Agent skill

SEO Autopilot

by kennyzir in kennyzir/7deer_skills

全自动 SEO 内容新鲜度引擎。监听关键词研究报告目录,自动生成落地页和博客文章,运行 SEO 审计后推送更新。适用于任何需要定期更新内容以保持 Google 排名新鲜度的网站项目。支持 Next.js / Astro / Nuxt 等主流框架。

MITAuto-check passedMarketing & SEO

Install SEO Autopilot

skills CLI
$ npx skills add kennyzir/7deer_skills --skill seo-autopilot -a claude-code

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

GitHub CLI
$ gh skill install kennyzir/7deer_skills seo-autopilot --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/kennyzir/7deer_skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/seo-autopilot .claude/skills/seo-autopilot && 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
seo-autopilot
GitHub stars
322
Token cost
~1.6k tokens
SKILL.md length
388 words
Files
3 (incl. references)
Skills in repo
33
Repo updated
First seen
Licence
MIT

At a glance

全自动 SEO 内容新鲜度引擎。监听关键词研究报告目录,自动生成落地页和博客文章,运行 SEO 审计后推送更新。适用于任何需要定期更新内容以保持 Google 排名新鲜度的网站项目。支持 Next.js / Astro / Nuxt 等主流框架。

  • Works in 12 steps: 发现项目结构 → 配置 Git 自动拉取 → 创建 fileCreated Hook → …
  • Tasks that involve Static sites and blogs
  • SKILL.md covers 核心价值, 完整自动化链路, 使用场景 and 前置依赖, plus 9 more sections
  • Calls git

What it does

SEO Autopilot is an agent skill from kennyzir/7deer_skills. 全自动 SEO 内容新鲜度引擎。监听关键词研究报告目录,自动生成落地页和博客文章,运行 SEO 审计后推送更新。适用于任何需要定期更新内容以保持 Google 排名新鲜度的网站项目。支持 Next.js / Astro / Nuxt 等主流框架。

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including reference files (for example `references/setup-checklist.md` and `references/steering-template.md`).

It sits in Marketing & SEO, covering Static sites and blogs. It works with Astro, Next.js, Nuxt and Git. The repository describes itself as: Composable, auditable Agent Skills for building Roblox game sites—from opportunity and keyword research to content, SEO, updates, and backlinks. The licence is MIT.

When your agent uses it

  • Tasks that involve Static sites and blogs

Example prompts

  • “/seo-autopilot”

Workflow steps

12 steps, taken from the step headings in SKILL.md.

  1. 发现项目结构
  2. 配置 Git 自动拉取
  3. 创建 fileCreated Hook
  4. 创建 Steering 文件
  5. 初始化状态追踪
  6. 验证
  7. 测试运行
  8. 发现新报告
  9. 解析报告
  10. 去重
  11. 页面类型决策
  12. 内容生成

What it can do on your machine

Read from SKILL.md and the folder at commit 32a6881. 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

    Shell commands in SKILL.md call:

    • git

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

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    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

SEO Autopilot loads about 1.6k tokens when it runs, and up to ~2.6k if it reads all its reference files. Until then it costs about 34 tokens; SKILL.md has 388 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~34
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.6k

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 kennyzir/7deer_skills at commit 32a6881, republished under its MIT licence (© kennyzir). 388 words, ~1,580 tokens.

Download SKILL.mdSave it as .claude/skills/seo-autopilot/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
seo-autopilot
description
全自动 SEO 内容新鲜度引擎。监听关键词研究报告目录,自动生成落地页和博客文章,运行 SEO 审计后推送更新。适用于任何需要定期更新内容以保持 Google 排名新鲜度的网站项目。支持 Next.js / Astro / Nuxt 等主流框架。
metadata.keywords
seo automation, keyword report, content freshness, landing page generation, blog generation, google rankings, automated deployment, git autopull

SEO Autopilot — 全自动内容新鲜度引擎

把关键词研究报告变成已部署的 SEO 页面,零人工干预。

核心价值

当你有一个外部 Agent(如 OpenClaw)定期生成关键词研究报告并推送到 Git 仓库时,这个 skill 会:

  1. 自动检测新报告(通过 git autofetch + fileCreated hook)
  2. 自动解析报告中的 Top 关键词和推荐动作
  3. 自动去重(跳过已有页面覆盖的关键词)
  4. 自动决策页面类型(落地页 vs 博客文章)
  5. 自动生成符合项目风格的页面代码
  6. 自动审计(Technical SEO + EEAT 双门检查)
  7. 自动推送(git commit + push → 触发自动部署)

时间节省: 从报告到页面上线,传统方式需要 2-4 小时/页,自动化后 < 5 分钟/页。

完整自动化链路

┌─────────────────────────────────────────┐
│  外部 Agent(OpenClaw 等)              │
│  生成关键词报告 → git push              │
└──────────────┬──────────────────────────┘
               │ (git push to main)
               ▼
┌─────────────────────────────────────────┐
│  IDE(Kiro / Claude Code / Cursor)     │
│  git.autofetch: true (每 2 分钟)        │
│  git.pullOnFetch: true                  │
│  → 自动拉取新 commit                    │
└──────────────┬──────────────────────────┘
               │ (检测到新 .md 文件)
               ▼
┌─────────────────────────────────────────┐
│  fileCreated Hook 触发                  │
│  Pattern: {report_dir}/*.md             │
│  → 启动 Agent 执行流水线                │
└──────────────┬──────────────────────────┘
               │
               ▼
┌─────────────────────────────────────────┐
│  Agent 执行 8 阶段流水线               │
│  解析 → 去重 → 决策 → 生成 → 审计      │
│  → git commit + push                    │
└──────────────┬──────────────────────────┘
               │ (git push to main)
               ▼
┌─────────────────────────────────────────┐
│  自动部署(Vercel / Cloudflare / etc)  │
│  新页面上线生产环境                      │
└─────────────────────────────────────────┘

使用场景

  • 独立站 SEO 内容持续更新(保持 Google 排名新鲜度)
  • 多站点批量内容生产
  • 关键词研究 → 页面上线的全链路自动化
  • 任何需要定期发布新 SEO 内容的项目

前置依赖

依赖说明必须?
Git 仓库GitHub / GitLab / Bitbucket✅
外部关键词报告源定期推送 .md 报告到仓库的 Agent 或脚本✅
Web 框架Next.js / Astro / Nuxt / 静态站✅
自动部署Vercel / Cloudflare Pages / Netlify✅
IDE 保持打开Kiro / Claude Code / Cursor(需要运行 hook)✅

安装方式

bash
# 方式 1: 只复制这个 skill
cp -r 7deer_skills/seo-autopilot .agent/skills/seo-autopilot

# 方式 2: 克隆整个技能库
git clone https://github.com/kennyzir/7deer_skills.git .agent/skills

启动命令

安装后,对 Agent 说:

启动 SEO autopilot,报告目录是 keyword-research/

或英文:

Set up SEO autopilot, report directory is keyword-research/

Agent 会自动执行 7 步 setup 流程。


Setup 流程(Agent 自动执行)

Step 1: 发现项目结构

Agent 需要识别:

  • 框架类型(Next.js / Astro / Nuxt / 静态)
  • 页面系统(如何创建页面)
  • 博客系统(如何存储博客文章)
  • 导航/Sitemap 注册方式
  • 现有 SEO 模式(metadata、JSON-LD、canonical)
  • 关键词报告目录位置
Step 2: 配置 Git 自动拉取

创建或更新 .vscode/settings.json:

json
{
  "git.autofetch": true,
  "git.autofetchPeriod": 120,
  "git.autoStash": true,
  "git.pullOnFetch": true
}

⚠️ 不要覆盖已有设置,只合并这些 key。

Step 3: 创建 fileCreated Hook

创建 Kiro hook 监听报告目录:

json
{
  "name": "SEO Autopilot",
  "version": "1.0.0",
  "when": {
    "type": "fileCreated",
    "patterns": ["{report_dir}/*.md"]
  },
  "then": {
    "type": "askAgent",
    "prompt": "新的关键词研究报告已检测到。按照 #seo-autopilot steering 执行完整流水线:解析报告 → 去重 → 决策页面类型 → 生成页面(最多3个) → 注册 navigation + sitemap → SEO 审计 → git commit and push → 更新 processed.json。"
  }
}
Step 4: 创建 Steering 文件

创建 .kiro/steering/seo-autopilot.md,包含完整的 8 阶段处理指令(见 references/steering-template.md)。

Step 5: 初始化状态追踪

创建 {report_dir}/processed.json:

json
{
  "processed": []
}
Step 6: 验证
  • .vscode/settings.json 已配置 autofetch + pullOnFetch
  • Hook 文件已创建
  • Steering 文件已创建
  • processed.json 已初始化
  • 至少有一份报告可用于测试
Step 7: 测试运行

用现有报告执行一次完整流水线,验证所有环节正常。


8 阶段处理流水线

Phase 0: 发现新报告

读取 processed.json → 扫描报告目录 → 过滤未处理的报告

Phase 1: 解析报告

提取 Top 关键词、搜索意图、竞争度、推荐页面类型

Phase 2: 去重

对比现有页面(navigation + blog),跳过已覆盖的关键词

Phase 3: 页面类型决策
  • Transactional / Emotional → 落地页
  • Informational → 博客文章
  • 每次报告最多生成 3 个页面
Phase 4: 内容生成

按项目现有模式生成页面代码(metadata、JSON-LD、FAQ、内链、CTA)

Phase 5: 注册

添加到 navigation 系统 + sitemap

Phase 6: SEO 审计
  • Title < 60 chars,含主关键词
  • Description < 160 chars
  • Canonical URL
  • JSON-LD WebPage + FAQ schema
  • H1 唯一且含关键词
  • 3-5 个内链
  • CTA 到主转化页面
Show full SKILL.md (147 more words)Show less
Phase 7: 提交推送

git add → commit → push

Phase 8: 更新状态

更新 processed.json,记录已处理报告和生成的页面


关键词报告格式要求

报告为 Markdown 格式,需包含以下内容之一:

  • "Top N 关键词" 或 "推荐动作" 章节,列出关键词和优先级
  • 包含 keyword / intent / competition / action 列的表格

Agent 会自适应解析不同格式的报告。

状态追踪格式

json
{
  "processed": [
    {
      "report": "2026-04-10-keyword-research.md",
      "processedAt": "2026-04-10",
      "pagesCreated": [
        { "type": "landing", "slug": "/personalized-tarot", "keyword": "personalized tarot card generator" }
      ],
      "skipped": [
        { "keyword": "oracle card generator AI", "reason": "Already covered by /ai-oracle-card-generator" }
      ]
    }
  ]
}

适配不同框架

框架页面位置博客位置Sitemap
Next.js (App Router)app/{slug}/page.tsxlib/blog.ts 或 content/blog/*.mdxapp/sitemap.ts
Next.js (Pages Router)pages/{slug}.tsxpages/blog/[slug].tsxnext-sitemap.config.js
Astrosrc/pages/{slug}.astrosrc/content/blog/*.mdastro.config.mjs
Nuxtpages/{slug}.vuecontent/blog/*.mdnuxt.config.ts
静态 HTML{slug}/index.htmlblog/{slug}/index.htmlsitemap.xml

限制与注意事项

  • IDE 必须保持打开: Hook 只在 IDE 运行时生效
  • 每次最多 3 页: 避免内容质量下降
  • 语义去重: 不只是 URL 匹配,还要判断语义重叠
  • 不覆盖已有页面: 只创建新页面,不修改现有内容
  • 需要网络连接: git pull/push 需要网络

常见问题

问题解决方案
Hook 没触发检查 filePatterns 是否匹配报告文件名
自动 pull 不工作重启 IDE,确认 settings.json 已加载
页面风格不匹配更新 steering 文件中的示例页面引用
重复生成页面检查 processed.json 是否正确更新
git push 失败检查 git 凭证 / SSH key 配置
Build 失败确保引用的 mock 数据 / 组件在远端存在

实战案例

CardMuse.com 使用此 skill 实现了:

  • OpenClaw Agent 每 2 天生成关键词报告
  • Kiro 自动拉取 + 处理报告
  • 每次报告生成 2-3 个新 SEO 页面
  • Vercel 自动部署
  • 从报告推送到页面上线 < 5 分钟

License

MIT

© kennyzir, MIT. 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 2 other files (references) in seo-autopilot of kennyzir/7deer_skills.

  • SKILL.md
  • references/setup-checklist.md
  • references/steering-template.md

Open the folder on GitHubat commit 32a6881

Compare with similar skills

SEO Autopilot 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.

SEO Autopilot compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
SEO Autopilot this skillkennyzir/7deer_skills322—~1.6kAutomated safety check: PassMIT
SEO Setupalisamadiii/Portfolio180—~1.7kAutomated safety check: PassNone
Sanity Best Practicesrobotostudio/turbo-start-sanity183—~940Automated safety check: PassMIT
Feature Sliced Designfeature-sliced/skills109—~5.5kAutomated safety check: PassNone
Sanity Best Practicessanity-io/agent-toolkit188—~1.4kAutomated safety check: PassMIT
Edgeone Makers FrameworksTencentEdgeOne/edgeone-makers-tools1.9k—~2.5kAutomated safety check: PassMIT

Similar skills

  • SEO Setup

    alisamadiii/Portfolio

    Full SEO/metadata setup and audit for client websites (Astro, Next.js, any static site).

    180 GitHub stars~1.7k tokensUpdated 4 days ago
    Marketing & SEOAuto-check passed
  • Sanity Best Practices

    robotostudio/turbo-start-sanity

    Sanity development best practices for schema design, GROQ queries, TypeGen, Visual Editing, images, Portable Text, Studio structure, localization, migrations, Sanity Functions, Blueprints, and…

    183 GitHub stars~940 tokensUpdated 6 days ago
    Frontend & DesignAuto-check passed
  • Feature Sliced Design

    feature-sliced/skills

    Official Feature-Sliced Design (FSD) v2.1 skill for applying the methodology to frontend projects.

    109 GitHub stars~5.5k tokensUpdated 4 days ago
    Frontend & DesignAuto-check passed
  • Sanity Best Practices

    sanity-io/agent-toolkit

    Official

    Sanity development best practices for schema design, GROQ queries, TypeGen, Visual Editing, images, Portable Text, Studio structure, localization, migrations, Sanity Functions, webhooks, Blueprints…

    188 GitHub stars~1.4k tokensUpdated 2 days ago
    Backend & APIsAuto-check passed
  • Edgeone Makers Frameworks

    TencentEdgeOne/edgeone-makers-tools

    Web framework support matrix for EdgeOne Makers — which platform adapter each full-stack framework needs, where it plugs in, the build output directory, the preview asset-prefix option, the 404…

    1.9k GitHub stars~2.5k tokensUpdated 3 days ago
    Frontend & DesignAuto-check passed
  • App Builder

    Undertone0809/rudder

    Create and iteratively improve local web products from natural-language requests, then prepare them to run as Rudder Apps.

    292 GitHub stars~2k tokensUpdated yesterday
    Frontend & DesignAuto-check passed

More from kennyzir/7deer_skills

All 33 skills in this repo
  • Roblox Homepage Ranking Auditor

    kennyzir/7deer_skills

    Audit a Roblox or game-site homepage against the RB Auto Golden Homepage model.

    322 GitHub stars~3.8k tokensUpdated 12 days ago
    Auto-check passed
  • Roblox Site Architect

    kennyzir/7deer_skills

    Orchestrate an evidence-backed seven-stage Roblox site growth pipeline from opportunity assessment through keyword research, source collection, site planning, SEO QA, freshness, and growth.

    322 GitHub stars~3.6k tokensUpdated 12 days ago
    Auto-check passed
  • Youtube Transcribe

    kennyzir/7deer_skills

    YouTube video transcription and memory workflow. An agent skill from kennyzir/7deer_skills.

    322 GitHub stars~1.7k tokensUpdated 12 days ago
    Auto-check passed
  • SEO Link Strategy

    kennyzir/7deer_skills

    Research backlink opportunities, record contact evidence, and generate personalized local outreach drafts from user-provided product and contact data.

    322 GitHub stars~1.4k tokensUpdated 12 days ago
    Auto-check passed
  • Html5 Game Radar

    kennyzir/7deer_skills

    HTML5 游戏发现雷达 - 多源监测又新又热的 HTML5 游戏,识别 SEO 套利窗口. An agent skill from kennyzir/7deer_skills.

    322 GitHub stars~1.4k tokensUpdated 12 days ago
    Auto-check passed
  • Roblox Hit Evaluator

    kennyzir/7deer_skills

    Evaluate a Roblox game's 30-day breakout potential from public evidence with auditable scores, missing-data bounds, frozen forecasts, and outcome reviews.

    322 GitHub stars~1.3k tokensUpdated 12 days ago
    Auto-check passed

Questions about SEO Autopilot

What does SEO Autopilot do?

全自动 SEO 内容新鲜度引擎。监听关键词研究报告目录,自动生成落地页和博客文章,运行 SEO 审计后推送更新。适用于任何需要定期更新内容以保持 Google 排名新鲜度的网站项目。支持 Next.js / Astro / Nuxt 等主流框架。. SEO Autopilot is an agent skill from kennyzir/7deer_skills.

When should I use SEO Autopilot?

SEO Autopilot fits situations like: tasks that involve Static sites and blogs.

How do I install SEO Autopilot in Claude Code?

Run `npx skills add kennyzir/7deer_skills --skill seo-autopilot -a claude-code`. Or copy the skill folder (seo-autopilot in kennyzir/7deer_skills) into .claude/skills/seo-autopilot in your project. Claude Code loads it when a task matches its description.

How do I install SEO Autopilot in Codex?

Run `npx skills add kennyzir/7deer_skills --skill seo-autopilot -a codex`. Or copy the skill folder (seo-autopilot in kennyzir/7deer_skills) into .agents/skills/seo-autopilot in your project. Codex loads it when a task matches its description.

Can I use SEO Autopilot 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 kennyzir/7deer_skills --skill seo-autopilot -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/seo-autopilot, .gemini/skills/seo-autopilot, .github/skills/seo-autopilot and .opencode/skills/seo-autopilot in your project.

What does SEO Autopilot need to run?

Going by SKILL.md and its folder, SEO Autopilot needs the command-line tools its instructions call (git).

Does SEO Autopilot access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is SEO Autopilot 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 SEO Autopilot use?

SEO Autopilot is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does SEO Autopilot use?

About 1.6k tokens (SKILL.md is roughly 6.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 971 tokens, read only when the agent opens those files.

What are the alternatives to SEO Autopilot?

Skills that share tags, products or a category with SEO Autopilot: SEO Setup (alisamadiii/Portfolio, 180 stars), Sanity Best Practices (robotostudio/turbo-start-sanity, 183 stars), Feature Sliced Design (feature-sliced/skills, 109 stars) and Sanity Best Practices (sanity-io/agent-toolkit, 188 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains SEO Autopilot?

kennyzir (a GitHub user) maintains it in kennyzir/7deer_skills, which has 322 GitHub stars. The repository holds 33 skills in this directory. The repository was last updated on September 29, 2026.

Source: kennyzir/7deer_skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.