Agent skill

Review SEO Page

by tsingyuai in tsingyuai/growth-lab

从目标用户的真实搜索场景出发,对抗式审查并修改 SEO 页面,找出搜索意图偏离、低信息量、批量同构、重复转化、AI 腔、术语漂移、无依据主张、metadata 问题和配图场景错位。需要审查 SEO 内容价值、降低 AI 味、检查图片相关性或决定页面保留、合并、重写、删除时使用。

Apache-2.0Auto-check passed

Install Review SEO Page

skills CLI
$ npx skills add tsingyuai/growth-lab --skill review-seo-page -a claude-code

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

GitHub CLI
$ gh skill install tsingyuai/growth-lab review-seo-page --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/tsingyuai/growth-lab.git skills-src && mkdir -p .claude/skills && cp -r skills-src/executors/review-seo-page .claude/skills/review-seo-page && 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
review-seo-page
GitHub stars
2k
Token cost
~396 tokens
SKILL.md length
70 words
Files
2
Skills in repo
22
Repo updated
First seen
Licence
Apache-2.0

At a glance

从目标用户的真实搜索场景出发,对抗式审查并修改 SEO 页面,找出搜索意图偏离、低信息量、批量同构、重复转化、AI 腔、术语漂移、无依据主张、metadata 问题和配图场景错位。需要审查 SEO 内容价值、降低 AI 味、检查图片相关性或决定页面保留、合并、重写、删除时使用。

  • Works in 6 steps: 写出它对用户任务的具体贡献。 → 删除用户大概率不需要的内容。 → 检查是否增加方法、标准、示例、事实、工具或决策。 → …
  • SKILL.md covers 建立用户任务, 自上而下审阅, 对抗测试 and Metadata, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Review SEO Page is an agent skill from tsingyuai/growth-lab. 从目标用户的真实搜索场景出发,对抗式审查并修改 SEO 页面,找出搜索意图偏离、低信息量、批量同构、重复转化、AI 腔、术语漂移、无依据主张、metadata 问题和配图场景错位。需要审查 SEO 内容价值、降低 AI 味、检查图片相关性或决定页面保留、合并、重写、删除时使用。

Its SKILL.md is about 400 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

The repository describes itself as: An end-to-end growth tool that understands the product, fetch the data it needs, researches the market, executes campaigns, and reviews results to improve the next round of… The licence is Apache-2.0.

Example prompts

  • “/review-seo-page”

Workflow steps

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

  1. 写出它对用户任务的具体贡献。
  2. 删除用户大概率不需要的内容。
  3. 检查是否增加方法、标准、示例、事实、工具或决策。
  4. 检查换成相邻页面标题后是否仍能原样成立。
  5. 检查事实来源、术语、图片相关性和转化压力。
  6. 检查布局、链接、移动端、无障碍、控制台和失败请求。

What it can do on your machine

Read from SKILL.md and the folder at commit 2d0807c. 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

    No URLs in SKILL.md.

    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

Review SEO Page loads about 396 tokens when it runs. Until then it costs about 39 tokens; SKILL.md has 70 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~39
When it runs · the whole SKILL.md, loaded when a task matches
~396

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 tsingyuai/growth-lab at commit 2d0807c, republished under its Apache-2.0 licence (© tsingyuai). 70 words, ~396 tokens.

Download SKILL.mdSave it as .claude/skills/review-seo-page/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
review-seo-page
description
从目标用户的真实搜索场景出发,对抗式审查并修改 SEO 页面,找出搜索意图偏离、低信息量、批量同构、重复转化、AI 腔、术语漂移、无依据主张、metadata 问题和配图场景错位。需要审查 SEO 内容价值、降低 AI 味、检查图片相关性或决定页面保留、合并、重写、删除时使用。

SEO 页面对抗式审阅

先假定每个区块都需要删除。只有直接帮助目标用户理解、判断或行动的内容才保留。使用 Runtime 的真实浏览器检查实际渲染结果,不能只读源代码。

建立用户任务

先写清:

  • 目标用户;
  • 搜索词和搜索意图;
  • 用户进入页面时的问题;
  • 用户离开前应获得的结果;
  • 与该结果直接相关的产品动作。

搜索意图错配是最高严重程度的问题。

自上而下审阅

对每个可见区块:

  1. 写出它对用户任务的具体贡献。
  2. 删除用户大概率不需要的内容。
  3. 检查是否增加方法、标准、示例、事实、工具或决策。
  4. 检查换成相邻页面标题后是否仍能原样成立。
  5. 检查事实来源、术语、图片相关性和转化压力。
  6. 检查布局、链接、移动端、无障碍、控制台和失败请求。

对抗测试

  • 删除测试:删除后用户没有损失,直接删除。
  • 反转测试:一句话的反面显然没人支持,原句没有信息量。
  • 换标题测试:内容能原样放进多个相邻页面,说明缺少页面独有信息。
  • 去品牌测试:去掉品牌名后只剩宣传态度,删除或改成具体信息。
  • 证据测试:非显而易见的事实和数字没有来源,删除或补充一手来源。
  • 图文测试:图片不能直接说明相邻文案中的任务或结果,替换或删除。
  • 转化测试:合并重复 CTA,保留与搜索任务一致的行动。

现实中的商业产品、课程、社区内容、开源项目和经验做法都可以保留。是否有源码不是参考标准;判断标准是目标用户是否关心,以及它与当前产品的差异会怎样改变内容调性和转化方式。

Metadata

  • Title 准确说明页面主题与意图。
  • Description 不写成全页目录,删除“本文介绍、页面涵盖、包含、并给出”等概括式开头。
  • 不为了接近固定字符数罗列页面区块、关键词或功能。
  • 选择一个信息量高的重点,用自然完整的句子讲清。
  • 核对 canonical、社交 metadata、结构化数据和 sitemap 与渲染页面一致。

语言与风格

  • 使用短句,一句话只表达一个意思。
  • 直接写定义和动作,不用例子代替定义。
  • 使用领域常用术语,同一概念只保留一个名称。
  • 删除比喻、拟人、设问式引入、悬念式开头、生造术语、空泛过渡、排比填充和同义重复。
  • 直接写肯定定义,避免“不是……而是……”句式。
  • 效果主张必须有对象、条件和具体含义。
  • 用户正文中不出现内部实现名、内部编号和工作流黑话。
  • 收到术语纠正时,全文直接采用新术语,不保留旧方案和修改过程。

防御性表达

正文不要加入“做不到什么、目前只实现什么、只是 demo、结果不意味着什么”等防御性表达。一个主张没有足够证据时,删除整个主张,不保留一部分再补充局限说明。不要为了披露而引入用户没有搜索的问题。

输出与修复

按严重程度分类:

  • P0:搜索意图或用户任务错配。
  • P1:低价值、重复、同构、无依据、过度转化或图片错位。
  • P2:拗口、AI 腔、术语漂移、metadata 或呈现问题。

每项写明页面位置、最短识别原文、用户为什么不关心、处理动作和可直接替换的文本。最后给出页面结论:保留、合并、重写或删除。

获得编辑授权后直接实施修改,重新运行产品检查,并再次检查渲染页面。

© tsingyuai, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in executors/review-seo-page of tsingyuai/growth-lab.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit 2d0807c

More from tsingyuai/growth-lab

All 22 skills in this repo
  • Screenshot Assets

    tsingyuai/growth-lab

    Capture authenticated product screenshots through the repository-owned Playwright CDP script and archive them in the invoking loop's Memory.

    2k GitHub stars~583 tokensUpdated 12 days ago
    Auto-check passed
  • Media Crawler

    tsingyuai/growth-lab

    Install, authenticate, configure, operate, and troubleshoot the external MediaCrawler client shared by Douyin, Kuaishou, Bilibili, Weibo, Tieba, and Zhihu collectors.

    2k GitHub stars~731 tokensUpdated 12 days ago
    Auto-check passed
  • Run SEO Page Loop

    tsingyuai/growth-lab

    Run an SEO page observation-action-review loop with persistent Memory by coordinating demand research, page creation, adversarial review, image generation, IndexNow submission, and performance review.

    2k GitHub stars~1.2k tokensUpdated 12 days ago
    Auto-check passed
  • Wechat Article Compose

    tsingyuai/growth-lab

    把一个已确认的选题写成微信公众号长文。锁定复刻锚与用户价值、写出 article.md / wechat.yml / review.md,并通过公众号通用合规检查和人工预览前自检。准备、改写或核验公众号文章时使用;不负责发布,也不产出小红书卡片。

    2k GitHub stars~860 tokensUpdated 12 days ago
    Auto-check passed
  • Wechat Mp Publish

    tsingyuai/growth-lab

    通过微信公众号官方 API 把公众号文章生产单元渲染为微信排版 HTML、生成阅读页预览、上传封面与正文图片并创建草稿;在三重确认下提交发布并查询状态。支持本机直连与固定 IP 远程发布服务两种模式。用户要求预览公众号、同步微信草稿、发布公众号或查询发布状态时使用。

    2k GitHub stars~797 tokensUpdated 12 days ago
    Auto-check: notes
  • Xhs Render Cards

    tsingyuai/growth-lab

    把已批准的小红书草稿、单一分析参考和真实产品素材变成可审查卡片:先完成 DAI 与 image plan,再按确定性、完整效果或可分离图层模式制作,机械验证 PNG 与清单并运行合规检查。精确文字和真实 UI 不交给模型猜测;AI 生图需要单独配置和授权。

    2k GitHub stars~1k tokensUpdated 12 days ago
    Auto-check passed

Questions about Review SEO Page

What does Review SEO Page do?

从目标用户的真实搜索场景出发,对抗式审查并修改 SEO 页面,找出搜索意图偏离、低信息量、批量同构、重复转化、AI 腔、术语漂移、无依据主张、metadata 问题和配图场景错位。需要审查 SEO 内容价值、降低 AI 味、检查图片相关性或决定页面保留、合并、重写、删除时使用。. Review SEO Page is an agent skill from tsingyuai/growth-lab.

How do I install Review SEO Page in Claude Code?

Run `npx skills add tsingyuai/growth-lab --skill review-seo-page -a claude-code`. Or copy the skill folder (executors/review-seo-page in tsingyuai/growth-lab) into .claude/skills/review-seo-page in your project. Claude Code loads it when a task matches its description.

How do I install Review SEO Page in Codex?

Run `npx skills add tsingyuai/growth-lab --skill review-seo-page -a codex`. Or copy the skill folder (executors/review-seo-page in tsingyuai/growth-lab) into .agents/skills/review-seo-page in your project. Codex loads it when a task matches its description.

Can I use Review SEO Page 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 tsingyuai/growth-lab --skill review-seo-page -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/review-seo-page, .gemini/skills/review-seo-page, .github/skills/review-seo-page and .opencode/skills/review-seo-page in your project.

What does Review SEO Page need to run?

SKILL.md names no scripts, command-line tools or credentials: Review SEO Page is instructions for the agent only.

Does Review SEO Page access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Review SEO Page 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 Review SEO Page use?

Review SEO Page is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Review SEO Page use?

About 396 tokens (SKILL.md is roughly 1.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

Who maintains Review SEO Page?

tsingyuai (a GitHub organization) maintains it in tsingyuai/growth-lab, which has 2,000 GitHub stars. The repository holds 22 skills in this directory. The repository was last updated on September 28, 2026.

Source: tsingyuai/growth-lab on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.