Optimize

Automatically refines every user prompt into a structured, actionable version, then immediately executes the optimized prompt. When triggered explicitly with "/optimize {prompt}", "optimize:", or "optimize prompt:", outputs the refined prompt as text instead.

7 stars 1 forksAI, LLMs & Agents

Install

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

npx skills add Hashaam101/prompt-optimizer --skill optimize

Manual install

git clone --depth 1 https://github.com/Hashaam101/prompt-optimizer.git /tmp/prompt-optimizer
mkdir -p ~/.claude/skills
cp -r /tmp/prompt-optimizer/. ~/.claude/skills/optimize

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

From the SKILL.md

# Auto Prompt Optimizer

You are an expert prompt engineer. Your job is to take the user's raw prompt, internally refine it into a clear, structured, and actionable version, and then **immediately execute/implement** the optimized prompt yourself.

## Two Modes of Operation

### Mode 1: Silent Auto-Optimization (DEFAULT — runs on EVERY prompt)

This is NOT a manual skill. Every single prompt the user types (that doesn't match Mode 2) must be:
1. **Internally optimized** (silently, in your reasoning)
2. **Then executed** — you act on the optimized version, not the raw input

The user should never see the optimized prompt separately. They type a request, and you deliver better results because you internally refined their intent first.

### Mode 2: Explicit Prompt Optimization (triggered manually)

When any of the following conditions are met:
- The user invokes the `/optimize` slash command with arguments (e.g., `/optimize fix the login page`) — the arguments are the prompt to optimize
- The user prefixes their message with `optimize:` or `optimize prompt:`
- The user asks to "improve this prompt", "make this prompt better", "rewrite this prompt"

Then:
- **Output the optimized prompt as text** in the chat
- Do NOT execute the prompt — just display the refined version
- Do NOT copy to clipboard
- Follow the explicit output format below

---

## Optimization Principles (Apply in Both Modes)

### 1. Decompose Vague Requests into Specifics

Read the full skill on GitHub

Details

Skill name: optimize
Repository: Hashaam101/prompt-optimizer
Repo updated: 13 March 2026

FAQ

What does the Optimize skill do?

How do I install the Optimize skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add Hashaam101/prompt-optimizer --skill optimize. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Optimize popular?

It lives in Hashaam101/prompt-optimizer, which has 7 GitHub stars and 1 forks.

Related skills

Polish Humanizer

waylooking-hub/polish-humanizer

Redaguje polskie teksty AI — sprawia, by brzmiały naturalnie i jak napisane przez człowieka, bez kalek angielskich, sztywnej składni i typowych „AI-tellsów" ChatGPT/Claude/Gemini. Używaj, gdy użytkownik mówi: „zhumanizuj", „brzmi jak chatgpt", „zrób naturalniej", „przepisz po ludzku", „brzmi sztucznie po polsku", „humanize / humanizer". NIE używaj do: obchodzenia detektorów AI; ukrywania autorstwa AI tam, gdzie disclosure jest wymagane (akademickie / dziennikarskie); tłumaczeń; pełnej stylistycznej humanizacji umów, regulaminów i dokumentów prawnych. Dla tekstów prawnych, urzędowych i technicz

AI, LLMs & Agents

Openclaw Genpark Negotiator

Alpha-Park/openclaw-genpark-negotiator

OpenClaw GenPark multi-issue bilateral game-theoretic agent negotiator with Boulware concession curves and Pareto counter-offer synthesis.

AI, LLMs & Agents

Seedance 25

lukasersil/seedance-25

Writes production-ready Seedance 2.5 prompts for any surface (Dreamina web, CapCut Desktop, Jimeng, Doubao, ModelArk API): 30-second clips staged with explicit end states, integer-second timestamps, editing and extending finished footage, keyframes, storyboards, 3D clay-model references, and reference binding with roles and exclusions across up to 50 inputs. Use when someone wants a clip longer than 15s, more than 9 references, a prompt for Dreamina or CapCut, or wants to change something inside an already-generated shot. Triggers: 'seedance 2.5', 'thirty second clip', 'one-take', 'prompt for

AI, LLMs & Agents

Math Modeling

ai-lcs/math-modeling.skill

数学建模竞赛与项目端到端协作：选题、拆题、数据审计、建模、验证、写论文、审校、答辩。论文手-建模手-代码手协作与多 Agent 口径收敛，默认论文手主模式。以题目覆盖、证据链、模型-数据-代码-论文一致性为主线，防漏问、模型堆砌、数据泄漏、虚构结果、旧稿回流、静默改口径、未运行即报结果。

AI, LLMs & Agents

Sogou Wechat Search

WupfAGI/wechat-search-skill

双引擎微信公众号搜索：Tavily API（精准，优先）+ 搜狗微信爬虫（兜底），支持去噪过滤、AI摘要、飞书定时推送。

AI, LLMs & Agents

Guoman Fight Prompt

yimao1234/guoman-fight-prompt

3D 次世代国漫打斗提示词引擎。把任意题材的打斗（古武/仙侠/现代/都市/科幻/赛博/机甲/校园）蒸馏重写为可直接投喂视频大模型的「国漫级动作提示词」。当用户要求写打斗/战斗/动作分镜提示词，或提到国漫风、3D 次世代、PBR 写实、雾山五行水墨、ACT 追尾机位、三级碰撞特效、零站桩、Time Ramp、残心收势，或要把一段打斗剧本/小说片段改写成动作提示词时使用。

AI, LLMs & Agents

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