SEO Keyword Clustering
AgriciDaniel/claude-seo
Clusters keywords by how much their search results overlap and designs a hub-and-spoke content plan with an internal link matrix and an interactive cluster map.
整站关键词研究与深度挖掘。输入一个网站域名或URL，自动完成：首页主题分析 → 递归式关键词树扩展（Google联想词多级分叉）→ 去重合并 → 关键词分层 → 10词SERP详细分析 → 3词定方向，最终输出完整 Markdown 报告。
Install Site Keyword Research
$ npx skills add kennyzir/7deer_skills --skill site-keyword-research -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install kennyzir/7deer_skills site-keyword-research --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/kennyzir/7deer_skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/site-keyword-research .claude/skills/site-keyword-research && rm -rf skills-srcUse ~/.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/
Install the "site-keyword-research" agent skill from https://github.com/kennyzir/7deer_skills/tree/main/site-keyword-research into .claude/skills/site-keyword-research/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "site-keyword-research", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/kennyzir/7deer_skills/tree/main/site-keyword-researchType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add kennyzir/7deer_skills --skill site-keyword-research -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install kennyzir/7deer_skills site-keyword-research --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/kennyzir/7deer_skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/site-keyword-research .agents/skills/site-keyword-research && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "site-keyword-research" agent skill from https://github.com/kennyzir/7deer_skills/tree/main/site-keyword-research into .agents/skills/site-keyword-research/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "site-keyword-research", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add kennyzir/7deer_skills --skill site-keyword-research -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install kennyzir/7deer_skills site-keyword-research --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/kennyzir/7deer_skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/site-keyword-research .cursor/skills/site-keyword-research && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "site-keyword-research" agent skill from https://github.com/kennyzir/7deer_skills/tree/main/site-keyword-research into .cursor/skills/site-keyword-research/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "site-keyword-research", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/kennyzir/7deer_skills.git --path site-keyword-research--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add kennyzir/7deer_skills --skill site-keyword-research -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install kennyzir/7deer_skills site-keyword-research --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/kennyzir/7deer_skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/site-keyword-research .gemini/skills/site-keyword-research && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "site-keyword-research" agent skill from https://github.com/kennyzir/7deer_skills/tree/main/site-keyword-research into .gemini/skills/site-keyword-research/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "site-keyword-research", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install kennyzir/7deer_skills site-keyword-researchInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add kennyzir/7deer_skills --skill site-keyword-research -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/kennyzir/7deer_skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/site-keyword-research .github/skills/site-keyword-research && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "site-keyword-research" agent skill from https://github.com/kennyzir/7deer_skills/tree/main/site-keyword-research into .github/skills/site-keyword-research/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "site-keyword-research", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add kennyzir/7deer_skills --skill site-keyword-research -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install kennyzir/7deer_skills site-keyword-research --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/kennyzir/7deer_skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/site-keyword-research .opencode/skills/site-keyword-research && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "site-keyword-research" agent skill from https://github.com/kennyzir/7deer_skills/tree/main/site-keyword-research into .opencode/skills/site-keyword-research/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "site-keyword-research", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
site-keyword-research- GitHub stars
- 322
- Token cost
- ~1.9k tokens
- SKILL.md length
- 489 words
- Files
- 3 (incl. references)
- Skills in repo
- 33
- Repo updated
- First seen
- Licence
- MIT
At a glance
整站关键词研究与深度挖掘。输入一个网站域名或URL，自动完成：首页主题分析 → 递归式关键词树扩展（Google联想词多级分叉）→ 去重合并 → 关键词分层 → 10词SERP详细分析 → 3词定方向，最终输出完整 Markdown 报告。
- Works in 3 steps: 等待 5 秒后刷新页面重试 → 最多重试 2 次 → 如果仍然失败，记录「CAPTCHA 拦截」标注，改用 web_search…
- Tasks that involve Keyword research
- SKILL.md covers 核心工作流, 输入参数, 第一阶段：递归关键词树扩展（核心改进） and 第二阶段：分层筛选（20词）, plus 6 more sections
- Reaches google.com
What it does
Site Keyword Research is an agent skill from kennyzir/7deer_skills. 整站关键词研究与深度挖掘。输入一个网站域名或URL，自动完成：首页主题分析 → 递归式关键词树扩展（Google联想词多级分叉）→ 去重合并 → 关键词分层 → 10词SERP详细分析 → 3词定方向，最终输出完整 Markdown 报告。 触发条件：用户说"分析网站关键词"、"关键词研究"、"keyword research"、"挖掘某网站的关键词"、或提供一个URL说"分析这个网站的SEO关键词机会"。
Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including reference files (for example `README.md` and `references/output-template.md`).
It sits in Marketing & SEO, covering Keyword research. 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 Keyword research
Example prompts
- “分析网站关键词”
- “keyword research”
- “挖掘某网站的关键词”
- “/site-keyword-research”
Workflow steps
3 steps, taken from the first numbered list in SKILL.md.
- 等待 5 秒后刷新页面重试
- 最多重试 2 次
- 如果仍然失败，记录「CAPTCHA 拦截」标注，改用 web_search 补充数据，并在报告中说明 SERP 数据为推算值
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
No scripts in the folder and no shell commands in SKILL.md (its code samples are javascript).
From the folder's file list and the shell code blocks in SKILL.md.
Network
Hosts in commands or code, which the agent is likely to contact:
google.com
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
Site Keyword Research loads about 1.9k tokens when it runs, and up to ~3.5k if it reads all its reference files. Until then it costs about 57 tokens; SKILL.md has 489 words of instructions outside code blocks.
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). 489 words, ~1,900 tokens.
Download SKILL.mdSave it as
.claude/skills/site-keyword-research/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.- name
- site-keyword-research
- description
- 整站关键词研究与深度挖掘。输入一个网站域名或URL，自动完成：首页主题分析 → 递归式关键词树扩展（Google联想词多级分叉）→ 去重合并 → 关键词分层 → 10词SERP详细分析 → 3词定方向，最终输出完整 Markdown 报告。 触发条件：用户说"分析网站关键词"、"关键词研究"、"keyword research"、"挖掘某网站的关键词"、或提供一个URL说"分析这个网站的SEO关键词机会"。
Site Keyword Research Skill
输入一个网站域名，输出完整的关键词研究与竞争度分析报告。核心改进：递归式关键词树扩展——不是一次扩展就停，而是持续分叉挖掘，直到词库收敛。
核心工作流
阶段一：递归关键词树扩展（不限次数，直到词库收敛）
→ 种子词 → Google搜索 → 提取 Related Searches + PASF + 问题词
→ 每个新词 → 再搜索 → 再提取 → 持续分叉
→ 直到：不再发现新词 或 词库达到上限（100个）
阶段二：去重合并 → 分层筛选（20词）
→ 去重、去无关词
→ 选20个最有价值的词进详细分析
阶段三：10词SERP详细分析 → 3词定方向
→ 竞争度打分
→ 给出最重要的3个词 + 具体操作建议关键词来源标注规范（强制）：
| 标签 | 含义 | 可信度 |
|---|---|---|
[PASF] | 来自 Google「People Also Search For」的真实搜索推荐 | ⭐⭐⭐⭐⭐ |
[RS] | 来自 Google Related Searches 联想词 | ⭐⭐⭐⭐ |
[Q] | 来自 Google 搜索结果中的「People Also Ask」问题 | ⭐⭐⭐⭐ |
[AI-主题] | AI 根据站点主题扩展生成，需人工验证 | ⭐⭐⭐ |
[竞品] | 从 SERP 结果中竞品内容提取 | ⭐⭐⭐⭐ |
输入参数
执行 skill 时需要提供以下参数：
| 参数 | 说明 | 默认值 |
|---|---|---|
domain | 要分析的网站域名（如 example.com） | 必填，从用户输入提取 |
output_dir | 报告输出目录 | 可选，默认为当前目录 |
域名格式支持：
https://example.com→ 自动提取 domainexample.com→ 直接使用www.example.com→ 提取 domain
第一阶段：递归关键词树扩展（核心改进）
1.1 站点主题分析
使用 web_fetch 抓取首页（maxChars: 2000），识别：
- 站点类型（产品工具/内容媒体/电商/SAAS/论坛）
- 核心主题（2-4个主题词，作为种子词根）
- 目标用户群体
- 主要功能/服务
同时抓取首页 HTML 标题、meta description。
1.2 种子词确定
根据站点分析，确定 3-5 个种子关键词（作为树的根节点）：
- 核心产品/服务词
- 核心场景/用途词
- 核心用户需求词
1.3 递归扩展算法（关键词树构建）
这是本 skill 的核心改进——不是一次扩展就停，而是持续分叉。
扩展规则：
每次取队首关键词出列 → Google搜索 → 提取三类词 → 入库 → 新词继续入队
直到队列空（词库收敛）或达到上限（100个唯一词）搜索格式：
https://www.google.com/search?q=<URL编码关键词>&hl=en反爬策略（必须执行）： 每次打开搜索页后，等待 3-5 秒 再执行 snapshot，给 JS 渲染足够时间：
browser(action=open, url="https://www.google.com/search?q=...&hl=en")
browser(action=wait, timeMs=4000) // 等待 JS 渲染
browser(action=snapshot, compact=true)连续搜索时，两次搜索之间随机等待 2-4 秒，避免固定频率触发反爬：
browser(action=wait, timeMs=2000 + Math.random() * 2000)如果遇到 CAPTCHA 验证页面：
- 等待 5 秒后刷新页面重试
- 最多重试 2 次
- 如果仍然失败，记录「CAPTCHA 拦截」标注，改用
web_search补充数据，并在报告中说明 SERP 数据为推算值
每次搜索必须提取以下内容：
A. Related Searches（RS）- 联想词
从搜索结果页底部「Related Searches」区域提取所有联想词，每个标注 [RS]。
B. People Also Search For（PASF）- 推荐词
从 SERP 中「People Also Search For」区域提取推荐词，每个标注 [PASF]。
C. People Also Ask（PAA）- 问题词
从 SERP 中「People Also Ask」区域提取问题，每个标注 [Q]。
提取方法：
- 用
browser(action=open, url="...")打开搜索页 browser(action=snapshot, compact=true)获取 DOM- 搜索
Related Searches、People Also Search For、People Also Ask区块 - 每个区块内的词/问题逐一提取
递归扩展流程图：
种子词队列：[seed1, seed2, seed3]
已收集词库：[]
第1轮：
出列 seed1 → 搜索 → 得到 [rs1, rs2, pasf1, q1]
入库：[rs1[RS], rs2[RS], pas1[PASF], q1[Q]]
新词入队：[rs1, rs2, pasf1, q1, seed2, seed3]
第2轮：
出列 rs1 → 搜索 → 得到 [rs1a, pasf1a, q1a]
入库：[rs1a[RS], pasf1a[PASF], q1a[Q]]
新词入队：[rs2, pasf1, q1, seed2, seed3, rs1a, pasf1a, q1a]
第3轮：
出列 rs2 → 搜索 → ...
...持续直到队列空或达到100词上限1.4 去重与过滤规则
每次入库前执行去重：
必须去重：
- 完全相同的词（大小写不敏感）
- 复数形式与原形视为同义词（保留一个）
- 与站点主题完全无关的词
词库上限：
- 目标：收集 80-100 个唯一关键词
- 实际执行中如果达到 100 个，停止扩展，进入分层
- 如果队列提前耗尽（词库收敛），也停止扩展
1.5 AI 辅助扩展（补充手段，不是主力）
在递归扩展完成后，如果词库不足 50 个，用 AI 补充扩展：
基于已收集的 [PASF] 和 [RS] 词，识别词根模式，生成更多变体：
模式举例：
{词根} + generator / maker / creator{词根} + free / online / AIhow to {词根} / {词根} tutorial / {词根} for beginnersbest {词根} / {词根} alternatives / {词根} vs
每个生成的词标注 [AI-主题]，需入库参与后续分层。
1.6 候选词收集结果记录
最终词库格式（每个词必须标注来源和深度）：
{关键词} [来源标签|扩展深度]
例：
oracle card generator [RS|depth=1] — 从种子词第1轮扩展
emotional tarot reading [PASF|depth=2] — 从第2轮词扩展而来
how to use oracle cards [Q|depth=1] — 从种子词第1轮扩展
ai oracle card generator [AI-主题] — AI补充生成扩展深度说明：
depth=1：直接从种子词一次扩展而来，最相关depth=2：从 depth=1 的词再扩展，相关性稍弱但覆盖更广depth=3+：多级扩展，可能发现意外的低竞争词
第二阶段：分层筛选（20词）
2.1 关键词相关性初筛
保留标准（同时满足）：
- 与站点核心主题高度相关
- 搜索意图明确
- 不涉及品牌词（除非该品牌是对手）
剔除标准（满足任一即剔除）：
- 完全无关领域（如医疗、法律等专业领域）
- 过于泛泛
- 无实际搜索信号（Google 没有推荐）
2.2 分层（四层模型）
| 层级 | 定义 | 目标数量 | 策略 |
|---|---|---|---|
| 核心词 | 高搜索量，主赛道 | 1-3个 | 品牌期/长期目标 |
| 中尾词 | 中等搜索量，明确意图 | 3-5个 | 3-6个月内容建设 |
| 长尾词 | 低搜索量，精准需求 | 8-12个 | 立即行动，快速见效 |
| 问题词 | 问句形式，信息需求 | 5-8个 | 博客内容，覆盖漏斗顶端 |
2.3 最终20词筛选标准
从词库中选 20 个进入 SERP 分析：
优先保留：
- 有
[PASF]或[RS]来源（Google 真实推荐） - 包含高意图修饰词（free、best、generator、alternative、how to）
- 搜索意图是 Transactional 或 Commercial Investigation
- 扩展深度浅的词优先（depth=1 > depth=2 > depth=3+）
第三阶段：10词SERP详细分析
Show full SKILL.md (196 more words)Show less
3.1 SERP 分析执行
对筛选出的 20 个词，快速扫描 SERP，挑选 10 个最有商业价值的做详细分析。
快速扫描维度：
- 广告主密度（0/少/多）
- 现有结果类型（工具/博客/论坛/目录）
- Featured Snippet 情况
优先分析：
- Transactional 意图词（商业价值最高）
- 有
[PASF]来源的词（Google 推荐=真实需求） - 扩展深度浅的词
3.2 详细分析维度
对每个入选词，打开 SERP：
https://www.google.com/search?q=<URL编码关键词>&hl=en用 snapshot compact=true 抓取，记录：
| 分析维度 | 记录内容 |
|---|---|
| 广告主数量 | 0 / 1-3 / 4-6 / 6+ |
| 广告主类型 | 列出主要广告主 |
| Featured Snippet | 有 / 无 |
| 视频结果 | 有 / 无（数量） |
| 前10域名 + 类型 | 工具/博客/目录/论坛/官方 |
| 前10内容深度 | 薄页(<200字) / 中等 / 深度(1000+字) |
| 高权重站数量 | Wikipedia/Quora/Amazon/大型媒体 |
| PASF 推荐词 | 列出 Google 推荐的关联搜索词 |
3.3 竞争度打分
| 维度 | 1分 | 2分 | 3分 | 4分 | 5分 |
|---|---|---|---|---|---|
| 广告主 | 0 | 1-2 | 3-5 | 6-8 | 8个以上 |
| 高权重站 | 0 | 1 | 2-3 | 4-5 | 5个以上 |
| Featured Snippet | 无 | — | 1个 | — | 2个以上 |
| 视频结果 | 无 | — | 1-2个 | — | 3个以上 |
| 内容深度 | 全薄页 | 多数薄 | 混合 | 多数深 | 全深度 |
总分 5-10 → 🟢 低竞争（立即行动） 总分 11-17 → 🟡 中竞争（可切入） 总分 18-25 → 🔴 高竞争（观望/迂回）
第四阶段：Top 3 词定方向
4.1 选词标准
综合以下选出最重要的 3 个词：
- 竞争度低（分数 ≤ 10）
- Transaction 意图强（商业转化价值高）
- Google 推荐词优先（[PASF] 来源）
- 扩展深度浅（depth=1 或 depth=2）
4.2 策略报告格式
对每个 Top 3 词，给出：
关键词：{词} [来源标签|扩展深度]
分层：{核心词/中尾词/长尾词/问题词}
竞争度：{分数}分 / {低中高三档}
机会描述：
{一句话说明为什么这个机会现在存在，以及为什么 Google 推荐这个词}
推荐动作（具体到操作）：
- 第一步：做什么
- 第二步：做什么
- 第三步（如需要）：做什么
落地页建议：
- 标题：{建议标题}
- 核心卖点：{3个核心卖点}
- CTA：{建议的 Call to Action}
- 覆盖长尾：{建议同时覆盖的关联长尾词}
外链机会：
{对应的外链建设策略}输出规范
Markdown 报告（主要内容输出到这里）
报告自动保存到文件，文件名格式：
{output_dir}/{domain}-keyword-research-{YYYY-MM-DD}.md如果 output_dir 未指定，默认保存到执行目录。
报告结构：
# {域名} 关键词研究报告 — YYYY-MM-DD
## 第一章：站点定位分析
## 第二章：递归关键词树扩展记录
## 第三章：完整候选词库（全部词，含来源+扩展深度）
## 第四章：关键词分层矩阵（20词）
## 第五章：10词SERP详细分析
## 第六章：综合机会矩阵（20词横向对比）
## 第七章：Top 3 关键词定方向
## 第八章：外链策略建议
## 第九章：数据说明与后续建议聊天回复（摘要形式）
✅ 关键词研究报告已生成
**站点：** {domain}
**递归扩展深度：** {N}轮
**候选词总数：** {N}个
**分析词数：** {M}个
**竞争度概况：** 🟢低竞{N1}个 / 🟡中竞{N2}个 / 🔴高竞{N3}个
📄 完整报告：{filename}
🥇 Top 3 关键词：
1. {词1} — {一句话机会描述}
2. {词2} — {一句话机会描述}
3. {词3} — {一句话机会描述}
💡 低竞争词发现：{1-2个特别值得关注的低竞争词简述}关键原则
- 递归扩展必须执行到底：不允许只扩一轮就停，必须持续到词库收敛或达到上限
- 每个词必须标注来源和扩展深度：不标注的词视为
[AI-主题] - PASF 词优先分析：Google 推荐 = 真实用户需求，最有价值的信号
- 20词 → 10词筛选：20词进分层，10词做详细 SERP 分析，不要跳过
- Top 3 必须有具体操作建议：不能只给词不给动作
- 扩展深度浅的词优先：depth=1 最相关，depth=3+ 可能发现意外机会但可信度稍低
错误处理
| 场景 | 处理 |
|---|---|
| web_fetch 403/404 | 跳过，用已知主题信息继续分析 |
| 站点是全新站（DA≈0） | 标注"新站，竞品内容质量差距是核心机会指标" |
| Google 弹出验证 | 必须用 browser retry（等5秒刷新 / 最多重试2次），禁止降级到 web_search；如果 browser 完全失败，标注「搜索数据获取失败，关键词来源基于官网分析+AI扩展，可信度降低」，不得使用 AI 猜测真实搜索量数据 |
| web_search 全部失败 | 标注「搜索数据获取失败，关键词来源基于官网分析+AI扩展，可信度降低」，不得使用 AI 猜测真实搜索量数据；报告中必须明确标注每个关键词的来源标签，无 [PASF]/[RS] 标签的词单独列出 |
| 队列提前耗尽（词库收敛） | 记录收敛轮次，进入分层分析 |
| SERP 无法抓取（地理位置限制） | 标注"竞争度为推算值，建议在美国节点复查 PASF 数据" |
参考文件
- 完整报告模板：
references/output-template.md - 单关键词竞争度分析：
keyword-competition-analysis/SKILL.md
© 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 2 other files (references) in site-keyword-research of kennyzir/7deer_skills.
- SKILL.md
- README.md
- references/output-template.md
Open the folder on GitHubat commit 32a6881
Compare with similar skills
Site Keyword Research 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Site Keyword Research this skillkennyzir/7deer_skills | 322 | — | ~1.9k | Automated safety check: Pass | MIT | |
| SEO Keyword ClusteringAgriciDaniel/claude-seo | 19k | 2 repos | ~3.3k | Automated safety check: Pass | MIT | |
| Evaluate Skillevery-app/open-seo | 23k | — | ~1.8k | Automated safety check: Notes | MIT | |
| SEO Content Brief GeneratorAgriciDaniel/claude-seo | 19k | 2 repos | ~2.6k | Automated safety check: Pass | MIT | |
| Blog GoogleAgriciDaniel/claude-blog | 2.3k | 1 repos | ~3.3k | Automated safety check: Notes | MIT | |
| FLOW SEO FrameworkAgriciDaniel/claude-seo | 19k | 2 repos | ~1.4k | Automated safety check: Pass | MIT |
Similar skills
Evaluate Skill
every-app/open-seo
Test a candidate OpenSEO skill end to end by running fresh, isolated Codex sessions against the local backend and scoring the reports they save.
SEO Content Brief Generator
AgriciDaniel/claude-seo
Builds research-backed SEO content briefs with competitor scoring, per-section word counts and page-type templates, for new pages or improving existing ones.
Blog Google
AgriciDaniel/claude-blog
Google API integration for blog performance: PageSpeed Insights, CrUX Core Web Vitals with 25-week history, Search Console performance, URL Inspection, Indexing API, GA4 organic traffic, NLP entity…
FLOW SEO Framework
AgriciDaniel/claude-seo
Brings the FLOW framework's stage-specific SEO prompts into the agent, from keyword discovery through backlinks, on-page work and conversion to local SEO, loaded on demand.
SEO Dataforseo
AgriciDaniel/codex-seo
Live SEO data via DataForSEO MCP server. An agent skill from AgriciDaniel/codex-seo.
More from kennyzir/7deer_skills
All 33 skills in this repoRoblox Homepage Ranking Auditor
kennyzir/7deer_skills
Audit a Roblox or game-site homepage against the RB Auto Golden Homepage model.
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.
Youtube Transcribe
kennyzir/7deer_skills
YouTube video transcription and memory workflow. An agent skill from kennyzir/7deer_skills.
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.
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.
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.
Related
Categories
Questions about Site Keyword Research
What does Site Keyword Research do?
整站关键词研究与深度挖掘。输入一个网站域名或URL，自动完成：首页主题分析 → 递归式关键词树扩展（Google联想词多级分叉）→ 去重合并 → 关键词分层 → 10词SERP详细分析 → 3词定方向，最终输出完整 Markdown 报告。. Site Keyword Research is an agent skill from kennyzir/7deer_skills.
When should I use Site Keyword Research?
Site Keyword Research fits situations like: tasks that involve Keyword research.
How do I install Site Keyword Research in Claude Code?
Run `npx skills add kennyzir/7deer_skills --skill site-keyword-research -a claude-code`. Or copy the skill folder (site-keyword-research in kennyzir/7deer_skills) into .claude/skills/site-keyword-research in your project. Claude Code loads it when a task matches its description.
How do I install Site Keyword Research in Codex?
Run `npx skills add kennyzir/7deer_skills --skill site-keyword-research -a codex`. Or copy the skill folder (site-keyword-research in kennyzir/7deer_skills) into .agents/skills/site-keyword-research in your project. Codex loads it when a task matches its description.
Can I use Site Keyword Research 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 site-keyword-research -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/site-keyword-research, .gemini/skills/site-keyword-research, .github/skills/site-keyword-research and .opencode/skills/site-keyword-research in your project.
What does Site Keyword Research need to run?
SKILL.md names no scripts, command-line tools or credentials: Site Keyword Research is instructions for the agent only.
Does Site Keyword Research access the network?
SKILL.md names 1 domain. In commands or code: google.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.
Is Site Keyword Research 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 Site Keyword Research use?
Site Keyword Research 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 Site Keyword Research use?
About 1.9k tokens (SKILL.md is roughly 7.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.6k tokens, read only when the agent opens those files.
What are the alternatives to Site Keyword Research?
Skills that share tags, products or a category with Site Keyword Research: SEO Keyword Clustering (AgriciDaniel/claude-seo, 19k stars), Evaluate Skill (every-app/open-seo, 23k stars), SEO Content Brief Generator (AgriciDaniel/claude-seo, 19k stars) and Blog Google (AgriciDaniel/claude-blog, 2.3k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Site Keyword Research?
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.