: "Adjust the improved prompt?"
options:
  - label: "Looks good"
    description: "Use as-is"
  - label: "More specific"
    description: "Add constraints"
  - label: "More concise"
    description: "Shorten"
  - label: "Different focus"
    description: "Change emphasis"
```

## Output Format

```markdown
## Analysis
[Brief issues/opportunities]

## Improved Prompt
[Ready-to-use prompt]

## Key Changes
- [Change]: [Why]
```

## Quick Mode

If user says "quick improve", skip questions and make reasonable assumptions. Note assumptions made.

## Aristotelian Mode (First Principles)

Activated when user says "Aristotelian", "first principles", or "proof-based". Instead of the standard framework, produce a prompt that **instructs the receiving LLM to reason from first principles** when executing the task.

The prompt-improver does NOT do the Aristotelian reasoning itself. It crafts a prompt that tells the LLM to:

1. **Gather context from user** - Ask what system capabilities, tools, and constraints exist. Bake known context (root access, AI model, available tools, domain) directly into the prompt as given axioms.

2. **Embed the reasoning directive** - The improved prompt tells the LLM to:
   - Identify the atomic, irreducible truths of the task before acting
   - Interrogate each truth: "Can this be decomposed further? If removed, does the task break? Does it contradict anything?"
   - Discard anything that is not strictly necessary
   - Build the solution deductively, where every action traces to a stated axiom
   - Verify the result against the axioms at the end

3. **Structure the output prompt** with these sections:
   ```
   REASONING DIRECTIVE: [Instruct the LLM to use first-principles reasoning]
   GIVEN AXIOMS: [Known truths about system, capabilities, domain -- baked in]
   TASK: [What to accomplish]
   METHOD: [Tell LLM to discover task-specific axioms, interrogate them, then build deductively]
   VERIFICATION: [Tell LLM to check its result against its axioms]
   ```

**Output format for Aristotelian mode:**
```markdown
## Analysis
[What context was embedded and why]

## Improved Prompt (Aristotelian)
[The complete prompt with reasoning directive, given axioms, task, method, and verification]

## What This Prompt Does
- Tells the LLM to [specific reasoning behavior]
- Bakes in [specific context] so the LLM does not hallucinate it
```

See references/aristotelian.md for the full methodology and prompt structure.

## References

- **Framework details**: See references/framework.md for the 6-principle improvement framework
- **Aristotelian mode**: See references/aristotelian.md for the proof-based first principles methodology
- **Examples**: See references/examples.md for before/after transformations
- **Anti-patterns**: See references/anti-patterns.md for common issues to fix

© happycapy-ai · MIT · happycapy-ai/Happycapy-skills

Similar skills

All skills for AI and ML →

prompt-improver by other authors comes first.

prompt-improver dotneet The prompt-improver skill reviews prompts, spots missing context and turns vague requests into clearer instructions. Use it when an agent task lacks scope or checks. CX Codex +1 519installs automatic-stateful-prompt-improver curiositech automatic-stateful-prompt-improver intercepts complex prompts to refine them via DSPy, APE, and OPRO techniques. Stores optimization outcomes in an MCP server to learn across sessions. CX Codex +1 207installs claude-md-improver official Anthropic The claude-md-improver skill audits CLAUDE.md files, produces a quality report, and suggests focused edits. Use it when project instructions need a careful review. CX Codex +1 12,558installs agents-md-improver waybarrios agents-md-improver audits project rule files and suggests focused updates so coding agents retain current repository context. Use it when AGENTS.md or CLAUDE.md needs review. CX Codex +1 145installs ai-prompt-engineering-safety-review official github The ai-prompt-engineering-safety-review skill reviews prompts for safety, bias, security flaws, and clarity, then suggests concrete improvements. Use it before putting prompt changes into practice. CX Codex +1 10,327installs prompt-master nidhinjs The prompt-master skill writes and improves prompts for a named AI tool. Use it when a rough request needs to become a ready-to-paste prompt for Claude Code, Cursor, or another supported tool. CX Codex +1 4,900installs prompt-engineering giuseppe-trisciuoglio The prompt-engineering skill helps write, debug, and test LLM prompts. Use it for few-shot examples, system prompts, reasoning workflows, and reusable templates. CX Codex +1 4,200installs

From the same set41

The whole set →
agent-4-code-writer agent-4-code-writer — a Claude Code subagent that implements fixes or features within an open-source contributor swarm using an existing issue plan and codebase map. CX Codex ★ 138repo stars agent-3-codebase-explorer agent-3-codebase-explorer explores a repository before a fix or feature, locating relevant files and documenting the project structure for the next agents. CX Codex ★ 138repo stars agent-2-issue-analyst agent-2-issue-analyst is a Claude Code subagent that turns a chosen GitHub issue into a spec with complexity, files to touch and an ordered fix plan. CX Codex ★ 138repo stars agent-6-docs-writer agent-6-docs-writer is a Claude Code subagent that keeps README files, API docs, code comments, and CHANGELOG entries aligned with code updates in contributor swarms. CX Codex ★ 138repo stars agent-5-test-writer agent-5-test-writer writes tests for Agent 4's code changes: picks the repo's framework, adds regression and unit tests, runs the full suite, and records results in ./workspace/test-changes.json. CX Codex ★ 138repo stars mobile-app-developer mobile-app-developer guides Claude Code through scaffolding, previewing, and shipping Expo or React Native apps via EAS cloud builds without needing Xcode or a Mac. CX Codex +1 ★ 138repo stars pptx Create a PowerPoint deck from a topic or content brief. The skill saves the finished .pptx file in outputs/. CX Codex +1 ★ 138repo stars agent-0-repo-qualifier agent-0-repo-qualifier grades GitHub repositories before issue hunting starts: commit recency, license, maintainer response, CLA blockers. Hands a scored shortlist to the next agent. CX Codex ★ 138repo stars

Project sponsors

Companies that keep this analytics open