Agent skill

Auto Page Sync

by kennyzir in kennyzir/7deer_skills

仓库 Markdown/JSON 内容自动同步到前端页面,配置 GitHub Actions 定时拉取 + 部署,保持 Google SEO 内容新鲜度。支持日报、博客、Changelog、Landing Page 等多种页面模式。

MITAuto-check passedDevOps & Cloud

Install Auto Page Sync

skills CLI
$ npx skills add kennyzir/7deer_skills --skill auto-page-sync -a claude-code

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

GitHub CLI
$ gh skill install kennyzir/7deer_skills auto-page-sync --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/auto-page-sync .claude/skills/auto-page-sync && 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
auto-page-sync
GitHub stars
322
Token cost
~1.7k tokens
SKILL.md length
300 words
Files
4
Skills in repo
33
Repo updated
First seen
Licence
MIT

At a glance

仓库 Markdown/JSON 内容自动同步到前端页面,配置 GitHub Actions 定时拉取 + 部署,保持 Google SEO 内容新鲜度。支持日报、博客、Changelog、Landing Page 等多种页面模式。

  • Works in 7 steps: 分析内容源 → 选择页面模式 → 创建静态数据管道 → …
  • Tasks that involve CI/CD
  • SKILL.md covers When This Skill Applies, 核心价值, Instructions and Actions, plus 4 more sections
  • Runs Python scripts from its folder

What it does

Auto Page Sync is an agent skill from kennyzir/7deer_skills. 仓库 Markdown/JSON 内容自动同步到前端页面,配置 GitHub Actions 定时拉取 + 部署,保持 Google SEO 内容新鲜度。支持日报、博客、Changelog、Landing Page 等多种页面模式。

Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files (for example `resources/rebuild_index.py`, `resources/report_types_example.json` and `resources/sync_workflow_template.yml`).

It sits in DevOps & Cloud, covering CI/CD, Landing pages and Changelog and release notes. It works with GitHub Actions. 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 CI/CD
  • Tasks that involve Landing pages
  • Tasks that involve Changelog and release notes

Example prompts

  • “/auto-page-sync”

Requirements

  • Python 3

Workflow steps

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

  1. 分析内容源
  2. 选择页面模式
  3. 创建静态数据管道
  4. 生成前端页面
  5. 添加导航入口
  6. 配置 GitHub Actions 定时同步
  7. SEO 优化(推荐)

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

    Ships script files (Python), which the agent can run.

    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

Auto Page Sync loads about 1.7k tokens when it runs. Until then it costs about 33 tokens; SKILL.md has 300 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~33
When it runs · the whole SKILL.md, loaded when a task matches
~1.7k

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). 300 words, ~1,659 tokens.

Download SKILL.mdSave it as .claude/skills/auto-page-sync/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
auto-page-sync
description
仓库 Markdown/JSON 内容自动同步到前端页面,配置 GitHub Actions 定时拉取 + 部署,保持 Google SEO 内容新鲜度。支持日报、博客、Changelog、Landing Page 等多种页面模式。
metadata.keywords
auto sync, github actions, cron, markdown, blog, report, landing page, seo freshness, sitemap, content pipeline, static site
metadata.version
1.0

Auto Page Sync — 仓库内容自动同步到前端页面

将仓库中的 Markdown / JSON 内容自动同步到前端项目,生成对应页面,并通过 GitHub Actions 定时更新,确保 Google SEO 内容新鲜度。

When This Skill Applies

  • 当用户说「把仓库的 XX 目录同步到网站」时
  • 当用户说「每天自动更新页面内容」时
  • 当用户需要把 Markdown 报告、博客文章、Changelog 展示到前端时
  • 当用户提到「SEO 内容新鲜度」「定时更新」「自动部署」时
  • 当用户需要配置 GitHub Actions 定时同步内容到前端时

核心价值

手动更新网站内容既耗时又容易遗忘。这个 Skill 让你:

  • 只管往仓库写 Markdown,前端页面自动生成
  • GitHub Actions 定时拉取,零人工干预
  • 每次更新自动触发部署,Google 爬虫看到的永远是最新内容
  • 支持多种页面形态,一套机制复用所有项目

Instructions

Step 1: 分析内容源
  1. 读取用户指定的仓库目录结构
  2. 识别内容格式(Markdown、JSON、YAML)
  3. 分析内容组织方式(按日期、按分类、单文件)
  4. 确定元数据提取规则(标题、日期、标签等)
bash
# 典型的内容源结构
daily-reports/
├── 2026-04-10/
│   ├── morning-report.md
│   └── youtube-report.md
├── 2026-04-11/
│   ├── morning-report.md
│   └── youtube-report.md

# 或者博客结构
blog/
├── 2026-04-10-my-first-post.md
├── 2026-04-11-another-post.md
Step 2: 选择页面模式

根据内容类型选择合适的模式:

模式适用场景路由结构特点
A: 日报型每日报告、周报/reports/[date]日期导航 + Tab 切换
B: 博客型文章、教程/blog/[slug]列表页 + 分类筛选
C: 动态区块型Landing Page 数据更新现有页面区块无新路由
D: Changelog 型更新日志/changelog单页时间线
Step 3: 创建静态数据管道

将内容文件复制到前端项目的 public/data/ 目录,并生成索引文件。

目标目录结构:

public/data/{content-type}/
├── index.json          # 索引文件
├── 2026-04-10/
│   ├── report-a.md
│   └── report-b.md
└── 2026-04-11/
    ├── report-a.md
    └── report-b.md

index.json 标准格式:

json
{
  "dates": ["2026-04-11", "2026-04-10"],
  "latest": "2026-04-11",
  "items": {
    "2026-04-11": [
      {
        "slug": "unique-identifier",
        "title": "显示标题",
        "icon": "🎮",
        "filename": "source-file.md",
        "description": "可选摘要",
        "tags": ["可选标签"]
      }
    ]
  }
}
Step 4: 生成前端页面

根据目标框架生成页面代码。以下以 Next.js App Router 为例:

必须遵循的原则:

  • 读取项目现有的 layout.tsx、globals.css、组件库,匹配设计风格
  • 使用项目已安装的依赖(如 react-markdown、remark-gfm)
  • 响应式设计,移动端友好
  • 支持暗色模式(如果项目已有)

日报型页面结构(模式 A):

app/reports/page.tsx              # 重定向到最新日期
app/reports/[date]/page.tsx       # 日期详情页
components/report-viewer.tsx      # 内容渲染组件

博客型页面结构(模式 B):

app/blog/page.tsx                 # 文章列表页
app/blog/[slug]/page.tsx          # 文章详情页
components/blog-card.tsx          # 文章卡片组件

内容渲染组件核心逻辑:

tsx
// 使用 react-markdown + remark-gfm 渲染 Markdown
import ReactMarkdown from "react-markdown"
import remarkGfm from "remark-gfm"

<article className="prose prose-neutral dark:prose-invert max-w-none">
  <ReactMarkdown remarkPlugins={[remarkGfm]}>
    {markdownContent}
  </ReactMarkdown>
</article>
Step 5: 添加导航入口

在项目的全局导航中添加新页面链接,使用与现有导航一致的样式。

Step 6: 配置 GitHub Actions 定时同步

创建 .github/workflows/sync_{content_type}.yml:

yaml
name: Sync {ContentType} to Frontend

on:
  schedule:
    - cron: '{cron_expression}'  # UTC 时间,注意时区转换
  workflow_dispatch:              # 允许手动触发

permissions:
  contents: write

jobs:
  sync:
    runs-on: ubuntu-latest
    steps:
    - uses: actions/checkout@v4
      with:
        fetch-depth: 0

    - name: Sync content files
      run: |
        set -e
        SRC="{source_directory}"
        DST="{frontend_public_data_path}"
        mkdir -p "$DST"
        if [ -d "$SRC" ]; then
          for dir in "$SRC"/*/; do
            name=$(basename "$dir")
            if [[ "$name" =~ ^[0-9]{4}-[0-9]{2}-[0-9]{2}$ ]]; then
              mkdir -p "$DST/$name"
              cp -f "$dir"*.md "$DST/$name/" 2>/dev/null || true
            fi
          done
        fi

    - name: Rebuild index.json
      run: |
        python3 .agent/skills/auto-page-sync/resources/rebuild_index.py \
          --dir "{frontend_public_data_path}"

    - name: Commit and Push
      run: |
        git config --local user.email "github-actions[bot]@users.noreply.github.com"
        git config --local user.name "github-actions[bot]"
        git pull --rebase || true
        git add {target_paths}
        git diff --quiet && git diff --staged --quiet || \
          (git commit -m "🔄 Auto-sync: {content_type} [deploy]" && git push)

Cron 时间计算:

  • 用户说「每天 X 点(北京时间)」→ X - 8 小时 = UTC 时间
  • 内容生成时间 + 1 小时 = 同步时间(确保内容已就绪)
  • 示例:内容 10:00 生成 → 同步 cron 设为 0 3 * * *(UTC 03:00 = 北京 11:00)
Step 7: SEO 优化(推荐)
  1. Sitemap 自动更新 — 在同步脚本中追加新 URL,设置 lastmod 和 changefreq: daily
  2. 页面 Meta 标签 — 从 Markdown 标题提取 <title> 和 <meta description>
  3. 结构化数据 — 博客型用 Article schema,报告型用 Report schema
  4. 内容新鲜度信号 — 页面显示「最后更新时间」,可选生成 RSS Feed

Actions

可用资源文件
  • resources/rebuild_index.py — 通用索引重建脚本,可在 GitHub Actions 或本地运行
  • resources/sync_workflow_template.yml — GitHub Actions workflow 模板,替换占位符即可用
  • resources/report_types_example.json — 报告类型映射示例

完成检查清单

  • 内容文件已复制到 public/data/ 并可通过 URL 访问
  • index.json 正确列出所有内容条目
  • 前端页面能正确渲染 Markdown(含表格、代码块)
  • 页面风格与项目整体一致
  • 导航栏已添加入口
  • GitHub Actions workflow 语法正确
  • Cron 时间设置正确(注意 UTC 转换)
  • Commit message 包含 [deploy] 触发自动部署
  • 无 TypeScript 编译错误

使用示例

示例 1: 每日数据报告
用户输入:
"把 daily-reports/ 目录的报告同步到网站,做成报告页面,每天 11 点更新"

AI 执行:
1. 分析 daily-reports/ → 按日期组织,每天 2 份 Markdown 报告
2. 选择模式 A(日报型)
3. 复制到 public/data/reports/,生成 index.json
4. 创建 /reports/[date] 页面 + report-viewer 组件
5. 导航栏添加「每日报告」
6. 创建 sync_daily_reports.yml,cron: '0 3 * * *'
示例 2: 技术博客
用户输入:
"把 blog/ 目录的文章展示到网站,做成博客,每周一更新"

AI 执行:
1. 分析 blog/ → 按文件组织,Markdown 带 frontmatter
2. 选择模式 B(博客型)
3. 复制到 public/data/blog/,生成 index.json
4. 创建 /blog 列表页 + /blog/[slug] 详情页
5. 导航栏添加「Blog」
6. 创建 sync_blog.yml,cron: '0 0 * * 1'(每周一 UTC 00:00)
示例 3: Landing Page 数据更新
用户输入:
"把 data/stats.json 的数据同步到首页的统计区块,每天更新"

AI 执行:
1. 分析 data/stats.json → 单文件 JSON
2. 选择模式 C(动态区块型)
3. 复制到 public/data/stats.json
4. 修改首页组件读取该 JSON 渲染统计区块
5. 创建 sync_stats.yml,cron: '0 2 * * *'

支持的框架

框架页面生成Markdown 渲染备注
Next.js (App Router)✅ 完整支持react-markdown + remark-gfm推荐
Next.js (Pages Router)✅ 支持react-markdown + remark-gfm
Astro✅ 支持内置 Markdown 支持
Hugo / Jekyll✅ 支持原生 Markdown静态站点
Vite + React✅ 支持react-markdown需手动路由

注意事项

  • 内容源和前端项目在同一仓库时最简单;跨仓库需要在 Actions 中配置多仓库 checkout
  • 首次同步大量历史内容时注意 Git commit 大小
  • 不同部署平台(Cloudflare Pages / Vercel / Netlify)的自动部署触发方式可能不同
  • 确保 Markdown 文件使用 UTF-8 编码

© 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 3 other files in auto-page-sync of kennyzir/7deer_skills.

  • SKILL.md
  • resources/rebuild_index.py
  • resources/report_types_example.json
  • resources/sync_workflow_template.yml

Open the folder on GitHubat commit 32a6881

Compare with similar skills

Auto Page Sync 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.

Auto Page Sync compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Auto Page Sync this skillkennyzir/7deer_skills322—~1.7kAutomated safety check: PassMIT
Released-kimuson/claude-code-viewer1.3k—~1.2kAutomated safety check: PassMIT
npm Release Via GitHub Actionsjmfederico/pi-web871—~2.9kAutomated safety check: PassMIT
Agr Releasecomputerlovetech/agr451—~1.6kAutomated safety check: PassMIT
OpenWork Release Processdifferent-ai/openwork24k—~2.3kAutomated safety check: PassCustom licence
Release And CIeser/stack128—~665Automated safety check: PassCustom licence

Similar skills

  • Release

    d-kimuson/claude-code-viewer

    Run the claude-code-viewer release flow end-to-end. An agent skill from d-kimuson/claude-code-viewer.

    1.3k GitHub stars~1.2k tokensUpdated 1 mo ago
    DevOps & CloudAuto-check passed
  • A skill your agent uses whenever the user asks for a new npm version, npm release, package release, new release, version bump, publishing to npm, cutting a GitHub release, tagging a release, or…

    871 GitHub stars~2.9k tokensUpdated yesterday
    DevOps & CloudAuto-check passed
  • Agr Release

    computerlovetech/agr

    Release process for the agr package. An agent skill from computerlovetech/agr.

    451 GitHub stars~1.6k tokensUpdated 1 mo ago
    DevOps & CloudAuto-check passed
  • OpenWork Release Process

    different-ai/openwork

    Cuts an OpenWork desktop release through a tag-driven GitHub Actions workflow that makes no commits, with pre-tag checks on open fix PRs and verification afterward.

    24k GitHub stars~2.3k tokensUpdated today
    DevOps & CloudAuto-check passed
  • Release And CI

    eser/stack

    Releases and CI for eserstack: the shared version of all packages, the release command, the tag-driven build.yml run, JSR and npm publishing, changelog and breaking changes, release recovery, GitHub…

    128 GitHub stars~665 tokensUpdated 6 days ago
    DevOps & CloudAuto-check passed
  • Releasing Marchat

    Cod-e-Codes/marchat

    Prepares marchat releases: version bumps, CHANGELOG, packaging checksums, GitHub Actions release workflow, and Docker tags.

    137 GitHub stars~801 tokensUpdated 7 days ago
    DevOps & CloudAuto-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 11 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 11 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 11 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 11 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 11 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 11 days ago
    Auto-check passed

Works with

Questions about Auto Page Sync

What does Auto Page Sync do?

仓库 Markdown/JSON 内容自动同步到前端页面,配置 GitHub Actions 定时拉取 + 部署,保持 Google SEO 内容新鲜度。支持日报、博客、Changelog、Landing Page 等多种页面模式。. Auto Page Sync is an agent skill from kennyzir/7deer_skills.

When should I use Auto Page Sync?

Auto Page Sync fits situations like: tasks that involve CI/CD; tasks that involve Landing pages; tasks that involve Changelog and release notes.

How do I install Auto Page Sync in Claude Code?

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

How do I install Auto Page Sync in Codex?

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

Can I use Auto Page Sync 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 auto-page-sync -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/auto-page-sync, .gemini/skills/auto-page-sync, .github/skills/auto-page-sync and .opencode/skills/auto-page-sync in your project.

What does Auto Page Sync need to run?

Going by SKILL.md and its folder, Auto Page Sync needs Python for the scripts in its folder. Our summary lists: Python 3.

Does Auto Page Sync 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 Auto Page Sync 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 Auto Page Sync use?

Auto Page Sync 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 Auto Page Sync use?

About 1.7k tokens (SKILL.md is roughly 6.6k 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 Auto Page Sync?

Skills that share tags, products or a category with Auto Page Sync: Release (d-kimuson/claude-code-viewer, 1.3k stars), npm Release Via GitHub Actions (jmfederico/pi-web, 871 stars), Agr Release (computerlovetech/agr, 451 stars) and OpenWork Release Process (different-ai/openwork, 24k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Auto Page Sync?

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.