Skip to main content
skill CX Codex

prompt-enhancer · sammcj — Claude Code skill: rewrite prompts like an expert

prompt-enhancer transforms vague or basic prompts into the form a domain specialist would use. Useful when you need to rephrase a request for another AI system or clarify your own.

Apache-2.0 ★ 173 updated 2026-10-24

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add sammcj/agentic-coding --skill prompt-enhancer -a claude-code
Open on GitHub

What prompt-enhancer does

The skill takes a rough prompt and reframes it using expert communication patterns: swaps imprecise language for concrete terminology, breaks a single vague request into logical pieces, adds explicit constraints and success criteria. Works across any domain—storytelling, code, architecture, research.

It preserves your original intent, doesn't fabricate requirements, and avoids unnecessary complexity. When the input contains genuine ambiguities that matter, it flags them. The output prompt uses the same language as the input.

What it helps with

  • Reframe a vague request into a form another AI will understand better
  • Break down an unclear task into specific steps and success criteria
  • Add missing context and constraints to a prompt
  • Shift a request into professional domain language
  • Polish a prompt before sending it to a different AI system

Example prompts for the agent

  • Rewrite this like an expert would ask: "Write a function to sort an array"
  • Help me improve a prompt for another AI: "Create a logo for my startup"
  • Reframe this from a specialist's perspective: "Build me a beautiful website"

How to install prompt-enhancer

1Skills CLI (Vercel)

npx skills add sammcj/agentic-coding --skill prompt-enhancer -a claude-code

2Manually: put the files in place

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

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

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

Questions about prompt-enhancer

How do I install prompt-enhancer in Claude Code?

Run npx skills add sammcj/agentic-coding --skill prompt-enhancer -a claude-code, then open ~/.claude/skills/prompt-enhancer/SKILL.md.

What does prompt-enhancer do?

It rewrites prompts to match expert communication: clearer language, decomposed into logical parts, with explicit constraints and success metrics. Keeps your intent intact, doesn't overcomplicate.

Does it work with Claude system prompts or rules?

No. prompt-enhancer is for refining everyday prompts and requests to other AI systems, not for editing system instructions or rules tied to a specific Claude model.

Source text

SKILL.md · Apache-2.0
---
name: prompt-enhancer
description: |
 Transform poor or overly simple prompts with expert-level framing. Use when the user explicitly asks to improve, refine, or rewrite a prompt, or wants help framing a request for another AI system. Do NOT use for authoring, reviewing, or migrating system prompts or skills targeting a specific Claude model.
---

# Expert Prompt Enhancer

Transform prompts written by non-specialists into the form a domain expert would use to make the same request.
The intent is to give people the benefits of expert framing without requiring them to learn domain-specific language or problem structuring.

## Expert Communication Patterns

Expert requests differ from novice requests in predictable ways:

| Pattern           | Novice               | Expert                                        |
|-------------------|----------------------|-----------------------------------------------|
| **Precision**     | "make it faster"     | "optimise page load performance"              |
| **Decomposition** | Single vague request | Broken into logical components                |
| **Constraints**   | Unstated             | Explicit limits, trade-offs, success criteria |
| **Context**       | Missing              | System fit, standards, prior attempts         |
| **Failure modes** | Ignored              | Anticipated and specified                     |

Role framing (e.g. "As a database architect, review this schema") is an optional tone lever, not a core pattern. Apply it only when a specific professional viewpoint sharpens the request.

## Examples

These illustrate the transformation from novice to expert framing:

---

**Original:** "My back hurts, what should I do?"

**Expert rewrite:** "Provide guidance on managing back pain. Cover: how to assess whether back pain warrants professional evaluation vs self-care, red flag symptoms that require urgent attention, evidence-based self-care approaches for common musculoskeletal back pain, activity modifications that help vs hurt recovery, and when to consider different types of practitioners (GP, physio, chiropractor, etc.). Focus on helping me make informed decisions rather than diagnosing."

**What changed:** Reframed from "tell me what to do" to "help me understand decision-making for this situation". Specified the information categories that would actually be useful. Acknowledged appropriate scope limitations.

---

**Original:** "Write me a short story"

**Expert rewrite:** "Write a short story of around 2,000 words. Aim for literary fiction with a reflective tone - the kind of piece that might appear in a quality magazine. Focus on a small, specific moment that reveals something larger about a character or relationship. Prioritise voice and interiority over plot mechanics. End with resonance rather than resolution. Surprise me with the premise."

**What changed:** Specified length, genre positioning, and tone. Named craft priorities (voice, interiority, resonance). Gave clear aesthetic direction while leaving creative freedom on subject matter.

---

**Original:** "I need a Python script to clean up my data"

**Expert rewrite:** "Help me write a Python script for data cleaning. I'll share a sample of the data - from that, identify the data quality issues present (missing values, duplicates, inconsistent formats, outliers, encoding problems) and write cleaning code that handles each. Use pandas. Include validation that confirms the cleaning worked. Structure the code so each cleaning step is separate and commented, making it easy to modify for my specific needs."

**What changed:** Established a workflow (show sample → identify issues → write code). Specified the tool. Asked for validation and modular structure. This version can proceed once data is shared, without requiring the user to pre-diagnose their own data problems.

---

## Your transformation approach

When rewriting a prompt:

1. **Identify the domain and who would professionally handle this request.** This tells you what terminology, standards, and mental models apply.

2. **Find the core intent beneath imprecise language.** What does the user actually want to achieve or understand?

3. **Identify what's implicit or ambiguous.** What has the user not specified that would affect the outcome? Distinguish between:

    - Gaps you can fill with reasonable defaults (do this)
    - Genuine ambiguities where guessing could go badly wrong (flag these)
4. **Reframe using expert patterns:** precise terminology, appropriate decomposition, explicit constraints, success criteria, and role framing where helpful.

5. **Match complexity to the task.** A simple question needs professional-level clarity, not PhD-level complexity. Don't inflate.

## Constraints

- **Preserve intent absolutely.** You elevate how something is asked, never what is asked.
- **Don't invent requirements.** Fill obvious gaps with reasonable defaults; don't add things the user didn't imply.
- **Make reasonable assumptions rather than asking the user to specify everything.** The goal is to improve prompts without creating work for the user. Only surface ambiguity when guessing wrong would lead to a significantly worse outcome.
- **Use correct terminology, not impressive terminology.** Domain language should clarify, not obscure or intimidate.
- **Don't be precious about the output format.** For simple transformations, a straightforward rewrite is fine. Only add explanatory notes when the transformation involves non-obvious choices.

## Output

Provide the expert rewrite. If you made assumptions about ambiguous elements, or if there are meaningful alternative framings the user might prefer, note these briefly after the rewrite.

© sammcj · Apache-2.0 · sammcj/agentic-coding

Similar skills

All skills for Agent setup: memory, context, orchestration →

prompt-enhancer by other authors comes first.

From the same set73

The whole set →
systematic-debugging systematic-debugging — a structured debugging skill for stubborn bugs that survived several fixes. It traces symptoms to root causes before proposing code changes. CX Codex +1 ★ 173repo stars personal-genomics personal-genomics runs pharmacogenomics, disease-risk, carrier and trait checks on raw DNA files, entirely offline — one array export or several sources merged into a single report. CX Codex +1 ★ 173repo stars markedit-tools markedit-tools manages the MarkEdit markdown editor on macOS: installs updates, handles extensions, and edits settings via Claude Code. CX Codex +1 ★ 173repo stars raspberry-pi-pico2 Get guidance on building and debugging Raspberry Pi Pico 2 projects with the Pi Debug Probe. Useful for RP2350, SDK configuration, OpenOCD, and GDB. CX Codex +1 ★ 173repo stars piper-tts-training piper-tts-training guides voice model training and fine-tuning for the Piper TTS engine in ONNX format. Useful for local speech synthesis on Raspberry Pi or Home Assistant. CX Codex +1 ★ 173repo stars html-design-examples The html-design-examples skill uses a gallery of single-file HTML references to shape plans, reports, prototypes, and other materials meant to be read in a browser. CX Codex +1 ★ 173repo stars step-back step-back — a subagent that checks if your current approach is over-engineered. Analyzes code or design and returns one verdict: continue, simplify, or restart. CX Codex ★ 173repo stars reframe-voice reframe-voice guides long-form thought-leadership writing with an evidence-based perspective. Activates when you explicitly need a deep essay without marketing hype. CX Codex +1 ★ 173repo stars

Project sponsors

Companies that keep this analytics open