Agent skill · Backend & API

site-analyzer

大型商业网站深度分析工具。基于 neo 项目理念,通过被动捕获 + 主动探索 + 视觉理解,完整解析网站操作逻辑。支持 API 逆向、模式提取、知识库生成。

majiayu000github.com/majiayu000GitHub ↗
claude-coderead-onlyMIT
Install
npx skills add majiayu000/claude-skill-registry --skill site-analyzer --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 6 KB
Bundled scripts: none
Version: 1.1
Allowed tools: Bash(neo:*)Bash(browser-use:*)Bash(curl:*)Bash(jq:*)
Path: skills/analysis/site-analyzer/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 534
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# Site Analyzer 大型商业网站深度分析框架,整合三种分析方式: - **被动捕获** - neo Chrome 扩展拦截所有 API 流量 - **主动探索** - browser-use 进行交互式测试 - **视觉理解** - VL 模型辅助页面语义分析 ## 完成标准 触发此 skill 时,任务完成必须满足: - [ ] 至少捕获 50 个 API 请求 - [ ] API Schema 已生成(OpenAPI 格式) - [ ] 关键流程已识别(登录/核心操作) - [ ] 知识库 SKILL.md 已生成 ## 错误处理 | 错误类型 | 处理方式 | |----------|----------| | Chrome 连接失败 | 检查 CDP 端口,重启浏览器 | | 扩展未捕获 | 重新加载扩展,检查权限 | | API 解析失败 | 手动标注,跳过复杂 schema | | 超时 | 增加 capture 时间或分批处理 | ## Token 效率优化 - 分批捕获(每批 100 请求) - 压缩 API 输出(仅保留关键字段) - 分页生成知识库 ```bash # 压缩 API 列表输出 neo capture list target-site.com --limit 20 --json | \ jq '[.[] | {method, path, status, has_body}]' ``` ## Orchestrator-Workers 模式 复杂网站分析采用分工协作: ``` ┌─────────────────┐ │ Orchestrator │ 协调分析任务 └────────┬────────┘ │ ┌────┼────┐ ▼ ▼ ▼ ┌──────┐ ┌──────┐ ┌──────┐ │捕获层│ │分析层│ │生成层│ └──────┘ └──────┘ └──────┘ │ │ │ ▼ ▼ ▼ neo flows SKILL.md capture deps openapi.yaml ``` ### Orchestrator 职责 ```bash # 主控脚本 analyze_site() { local site="$1" mkdir -p "site-analysis/$site" # Phase 1: 捕获(可并行) neo capture start "$site" & capture_pid=$! # Phase 2: 分析(依赖捕获) wait $capture_pid neo schema generate "$site" > "site-analysis/$site/schema.json" neo flows "$site" > "site-analysis/$site/flows.jso

What's inside
Steps it walks through
  1. 完成标准
  2. 错误处理
  3. Token 效率优化
  4. Orchestrator-Workers 模式
  5. Orchestrator 职责
  6. Workers 分工
  7. 核心理念
  8. 前置条件
  9. 1. 安装 neo CLI
  10. 2. 安装 browser-use
  11. 3. 配置 VL 模型
  12. 工作流
  13. Phase 1: 捕获阶段
  14. Phase 2: 分析阶段
Ships with 1 file
  • metadata.json
Commands it runs
neo capture list target-site.com --limit 20 --json | \
jq '[.[] | {method, path, status, has_body}]'
local site="$1"
mkdir -p "site-analysis/$site"
neo capture start "$site" &
wait $capture_pid
neo schema generate "$site" > "site-analysis/$site/schema.json"
neo flows "$site" > "site-analysis/$site/flows.json"
neo export-skill "$site" > "site-analysis/$site/SKILL.md"
git clone https://github.com/4ier/neo.git
More from claude-skill-registry
All skills →
About this skill
What does the site-analyzer skill do?

大型商业网站深度分析工具。基于 neo 项目理念,通过被动捕获 + 主动探索 + 视觉理解,完整解析网站操作逻辑。支持 API 逆向、模式提取、知识库生成。

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill site-analyzer --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going