
Tuzi Copy Polish
- 150 installs
- 37 repo stars
- Updated April 24, 2026
- tuziapi/tuzi-skills
Use tuzi-copy-polish for development tasks
About
tuzi-copy-polish: A skill for development. This provides functionality for development workflows.
- tuzi-copy-polish
Tuzi Copy Polish by the numbers
- 150 all-time installs (skills.sh)
- Ranked #2,522 of 4,347 Backend & APIs skills by installs in the Skillselion catalog
- Data as of Aug 5, 2026 (Skillselion catalog sync)
npx skills add https://github.com/tuziapi/tuzi-skills --skill tuzi-copy-polishAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 150 |
|---|---|
| repo stars | ★ 37 |
| Last updated | April 24, 2026 |
| Repository | tuziapi/tuzi-skills ↗ |
What it does
Use tuzi-copy-polish for development tasks
Files
Social Copy Polish
Optimizes social media copy for different platforms. Adjusts tone, length, hashtags, and formatting based on platform best practices.
Step 0: Load Preferences ⛔ BLOCKING
0.1 Check EXTEND.md
test -f .tuzi-skills/tuzi-copy-polish/EXTEND.md && echo "project"
test -f "$HOME/.tuzi-skills/tuzi-copy-polish/EXTEND.md" && echo "user"| Result | Action |
|---|---|
| Found | Load, parse, apply settings |
| Not found | Continue with defaults (ask platform in Step 2) |
| Path | Location |
|---|---|
.tuzi-skills/tuzi-copy-polish/EXTEND.md | Project directory |
$HOME/.tuzi-skills/tuzi-copy-polish/EXTEND.md | User home |
EXTEND.md Supports: Default platform | Default language | Custom brand voice
Schema: references/config/preferences-schema.md
Step 1: Analyze Input
Determine input source:
- File path: Read file content as draft copy. Record the file path for Step 3 output.
- Inline text: Use the text directly as draft copy.
Identify:
- Content type (product promotion, knowledge sharing, personal story, news, opinion)
- Current language and tone
- Key message and selling points
- Target audience (if mentioned)
Step 2: Confirm Platform
If platform not specified by user or EXTEND.md, use AskUserQuestion:
header: "Target Platform"
question: "优化目标平台?"
options:
- label: "小红书"
description: "种草风、emoji、标签、口语化"
- label: "X/Twitter"
description: "简洁有力、英文友好、话题标签"
- label: "抖音"
description: "口语化、悬念开头、引导互动"
- label: "微信公众号"
description: "深度内容、段落清晰、引导关注"
- label: "通用"
description: "不针对特定平台,仅优化表达"Step 3: Polish Copy
Load platform rules from references/platforms/, then rewrite:
Optimization Dimensions
| Dimension | Description |
|---|---|
| Hook | Opening line that grabs attention |
| Tone | Match platform culture (e.g., 小红书 casual, 公众号 professional) |
| Length | Trim or expand to platform sweet spot |
| Structure | Platform-specific formatting (line breaks, paragraphs, lists) |
| Hashtags | Add relevant tags per platform convention |
| CTA | Call-to-action matching platform interaction patterns |
| Emoji | Platform-appropriate emoji usage |
Output Format
If input is a file path: Append the polished copy to the end of the original file, separated by a clear divider:
---
## Polished Copy ({platform})
{polished content}Then inform the user: "已将优化后的文案追加到文件末尾: {file_path}"
If input is inline text: Present the polished copy in a code block for easy copying.
In both cases, include a brief changelog (what was changed and why, 2-3 bullet points).
Multiple Variants
When the user asks for options, generate 2-3 variants with different angles:
- Variant A: Focus on emotion/story
- Variant B: Focus on value/benefit
- Variant C: Focus on curiosity/hook
Step 4: Iterate
After presenting the polished copy, ask if the user wants to:
- Adjust tone (more casual / more professional)
- Try a different angle
- Optimize for another platform
- Fine-tune specific parts
Extension Support
Custom configurations via EXTEND.md. See Step 0 for paths and supported options.
Preferences Schema
Full Schema
---
version: 1
default_platform: null # xiaohongshu|x-twitter|douyin|weixin|null
default_language: null # zh|en|null (null = auto-detect from input)
brand_voice: null # Custom brand voice description (free text)
---Field Reference
| Field | Type | Default | Description |
|---|---|---|---|
version | int | 1 | Schema version |
default_platform | string\ | null | null |
default_language | string\ | null | null |
brand_voice | string\ | null | null |
Examples
Minimal:
---
version: 1
default_platform: xiaohongshu
---With brand voice:
---
version: 1
default_platform: x-twitter
default_language: en
brand_voice: "Professional but approachable. Use data-driven arguments. Avoid slang."
---抖音 (Douyin / TikTok)
Platform Rules
| Parameter | Guideline |
|---|---|
| Title | 15-30 字,悬念或痛点 |
| Description | 50-150 字,口语化 |
| Hashtags | 3-5 个,热门+垂直 |
| Emoji | 适量,1-3 个 |
| Tone | 口语化、有节奏感、引导互动 |
Writing Style
- 前 5 个字决定用户是否继续看
- 悬念开头:"你知道 XX 吗?"
- 口语化,像在跟人说话
- 短句、有节奏感
- 结尾引导评论:"你觉得呢?"
Patterns
- 悬念型:"99% 的人不知道..."
- 教程型:"教你一招 XX"
- 反转型:"我以为 XX,没想到..."
- 共鸣型:"有没有人跟我一样..."
Structure Template
[悬念/痛点开头]
[核心内容,2-3 句]
[引导互动:提问/投票/评论]
#标签1 #标签2 #标签3微信公众号 (WeChat Official Account)
Platform Rules
| Parameter | Guideline |
|---|---|
| Title | 22 字以内,核心信息前置 |
| Body | 800-3000 字,深度内容 |
| Hashtags | 1-3 个公众号标签 |
| Emoji | 少量,标题可用 |
| Tone | 专业、有深度、可信赖 |
Writing Style
- 段落清晰,每段 3-5 行
- 小标题分隔内容块
- 数据和案例增强说服力
- 金句/引用提升格调
- 结尾引导关注和转发
Patterns
- 深度解析:"关于 XX,你需要知道的一切"
- 观点输出:"为什么我认为 XX"
- 干货总结:"XX 的 N 个关键要点"
- 故事驱动:"从 XX 说起..."
Structure Template
[标题:核心价值前置]
[开头:背景/痛点/故事引入,2-3 段]
[正文:分小标题展开]
## 要点一
...
## 要点二
...
[总结:核心观点回顾]
[CTA:关注/转发/留言引导]X / Twitter
Platform Rules
| Parameter | Guideline |
|---|---|
| Length | 280 chars max (ideal: 70-200) |
| Hashtags | 1-3, at end or inline |
| Emoji | Sparingly, 0-2 per post |
| Tone | Sharp, witty, opinionated |
| Thread | Break long content into numbered tweets |
Writing Style
- Lead with the strongest point
- One idea per tweet
- Use line breaks for readability
- Contrarian or surprising takes perform well
- End with a question or CTA for engagement
Patterns
- Hot take: "Unpopular opinion: ..."
- Thread opener: "Here's what I learned about X (thread 🧵)"
- Listicle: "5 things about X:\n\n1. ..."
- Story: "Last week I ... Here's what happened:"
Structure Template
[Hook: strong opening statement]
[Supporting point or story]
[CTA or question]
#tag1 #tag2小红书 (Xiaohongshu / RedNote)
Platform Rules
| Parameter | Guideline |
|---|---|
| Title | 20 字以内,含 emoji,制造好奇心 |
| Body | 300-800 字,口语化,分段短 |
| Hashtags | 5-10 个,混合热门+精准标签 |
| Emoji | 大量使用,每段 1-3 个 |
| Tone | 闺蜜聊天、真诚分享、种草感 |
Writing Style
- 第一人称,像跟朋友聊天
- 短句为主,每段 2-3 行
- 多用感叹句和反问句
- 避免硬广感,强调真实体验
- 数字具体化("用了 3 天"比"用了几天"好)
Title Patterns
- 🔥 + 痛点/好奇心:"后悔没早知道的 XX 技巧"
- 数字列表:"5 个让你 XX 的方法"
- 对比反差:"从 XX 到 XX,我只做了这一件事"
- 身份共鸣:"打工人必看!XX"
Hashtag Strategy
- 2-3 个大流量标签(#好物分享 #生活方式)
- 2-3 个精准标签(与内容强相关)
- 1-2 个长尾标签(竞争小、精准)
Structure Template
[emoji] [吸引力标题]
[开头:痛点/共鸣/悬念,1-2 句]
[正文:分点阐述,每点 emoji 开头]
[emoji] 要点一...
[emoji] 要点二...
[emoji] 要点三...
[总结:一句话收尾]
#标签1 #标签2 #标签3 ...