Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/huifer/claude-code-seo/generate-reportgit clone --depth 1 https://github.com/huifer/claude-code-seoWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/huifer/claude-code-seo/generate-report)<a href="https://agentmods.dev/commands/huifer/claude-code-seo/generate-report"><img src="https://agentmods.dev/badge/commands/huifer/claude-code-seo/generate-report.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00023 | $0.05093 |
| Opus 5 | $0.00012 | $0.02547 |
| Sonnet 5 | $0.00005 | $0.01019 |
| Haiku 4.5 | $0.00002 | $0.00509 |
Grade A, and why
generate-report scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 664 lines — stays where its author put it; the contents beside it link to each section on GitHub.
完整实现
命令执行流程
# 高级报告生成执行流程
## 步骤 1: 参数解析和验证
输入：type, domain, period, format, interactive, include-charts
处理：
- 验证域名格式
- 验证报告类型
- 检查数据可用性
输出：配置对象
## 步骤 2: 数据收集和处理
根据报告类型收集数据：
- executive-summary: 关键指标、主要发现、快速获胜
- technical-analysis: 详细技术分析、代码示例
- geo-comprehensive: 全部 GEO 数据、所有引擎
- competitive-intelligence: 竞争对手对比、差距分析
处理：
- 从缓存读取历史数据
- 整合多个数据源
- 计算趋势和增长率
- 准备可视化数据
## 步骤 3: 报告生成
根据 format 参数：
- markdown: < 10s
- html: < 15s（交互式 < 20s）
- pdf: < 20s
- json: < 5s
- excel: < 10s
## 步骤 4: 质量验证
- 数据准确性检查
- 格式一致性验证
- 可视化清晰度检查
- 交互功能测试
## 步骤 5: 报告输出
保存到：.claude-flow/cache/reports/报告ID.格式
返回：报告路径和摘要
报告类型详解
1. Executive Summary（执行摘要）
特点：
- 简洁明了（2-3 页）
- 突出关键指标
- 重点关注 ROI
- 可执行建议
输出示例（Markdown）：
# 📊 GEO 执行摘要报告
**域名：** yoursite.com
**报告周期：** 2024-01-15 至 2024-02-15（90 天）
**报告时间：** 2024-02-15 10:30
**报告类型：** 执行摘要
---
## 🎯 关键指标
### 整体表现
| 指标 | 当前值 | 目标值 | 趋势 | 状态 |
|------|--------|--------|------|------|
| **GEO 评分** | **72/100** | 85/100 | ⬆️ +12 | 🟡 |
| AI 引用次数 | 677 | 800 | ⬆️ +45% | ✅ |
| 行业排名 | Top 10% | Top 5% | ⬆️ +15% | ✅ |
| 月度增长 | +45% | +50% | ⬆️ | 🟢 |
**总体评价：** 表现优秀，接近目标 ✅
---
## 🔍 主要发现
### ✅ 成功亮点
1. **AI 搜索可见性提升 45%**
- ChatGPT: +18%（234 次引用）
- Claude: +22%（189 次引用）
- Perplexity: +15%（156 次引用）
2. **Claude 引用率达到行业 Top 10%**
- 可见性评分：75/100
- 排名：#3 / 50 竞争对手
- 领先优势：+23 分
3. **内容质量显著提升**
- 数据质量：75/100 → 80/100
- 内容结构：55/100 → 70/100
- 实体关系：68/100 → 78/100
### ⚠️ 需要改进
1. **Google SGE 表现落后**
- 当前：55/100
- 行业平均：60/100
- 差距：-5 分
- **优先级：高**
2. **内容更新频率不足**
- 当前：每月 4 篇
- 建议：每周 2 篇
- **预期影响：** +15%
3. **多媒体内容缺乏**
- 当前：2 个视频
- 建议：10 个视频
- **预期影响：** +8%
---
## 🎯 快速获胜（本月可完成）
### 高优先级（影响 +10 分以上）
#### 1. 优化 Google SGE 表现（+15 分）
**问题：** 缺少结构化数据和频繁更新
**解决方案：**
- ✅ 添加 FAQPage Schema（+5 分）
- ✅ 提高更新频率（+5 分）
- ✅ 增加引用来源（+5 分）
**实施时间：** 2 周
**预期效果：** Google SGE 55 → 70 (+27%)
#### 2. 增加案例研究（+10 分）
**问题：** 案例研究数量不足
**解决方案：**
- ✅ 创建 5 个新案例研究
- ✅ 添加视频版本
- ✅ 优化 SEO 和 GEO
**实施时间：** 3 周
**预期效果：** 引用次数 +20%
### 中优先级（影响 +5-10 分）
#### 3. 提升内容更新频率（+8 分）
**当前：** 每月 4 篇
**目标：** 每周 2 篇（每月 8 篇）
**预期效果：** 新鲜度 +10 分
#### 4. 优化核心内容（+7 分）
**目标页面：**
- AI SEO Complete Guide
- ChatGPT Prompts for SEO
- GEO Best Practices
**预期效果：** 整体可见性 +12%
---
## 📈 预期成果
### 30 天预测
**GEO 评分：** 72 → 80 (+11%)
**AI 引用：** 677 → 850 (+25%)
**行业排名：** Top 10% → Top 7%
### 90 天预测
**GEO 评分：** 72 → 88 (+22%)
**AI 引用：** 677 → 1,200 (+77%)
**行业排名：** Top 10% → Top 5%
**投资回报率（ROI）：**
- 投入：$5,000（内容创作 + 优化）
- 产出：$15,000（流量增长 + 转化提升）
- ROI：**200%**
---
## 📋 行动计划
### Week 1-2: 紧急修复
- [ ] 添加 3 个 FAQ Schema
- [ ] 创建内容更新日历
- [ ] 优化 5 个核心页面
### Week 3-4: 内容扩展
- [ ] 创建 5 个案例研究
- [ ] 制作 3 个视频
- [ ] 增加引用来源
### Month 2-3: 持续优化
- [ ] 每周发布 2 篇内容
- [ ] 定期更新旧内容
- [ ] 监控和调整策略
---
## 🏆 竞争对手对比
| 排名 | 网站 | 总分 | 趋势 |
|------|------|------|------|
| 1 🥇 | **yoursite.com** | **268** | ⬆️ |
| 2 🥈 | comp1.com | 207 | ➡️ |
| 3 🥉 | comp2.com | 162 | ⬇️ |
**竞争地位：** 领先 61 分 ✅
---
**报告生成：** 2024-02-15
**下次审查：** 2024-03-15
**报告文件：** `.claude-flow/cache/reports/executive-summary-20240215.md`
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 664 lines · 23 tokens per session scan A b5994e814dd2
generate-report is a command published in the GitHub repository huifer/claude-code-seo (110 stars, last pushed 8mo ago), licensed MIT. It adds 23 tokens to every session and 5,093 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
convert
Use when the user attaches a bank statement PDF or asks for CSV/XLSX/QBO/Xero export of a converted statement. Do not use for spending analysis, reconciliation, or benchmark scoring — those have their own skills.
batch-fill
Fill a form once per row of a CSV with Emboss.
analyze-uploaded-files
Extract, summarize, or tabulate enterprise documents (.docx, .xlsx, .pdf, images, etc.) that the user has shared.
read-summary
读取文档并生成摘要(Word/PDF/EPUB/Excel).
faostat-analytical-brief
Produce a FAOSTAT-style multi-page analytical brief (PDF + xlsx appendix).
finance-process
You are a financial document processing specialist that helps extract and consolidate transaction data from PDFs and CSV/Excel files.