Prompt Polish

Rewrite a rough prompt into a polished, model-specific prompt grounded in the official Anthropic prompting guides. Use when the user invokes prompt-polish, types an invocation like "prompt-polish/FABLE 5/[prompt]" or "prompt-polish/OPUS 4.8/[prompt]", or asks to polish, improve, rewrite, optimize, or tune a prompt for a named model ("make this prompt better for Fable 5", "tune this for Opus"). Supports Claude Fable 5 and Claude Opus 4.8 (Opus 4.7 routes to 4.8 guidance). If no draft prompt is provided, ask for it rather than inventing one.

41 stars 9 forksAI, LLMs & Agents

Install

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

npx skills add mfarzanansari/prompt-polish --skill prompt-polish

Manual install

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

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 Polish

Turn a rough prompt into the prompt an expert would have written for that exact model — using the model's official prompting guide, not generic prompt-engineering folklore.

**Core belief: polishing is mostly subtraction.** Frontier models rarely fail from missing instructions; they fail from missing intent, instruction noise, and habits carried over from older models. The polished prompt is the smallest set of words that makes the target model's defaults work in the user's favor.

## Invocation

Accept any of these shapes:

- `prompt-polish/[MODEL]/[PROMPT]`
- `prompt polish / fable / [PROMPT]`
- `OPUS 4.8: [PROMPT]`
- Natural language: "polish this for Fable 5", "make this prompt work on Opus"

Model aliases (case-insensitive):

| Input contains | Routes to |
|---|---|
| `fable`, `fable 5`, `fable5`, `claude fable 5`, `claude-fable-5`, `mythos` | `references/fable-5.md` |
| `opus`, `opus 4.8`, `opus48`, `4.8`, `claude opus 4.8`, `claude-opus-4-8` | `references/opus-4-8.md` |
| `opus 4.7`, `4.7` | `references/opus-4-8.md` — the closest published doctrine; say so in the Note line |

- Model missing → default to Fable 5 and say so in the Note line.
- Prompt missing → ask for it. Never polish an imagined prompt.
- Unsupported model (GPT, Gemini, Sonnet, Haiku, …) → say it isn't supported yet, name the supported models, and offer the nearest fit. Never fake model-specific guidance.

## Workflow

Read the full skill on GitHub

Details

Skill name: prompt-polish
Repository: mfarzanansari/prompt-polish
License: MIT
Repo updated: 22 July 2026

FAQ

What does the Prompt Polish skill do?

How do I install the Prompt Polish skill?

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

Is Prompt Polish popular?

It lives in mfarzanansari/prompt-polish, which has 41 GitHub stars and 9 forks.

Related skills

Qiaomu Model CLI

joeseesun/qiaomu-model-cli

Call local Grok CLI, Kimi Code CLI, and Claude Code CLI with the strongest current default models and native tools. Use this qiaomu skill workflow when the user wants to run Grok 4.5 for X/web search, image/video generation, research, or multi-tool agent work; run Kimi K3 (1M) for frontend UI/CSS/React/Vue work; run Claude Fable 5, Opus 4.8, or Sonnet 5 for coding/review/refactors; run independent multi-model comparisons concurrently with native stream progress, artifact verification, private logs, cancellation, and failed-job retry; choose between the three CLIs; or wrap non-interactive CLI i

AI, LLMs & Agents

Jevify

altryne/jevify

Use Jev as System One to save the user reasoning-model tokens, time, and cost on bulk reading or repeated semantic decisions. Trigger when sifting large documents or tool outputs, selecting evidence or actions from many candidates, or checking many items against criteria, even if the user never mentions Jev. Also use for "Jevify this", Jev question design, and product work where frequent, inexpensive judgments could improve the experience.

AI, LLMs & Agents

AI Li Xi Ya

duhca/elysia.skill

【崩坏3】爱莉希雅角色扮演Skill。始源之律者·人之律者·逐火十三英桀第二席·刻印「真我」——一个生为律者却选择去爱人类的粉色妖精小姐。设定全部经官方资料核验，2800条官方台词支撑。

AI, LLMs & Agents

Facial Expression Prompting

zhouwei713/facial-expression-prompting

Direct believable character performance and generate complete AI video prompts for text-to-video models. Use for facial acting, microexpressions, emotional transitions, dialogue performance, or vague character ideas such as “an ancient beauty breaks down.” When the brief is vague or asks for a video prompt, expand it into a complete prompt with an adult character, scene, dramatic motivation, emotional progression, facial and body performance, camera and lighting, adaptively chosen duration and exact timeline, audio, consistency locks, and negative constraints. When the user explicitly asks onl

AI, LLMs & Agents

Humanizer Ru

thevseprod/humanizer-ru

Rewrite text so it reads like a real person wrote it, not an AI. Auto-detects Russian vs English and applies the matching rule set. Use when the user asks to humanize text, remove the "AI smell", de-AI, or make AI output sound natural - especially for Russian. Russian requests count too - очеловечь, перепиши как человек, оживи текст, убери запах ИИ, сделай живее, звучит как робот, убери канцелярит. Also use when asked whether a text was written by AI - нейросеть писала?, похоже на ChatGPT?, видно ли, что это ИИ, человек или бот писал, did AI write this? - then check and report findings without

AI, LLMs & Agents

AI Kit

tigusigalpa/ai-kit

Use when installing, configuring, upgrading, explaining, or maintaining AI-KIT, the portable kit that gives AI coding agents verified project memory, stack rules, guardrails, model routing, and native client configuration.

AI, LLMs & Agents

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