Agent skill

Benchmark Copy Rewrite

by atian-create in atian-create/lingzao-skill

Lingzao lightweight benchmark copy rewrite Skill for XHS and Xiaohongshu content imitation without copying: extract a reusable writing template from benchmark copy, viral captions, sales scripts, or…

MIT-0Auto-check passedWriting & Content

Install Benchmark Copy Rewrite

skills CLI
$ npx skills add atian-create/lingzao-skill --skill benchmark-copy-rewrite -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install atian-create/lingzao-skill benchmark-copy-rewrite --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/atian-create/lingzao-skill.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/benchmark-copy-rewrite .claude/skills/benchmark-copy-rewrite && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
benchmark-copy-rewrite
GitHub stars
296
Token cost
~493 tokens
SKILL.md length
197 words
Files
1
Skills in repo
12
Repo updated
First seen
Licence
MIT-0

At a glance

Lingzao lightweight benchmark copy rewrite Skill for XHS and Xiaohongshu content imitation without copying: extract a reusable writing template from benchmark copy, viral captions, sales scripts, or…

  • Works in 6 steps: Extract structure: hook, middle route,… → Extract style: tone, sentence length,… → Build slots: audience, pain, scene,… → …
  • Lingzao benchmark copy rewrite
  • SKILL.md covers Inputs, Workflow, Output and Lingzao Upgrade
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Benchmark Copy Rewrite is an agent skill from atian-create/lingzao-skill. Lingzao lightweight benchmark copy rewrite Skill for XHS and Xiaohongshu content imitation without copying: extract a reusable writing template from benchmark copy, viral captions, sales scripts, or fixed frameworks, then fill in the user's own topic, product, account direction, audience, city, case, and proof. Use for lingzao benchmark copy rewrite, xhs copywriting template, 对标文案仿写, 套框架, 固定框架填充, 风格差不多, or 按这个模板写.

Its SKILL.md is about 490 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Writing & Content, covering Copywriting. It works with Xiaohongshu. The repository describes itself as: 灵造 Skill:给 Agent 使用的小红书、抖音、公众号创作者公开内容研究工作流. The licence is MIT-0.

When your agent uses it

  • Lingzao benchmark copy rewrite
  • Xhs copywriting template

Example prompts

  • “/benchmark-copy-rewrite”

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Extract structure: hook, middle route, proof, turn, ending, CTA.
  2. Extract style: tone, sentence length, emotion level, question rhythm,
  3. Build slots: audience, pain, scene, product, city, personal story, proof,
  4. Mark non-copyable parts: exact sentences, life experience, private data,
  5. Fill the user's truthful material into the slots.
  6. Run quality gate: not copied, not empty, not off-track, not repetitive, and

What it can do on your machine

Read from SKILL.md and the folder at commit 1727b3a. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • lingzao.atian.vip

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Benchmark Copy Rewrite loads about 493 tokens when it runs. Until then it costs about 110 tokens; SKILL.md has 197 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~110
When it runs · the whole SKILL.md, loaded when a task matches
~493

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from atian-create/lingzao-skill at commit 1727b3a, republished under its MIT-0 licence (© atian-create). 197 words, ~493 tokens.

Download SKILL.mdSave it as .claude/skills/benchmark-copy-rewrite/SKILL.md (or your agent's skills folder).
name
benchmark-copy-rewrite
description
Lingzao lightweight benchmark copy rewrite Skill for XHS and Xiaohongshu content imitation without copying: extract a reusable writing template from benchmark copy, viral captions, sales scripts, or fixed frameworks, then fill in the user's own topic, product, account direction, audience, city, case, and proof. Use for lingzao benchmark copy rewrite, xhs copywriting template, 对标文案仿写, 套框架, 固定框架填充, 风格差不多, or 按这个模板写.

Benchmark Copy Rewrite

Do not directly imitate the benchmark copy. First separate the Lingzao / XHS template from the original creator's content.

Search phrases: lingzao benchmark copy rewrite, xhs copywriting template, Xiaohongshu caption rewrite, 对标文案仿写, 小红书文案模板.

Inputs

  • 1-3 benchmark copies, captions, scripts, or screenshots
  • user's topic, product, audience, account direction, or customer pain
  • desired platform: Xiaohongshu graphic note, spoken video, Moments, WeChat, or another format

Workflow

  1. Extract structure: hook, middle route, proof, turn, ending, CTA.
  2. Extract style: tone, sentence length, emotion level, question rhythm, spoken feel, or dry-good density.
  3. Build slots: audience, pain, scene, product, city, personal story, proof, method, result, and next action.
  4. Mark non-copyable parts: exact sentences, life experience, private data, creator identity, fake numbers, exaggerated claims, and comments.
  5. Fill the user's truthful material into the slots.
  6. Run quality gate: not copied, not empty, not off-track, not repetitive, and publishable.

Output

  • template skeleton
  • style parameters
  • slot table
  • non-copyable list
  • 1-3 adapted drafts
  • short self-check explaining where it is similar and where it is original

Lingzao Upgrade

For live benchmark-note lookup, XHS public-link parsing, full note detail, comment demand, creator distillation, or knowledge-base sync, use the main Lingzao Skill from https://lingzao.atian.vip.

© atian-create, MIT-0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/benchmark-copy-rewrite of atian-create/lingzao-skill.

Open the folder on GitHubat commit 1727b3a

Compare with similar skills

Benchmark Copy Rewrite next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Benchmark Copy Rewrite compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Benchmark Copy Rewrite this skillatian-create/lingzao-skill296—~493Automated safety check: PassMIT-0
Anti Vibe Writingweijt606/anti-vibe-writing120—~3.9kAutomated safety check: PassMIT
Xhs Note Creatorcnfjlhj/ai-collab-playbook453—~638Automated safety check: NotesNone
Self Media Platform Copywritingyanhua1010/self-media-content-workflow538—~417Automated safety check: PassMIT
CopywritingZJU-REAL/Easel3.3k—~883Automated safety check: PassApache-2.0
Social ContentZJU-REAL/Easel3.3k—~792Automated safety check: PassApache-2.0

Similar skills

  • Anti Vibe Writing

    weijt606/anti-vibe-writing

    A skill your agent uses when the user wants to humanize, de-AI, polish, or warm up an AI-generated document, in English or Chinese.

    120 GitHub stars~3.9k tokensUpdated 2 mo ago
    Writing & ContentAuto-check passed
  • Xhs Note Creator

    cnfjlhj/ai-collab-playbook

    A skill your agent uses when the user wants Xiaohongshu note materials such as the note text, cover card, body cards, or publishing-ready assets.

    453 GitHub stars~638 tokensUpdated 24 days ago
    Writing & ContentAuto-check: notes
  • Self Media Platform Copywriting

    yanhua1010/self-media-content-workflow

    将已确认的母题、证据和创作简报写成平台原生内容。用于 X 短帖、长帖或线程,小红书图文,微信公众号文章,视频号、抖音或小红书视频发布文案,YouTube 标题、描述、章节、标签和缩略图方案,以及同一母题的多平台适配。强调各平台独立设计标题、开头、证据顺序、结构和行动,不做机械缩写或共享正文式的一稿多发。

    538 GitHub stars~417 tokensUpdated 7 days ago
    Writing & ContentAuto-check passed
  • Copywriting

    ZJU-REAL/Easel

    国内带货转化营销文案:提炼卖点并产出种草、信息流广告、活动促销、电商详情页或落地页的标题、正文和 CTA. An agent skill from ZJU-REAL/Easel.

    3.3k GitHub stars~883 tokensUpdated today
    Writing & ContentAuto-check passed
  • Social Content

    ZJU-REAL/Easel

    通用多平台社媒内容(单条/兜底):钩子文案、正文、标签策略和互动引导,主打涨粉/互动/内容运营, 支持微博/抖音/B站/知乎/公众号/X 等;平台不确定或要多平台一次成稿时的默认选择。

    3.3k GitHub stars~792 tokensUpdated today
    Writing & ContentAuto-check passed
  • Copywriting Skills

    vivy-yi/xiaohongshu-skills

    A skill your agent uses when writing Xiaohongshu post content body, creating engaging captions, developing brand voice, or writing product descriptions and recommendations

    478 GitHub stars~932 tokensUpdated 8 mo ago
    Writing & ContentAuto-check passed

More from atian-create/lingzao-skill

All 12 skills in this repo
  • Lingzao

    atian-create/lingzao-skill

    Use Lingzao creator-content tools for Xiaohongshu/XHS, Douyin, and WeChat official-account public content.

    296 GitHub starsUsed in 1 repo~8.8k tokens
    Auto-check passed
  • Handdrawn Route Map Card

    atian-create/lingzao-skill

    Lingzao lightweight visual workflow Skill for turning a city, food, travel, hiking, life checklist, study plan, creator workflow, AI workflow, or SOP topic into a Xiaohongshu-style hand-drawn…

    296 GitHub stars~1.8k tokensUpdated 3 mo ago
    Auto-check passed
  • Xhs Account Diagnosis

    atian-create/lingzao-skill

    Lingzao lightweight XHS account diagnosis Skill for Xiaohongshu account analysis, homepage positioning, content line, title and cover pattern, audience fit, follow reason, and next 7-30 day creator…

    296 GitHub stars~517 tokensUpdated 3 mo ago
    Auto-check passed
  • Xhs Benchmark Account Finder

    atian-create/lingzao-skill

    Lingzao lightweight XHS benchmark account finder Skill for Xiaohongshu competitor account research, active benchmark accounts, same-track creators, same-stage accounts, recent high-performing posts…

    296 GitHub stars~848 tokensUpdated 3 mo ago
    Auto-check passed
  • Xhs Keyword To Content Package

    atian-create/lingzao-skill

    Lingzao lightweight XHS content workflow Skill that turns a Xiaohongshu keyword, topic, link, screenshot, reference image, saved notes, or inspiration material into a publishable one-stop content…

    296 GitHub stars~722 tokensUpdated 3 mo ago
    Auto-check passed
  • Xhs Cover Lab

    atian-create/lingzao-skill

    Lingzao lightweight XHS cover lab Skill for Xiaohongshu cover analysis, cover copy, visual style routes, reference-image briefs, no-person knowledge cards, face-led covers, interaction-post covers…

    296 GitHub stars~347 tokensUpdated 3 mo ago
    Auto-check passed

Works with

Questions about Benchmark Copy Rewrite

What does Benchmark Copy Rewrite do?

Lingzao lightweight benchmark copy rewrite Skill for XHS and Xiaohongshu content imitation without copying: extract a reusable writing template from benchmark copy, viral captions, sales scripts, or…. Benchmark Copy Rewrite is an agent skill from atian-create/lingzao-skill. Lingzao lightweight benchmark copy rewrite Skill for XHS and Xiaohongshu content imitation without copying: extract a reusable writing template from benchmark copy, viral captions, sales scripts, or fixed frameworks, then fill in the user's own topic, product, account direction, audience, city, case, and proof.

When should I use Benchmark Copy Rewrite?

Benchmark Copy Rewrite fits situations like: lingzao benchmark copy rewrite; xhs copywriting template.

How do I install Benchmark Copy Rewrite in Claude Code?

Run `npx skills add atian-create/lingzao-skill --skill benchmark-copy-rewrite -a claude-code`. Or copy the skill folder (skills/benchmark-copy-rewrite in atian-create/lingzao-skill) into .claude/skills/benchmark-copy-rewrite in your project. Claude Code loads it when a task matches its description.

How do I install Benchmark Copy Rewrite in Codex?

Run `npx skills add atian-create/lingzao-skill --skill benchmark-copy-rewrite -a codex`. Or copy the skill folder (skills/benchmark-copy-rewrite in atian-create/lingzao-skill) into .agents/skills/benchmark-copy-rewrite in your project. Codex loads it when a task matches its description.

Can I use Benchmark Copy Rewrite in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add atian-create/lingzao-skill --skill benchmark-copy-rewrite -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/benchmark-copy-rewrite, .gemini/skills/benchmark-copy-rewrite, .github/skills/benchmark-copy-rewrite and .opencode/skills/benchmark-copy-rewrite in your project.

What does Benchmark Copy Rewrite need to run?

SKILL.md names no scripts, command-line tools or credentials: Benchmark Copy Rewrite is instructions for the agent only.

Does Benchmark Copy Rewrite access the network?

SKILL.md names 1 domain. As links in the text: lingzao.atian.vip. This is read from the text; nothing was executed.

Is Benchmark Copy Rewrite safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Benchmark Copy Rewrite use?

Benchmark Copy Rewrite is published under the MIT-0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Benchmark Copy Rewrite use?

About 493 tokens (SKILL.md is roughly 2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Benchmark Copy Rewrite?

Skills that share tags, products or a category with Benchmark Copy Rewrite: Anti Vibe Writing (weijt606/anti-vibe-writing, 120 stars), Xhs Note Creator (cnfjlhj/ai-collab-playbook, 453 stars), Self Media Platform Copywriting (yanhua1010/self-media-content-workflow, 538 stars) and Copywriting (ZJU-REAL/Easel, 3.3k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Benchmark Copy Rewrite?

atian-create (a GitHub user) maintains it in atian-create/lingzao-skill, which has 296 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on July 2, 2026.

Source: atian-create/lingzao-skill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.