菜单
Lazarus — Bring dead websites back to life. Recover Google-indexed content from defunct websites via Wayback Machine, then deploy with AutoCode. Only recovers content that was actually indexed — no garbage. 捡尸复活已倒闭网站，只捡被谷歌收录过的内容，配合AutoCode一键部署。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
微信公众号写作助手。200+篇实战验证的爆文结构引擎。你投喂素材，它输出MD文件+封面图提示词+自查报告。内置17条写作基因、品牌简称、平台合规、10项自查清单。不接受无素材请求，不是内容生成器。
Niche-Awesome — Solve the #1 problem for beginners building AI products: not knowing what to build. A complete 6-step BRD (Business Requirements Document) research process for niche product selection and market validation. You do the searching, AI does the analysis. Works with any AI, no coding required.
DeAI — Improve AI-drafted text to sound naturally human. Three-layer editing: remove overused filler phrases, mark positions for authentic personal voice, restructure for natural rhythm. Adds review markers ([💬] [📝] [📊]) for user to fill in — does not generate content. Supports Chinese, English, Japanese, Korean.
白拿钱 — 美国、加拿大、英国、澳洲集体诉讼理赔追踪技能。监控多国开放案件，筛选免凭证案件。数据源覆盖OpenClassActions、TopClassActions、ClaimDepot及各国官方公告。纯中文交互，I-Lang v4.0协议驱动。被动查询工具，不主动推送（推送功能见freemoney-plugin插件版）。
无所不能 — Universal prompt compression protocol. Translate natural language into compressed I-Lang syntax (save 40-65% tokens). Text-to-text translator only — does not access files, URLs, or external resources. Works with ChatGPT, Claude, Gemini, DeepSeek, Kimi. Instruction-only, no code, no credentials.
Compress natural language prompts into I-Lang — AI-native structured instructions. 40-65% token savings. Output is text notation only — review before passing to execution agents.
| name | lazarus |
| description | Lazarus — Bring dead websites back to life. Recover Google-indexed content from defunct websites via Wayback Machine, then deploy with AutoCode. Only recovers content that was actually indexed — no garbage. 捡尸复活已倒闭网站，只捡被谷歌收录过的内容，配合AutoCode一键部署。 |
| version | 1.0.5 |
| author | ilang-ai |
| homepage | https://ilang.ai |
| tags | ["content-recovery","wayback-machine","original-content","seo","google-index","website-revival","archive","autocode","deployment"] |
Creating original content is hard. Millions of websites die every year. Their content disappears, but the Wayback Machine remembers everything.
That content is original, abandoned, and free. But not all of it is worth recovering — only content that Google actually indexed matters for SEO. Unindexed pages are garbage nobody ever saw.
[STEP:1] Verify Death — Confirm the site is truly dead (WHOIS expired, unreachable)
[STEP:2] Scout — Query Wayback Machine CDX API, discover all archived pages
[STEP:3] Verify Index — Check Google for each page: indexed = GOLD, likely indexed = SILVER, never indexed = SKIP
[STEP:4] Recover — Download latest snapshots (GOLD + SILVER only)
[STEP:5] Clean — Strip Wayback artifacts, fix links, convert to Markdown
[STEP:6] Organize — Categorize by topic + index status, add frontmatter
[STEP:7] Review — Screen recovered content for personal data (emails, phone numbers, addresses), API keys, internal URLs, account endpoints, and copyrighted assets. Flag or remove before publishing.
[STEP:8] Deploy — Guide user to deploy via AutoCode or any static site generator
> **Legal notice**: Recovered content may still be protected by copyright even if the original site is dead. Domain expiration does not transfer content ownership. Review all recovered material for copyright, trademark, and personal information before republishing.
Dead site with 500 archived pages. Without Lazarus, you'd blindly recover all 500 — most of them junk. With Lazarus: 80 were Google-indexed (GOLD), 120 were likely indexed (SILVER), 300 were never indexed (SKIP).
You just saved 60% of your time and got only the content that matters.
Lazarus recovers content → AutoCode deploys → Live site in one session
↑ |
└──── User finds more dead sites ←─────────────┘
AutoCode — 47 skills for Claude Code. One command to deploy recovered content to Cloudflare Pages, Hugo, WordPress, or any platform.
prompt.md, copy the full text做原创内容太难了。每年有数百万网站倒闭，内容从互联网上消失。但 Wayback Machine 记住了一切。
问题是：不是所有内容都值得捡。只有被谷歌收录过的内容才有SEO价值。没被收录过的页面，说明连搜索引擎都不要，捡回来是垃圾。
捡尸要捡有价值的尸。
[步骤1] 确认死亡 — 验证域名确实挂了（WHOIS过期，无法访问）
[步骤2] 侦察 — 查询 Wayback Machine CDX API，发现所有历史页面
[步骤3] 验证收录 — 逐一检查谷歌：收录过=金矿，可能收录=银矿，从未收录=跳过
[步骤4] 恢复 — 只下载金矿+银矿页面的最新快照
[步骤5] 清洗 — 去掉 Wayback 注入代码，修链接，转 Markdown
[步骤6] 整理 — 按主题+收录状态分类，加 frontmatter
[步骤7] 审查 — 筛查恢复内容中的个人信息（邮箱、电话、地址）、API密钥、内部URL、账户端点和受版权保护的资源。发布前标记或删除。
[步骤8] 部署 — 引导用户用 AutoCode 一键部署
> **法律提醒**：恢复的内容可能仍受版权保护，域名过期不等于内容所有权转移。发布前请确认版权、商标和个人隐私信息。
一个死站有500个历史页面。不用Lazarus的话，你只能盲目全捡回来——大部分是垃圾。 用 Lazarus：80个被谷歌收录过（金矿），120个可能收录过（银矿），300个从未收录（跳过）。
省了60%的时间，只拿有价值的内容。
Lazarus 恢复内容 → AutoCode 一键部署 → 活站上线
↑ |
└──── 用户发现更多死站 ←──────────────┘
AutoCode — Claude Code 的47技能包。一句话把恢复的内容部署到 Cloudflare Pages、Hugo、WordPress。
prompt.md，复制全文| Resource | Link |
|---|---|
| AutoCode | github.com/ilang-ai/autocode |
| I-Lang Protocol | ilang.ai |
| OpenClaw Skills | github.com/ilang-ai/ilang-openclaw |
MIT — Free to use, share, and build on.
© 2026 I-Lang Research, iLang Inc., Canada.