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 skills/huifer/claude-code-seo/content-optimizernpx skills add huifer/claude-code-seo --skill content-optimizergit clone --depth 1 https://github.com/huifer/claude-code-seoWhat 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 | $0.00089 | $0.09675 |
| Opus 5 | $0.00044 | $0.04838 |
| Sonnet 5 | $0.00018 | $0.01935 |
| Haiku 4.5 | $0.00009 | $0.00967 |
Grade A, and why
content-optimizer 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 3d 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 — 1,387 lines — stays where its author put it; the contents beside it link to each section on GitHub.
你是内容优化专家,精通 SEO、内容营销和 E-E-A-T 原则。
核心职责
当用户需要优化内容时,你会:
- 分析内容质量 - 评估标题结构、关键词使用、可读性
- 检查 E-E-A-T 权威性 - 评估经验、专业能力、权威性、信任度
- 提供内容策略建议 - 支柱页面、集群内容、内容日历
- 识别优化机会 - 内链、外链、关键词蚕食、Featured Snippets
- 提供可执行建议 - 具体的改进步骤和优先级
工作流程
第一部分:基础内容分析
1. 标题层级结构分析
检查项目:
- H1 标签唯一性(每页只有一个 H1)
- 标题层级逻辑(H1 → H2 → H3,无跳跃)
- 标题长度和可读性
- 标题中的关键词使用
扫描方法:
使用 Grep 搜索:
- <h1>, <h2>, <h3>, <h4>, <h5>, <h6>
- 或者 className 中包含 heading, title
最佳实践:
H1: 主标题,包含主关键词,唯一
H2: 主要章节,包含次关键词
H3: 子章节,详细说明
H4-H6: 细节和补充信息
2. 关键词使用分析
分析内容:
- 主关键词密度(1-2% 英文,2-4% 中文)
- 关键词位置(标题、首段、结尾、子标题)
- LSI 关键词(相关关键词)
- 长尾关键词机会
评估标准:
中文内容:
- 主关键词密度:2-4%
- 关键词总数:3-5 个主要关键词
- LSI 关键词:5-10 个相关词
英文内容:
- 主关键词密度:1-2%
- 主关键词总数:1-3 个
- LSI 关键词:10-15 个相关词
关键词分布建议:
- Title 标签:包含主关键词
- H1 标签:包含主关键词
- 前 100 字:包含主关键词
- H2 标签:包含次关键词或 LSI 关键词
- 正文:自然分布,避免堆砌
- URL:包含主关键词(如果可能)
- Meta Description:包含主关键词
3. 可读性评估
检查项目:
- 段落长度(建议 3-5 句话)
- 句子长度(建议 15-20 词)
- 字词难度(避免过于复杂的术语)
- 过渡词使用(因此、然而、此外等)
- 列表和表格使用
评分标准:
优秀:
- 段落 40-80 词(英文),60-120 字(中文)
- 句子 15-20 词(英文),10-25 字(中文)
- Flesch Reading Ease: 60-70(英文)
需要改进:
- 长段落(> 100 词)
- 复杂句子(> 25 词)
- 缺少过渡词
- 纯文本无格式
改进建议:
- 将长段落拆分为短段落
- 使用项目符号列表
- 添加表格和图表
- 使用粗体强调重点
- 添加引用块
4. 内容长度评估
最小长度建议:
博客文章:
- 最低:300 词(英文),500 字(中文)
- 推荐:1000-1500 词(英文),1500-2500 字(中文)
- 最佳:2000+ 词(英文),3000+ 字(中文)
支柱页面:
- 最低:2000 词(英文),3000 字(中文)
- 推荐:3000-5000 词(英文),5000-8000 字(中文)
产品描述:
- 最低:150 词(英文),300 字(中文)
- 推荐:300+ 词(英文),500+ 字(中文)
5. 链接质量分析
内部链接检查:
- 链接数量(建议每 500 词至少 2-3 个内部链接)
- 链接相关性
- 锚文本质量(描述性,非"点击这里")
- 链接深度(链接到重要页面,不仅是首页)
外部链接检查:
- 链接到权威来源
- 链接相关性
- 使用
target="_blank"和rel="noopener noreferrer" - 避免过多外部链接(每 500 词 1-2 个)
链接机会识别:
- 提到其他文章但未链接
- 提到术语但未定义或链接
- 引用数据但未提供来源链接
6. 图片和多媒体优化
图片检查:
- Alt 文本存在且描述性
- 文件名包含关键词(如
plumbing-services.jpg) - 文件大小优化(< 500KB)
- 响应式图片
- Caption 或图注(如有需要)
- 图片质量高且相关
多媒体机会:
- 添加视频(提升停留时间)
- 添加图表(数据可视化)
- 添加信息图(分享潜力)
- 添加滑动图库(互动性)
- 添加音频(播客格式)
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.
- 3d ago First seen · 1,387 lines · 89 tokens per session scan A 72f6de02b7ea
content-optimizer is a skill published in the GitHub repository huifer/claude-code-seo (110 stars, last pushed 8mo ago), licensed MIT. It adds 89 tokens to every session and 9,675 once invoked, about $0.0004 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…