Imp

Improve and enhance any prompt or request before executing it. Use this skill whenever the user's message starts with "/imp" or when the user asks to "improve my prompt", "enhance this request", "optimize this prompt", or wants Claude to apply prompt engineering techniques before executing a task. The skill rewrites the user's raw request using best practices (clarity, XML structure, examples, context, role-setting), then executes the improved prompt and shows both the improved version and the result.

6 starsAI, LLMs & Agents

Install

skills CLI (Claude Code, Cursor, Codex and more)

npx skills add Arabianaischool/prompt-action --skill imp

Manual install

git clone --depth 1 https://github.com/Arabianaischool/prompt-action.git /tmp/prompt-action
mkdir -p ~/.claude/skills
cp -r /tmp/prompt-action/. ~/.claude/skills/imp

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Prompt Improver (imp)

Triggered when the user prefixes their request with `/imp` or asks to improve/enhance a prompt before execution.

## What This Skill Does

1. **Improve** the user's raw prompt using prompt engineering best practices
2. **Execute** the improved prompt
3. **Show** both the improved prompt and the result

---

## Step-by-Step Process

### Step 1: Extract the Raw Prompt

The user's actual request comes after `/imp`. For example:
- `/imp اكتب مقال عن الذكاء الاصطناعي` → raw prompt: `اكتب مقال عن الذكاء الاصطناعي`
- `/imp write a python function to sort a list` → raw prompt: `write a python function to sort a list`

### Step 2: Improve the Prompt

Apply the following techniques as appropriate:

**Clarity & Directness**
- Be explicit about desired output format, length, and tone
- Add specific constraints and success criteria
- Replace vague instructions with concrete ones
- Use numbered steps when order matters

**Context & Role**
- Add a relevant role/persona when beneficial (e.g., "You are an expert Python developer...")
- Include motivation or purpose behind the request
- Specify the intended audience

**Structure**
- Use XML tags to separate instructions, context, examples, and input
- Use `<instructions>`, `<context>`, `<format>`, `<examples>` tags where helpful
- Break complex tasks into explicit sub-steps

**Examples (Few-Shot)**
- Add 1–3 concrete examples if the task involves a specific pattern or format
- Wrap examples in `<example>` tags

Read the full skill on GitHub

Details

Skill name: imp
Repository: Arabianaischool/prompt-action
License: MIT
Repo updated: 13 April 2026

FAQ

What does the Imp skill do?

How do I install the Imp skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add Arabianaischool/prompt-action --skill imp. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Imp popular?

It lives in Arabianaischool/prompt-action, which has 6 GitHub stars and 0 forks.

Related skills

Keldron Agent

keldron-ai/keldron-agent

GPU monitoring with risk intelligence. Local + cloud fleet monitoring, health tracking, proactive alerts, and AI-powered fleet analytics.

AI, LLMs & Agents

Humanizer Ko

IsaacEryn/humanizer-ko

한국어 텍스트에서 AI 생성 글의 티를 찾아 제거한다. 글을 자연스러운 사람의 문장으로 다듬거나 검토할 때 사용. Remove signs of AI-generated writing from Korean text (humanize Korean text). 의의 부풀리기, 홍보성 언어, 연결어미 부가절, AI 어휘, 이중 피동, 번역투, 문체 혼용, 대구 연쇄, 결산 공식, 연결어미 뒤 쉼표, 줄표 남용, 상투적 마무리 등 37개 패턴을 탐지하고 고친다. 논문 초록 과적재·단서 누적·삼중 요약 같은 학술 원고 티와 발표 대본 티는 장르 참고 파일로 따로 본다.

AI, LLMs & Agents

Life Role Inventory

gala-rong/life-role-inventory

生涯與生活角色盤點——用結構化訪談清點你正在扮演的所有角色（工作只是其中之一：父母、伴侶、朋友、興趣、信仰都算），收斂成一張可驗證的現況地圖與錨點句，並可延伸為 AI 協作分工建議。當使用者說「盤點我的角色」「生涯盤點」「人生盤點」「生活盤點」「幫我整理最近生活的各條線」「我該聚焦什麼」「深度訪談我」時使用（無論第幾次，一律跑同一套單次流程）。純方法論 skill：不含任何受訪者個人資料；訪談內容一律寫在受訪者自管的筆記檔，不進入任何記憶或其他 skill。多檔結構：口語技巧庫、判例集、製作參考收於 references/，依檔案地圖按需載入。

AI, LLMs & Agents

Hubspot AI Context

chadstamm/claude-skill-hubspot-ai-context

Fill HubSpot's AI Context page (Business tab + Customers tab — ICPs and Personas) by crawling a client website, researching competitors and brand reputation (positive + negative), and generating click-to-copy paste-sheet HTML. Use when setting up a new client in HubSpot's AI/Breeze Intelligence layer or when refreshing existing context. Triggers — "fill out AI context", "set up HubSpot ICPs", "create paste sheet for [client]", "generate Breeze Intelligence context", "research competitors for [client]".

AI, LLMs & Agents

Logseq Outline

kerim/logseq-outline-skill

Format any content as a Logseq-compatible outline using nested bullets (no markdown headers, no bold). Works in both Claude Code and Claude Desktop.

AI, LLMs & Agents

Gpt Pro

199-biotechnologies/claude-skill-gpt-pro

Package files + structured prompts for manual copy-paste into GPT-5.4 Pro for deep reasoning review. Use when user says 'send to GPT Pro', 'GPT Pro review', 'ChatGPT Pro review', 'prepare for GPT', 'package for GPT Pro', 'get GPT to review', 'GPT Pro analysis', 'upload to ChatGPT', 'gpt-pro', '/gpt-pro', 'pack for GPT', 'bundle for ChatGPT', 'have ChatGPT check this', 'send this to GPT', 'GPT deep review'. Creates structured prompt + file bundle as tar.gz in ~/Documents/GPT Pro Analysis/ and copies prompt to clipboard for manual paste into ChatGPT Pro.

AI, LLMs & Agents

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.