Keyword Research
Automatically discover high-traffic, low-competition keywords — give this skill a topic and it returns a prioritized list with search volume, difficulty scores, intent classification, and ready-to-use topic clusters. Stop guessing what to write; start ranking for terms your audience actually searches.
Quick example: Research keywords for "project management software for nonprofits" → get 30+ opportunities scored by ROI, grouped into pillar + cluster content, with GEO keywords that trigger AI answers.
System role: Research layer skill. It turns market signals into reusable strategic inputs for the rest of the library.
Part of the SEO & GEO Skills Library · 20 skills · ClawHub · skills.sh
When This Must Trigger
Use this when the conversation involves any of these situations — even if the user does not use SEO terminology:
Use this whenever the task needs reusable market intelligence that should influence strategy, not just an ad hoc answer.
- - Starting a new content strategy or campaign
- Expanding into new topics or markets
- Finding keywords for a specific product or service
- Identifying long-tail keyword opportunities
- Understanding search intent for your industry
- Planning content calendars
- Researching keywords for GEO optimization
What This Skill Does
- 1. Keyword Discovery: Generates comprehensive keyword lists from seed terms
- Intent Classification: Categorizes keywords by user intent (informational, navigational, commercial, transactional)
- Difficulty Assessment: Evaluates competition level and ranking difficulty
- Opportunity Scoring: Prioritizes keywords by potential ROI
- Clustering: Groups related keywords into topic clusters
- GEO Relevance: Identifies keywords likely to trigger AI responses
Quick Start
Start with one of these prompts. Finish with a short handoff summary using the repository format in Skill Contract.
Basic Keyword Research
CODEBLOCK0
CODEBLOCK1
With Specific Goals
CODEBLOCK2
CODEBLOCK3
Competitive Research
CODEBLOCK4
Skill Contract
Expected output: a prioritized research brief, evidence-backed findings, and a short handoff summary ready for memory/research/.
- - Reads: user goals, target market inputs, available tool data, and prior strategy from CLAUDE.md and the shared State Model when available.
- Writes: a user-facing research deliverable plus a reusable summary that can be stored under
memory/research/. - Promotes: durable keyword priorities, competitor facts, entity candidates, and strategic decisions to
CLAUDE.md, memory/decisions.md, and memory/research/; hand canonical entity work to entity-optimizer. - Next handoff: use the
Next Best Skill below when the findings are ready to drive action.
Data Sources
Note: All integrations are optional. This skill works without any API keys — users provide data manually when no tools are connected.
See CONNECTORS.md for tool category placeholders.
With ~~SEO tool + ~~search console connected:
Automatically pull historical search volume data, keyword difficulty scores, SERP analysis, current rankings from ~~search console, and competitor keyword overlap. The skill will fetch seed keyword metrics, related keyword suggestions, and search trend data.
With manual data only:
Ask the user to provide:
- 1. Seed keywords or topic description
- Target audience and geographic location
- Business goals (traffic, leads, sales)
- Current domain authority (if known) or site age
- Any known keyword performance data or search volume estimates
Proceed with the full analysis using provided data. Note in the output which metrics are from automated collection vs. user-provided data.
Instructions
When a user requests keyword research:
At the start of each phase, announce: [Phase X/8: Name] so the user can track progress.
Phase 1/8: Scope
Ask clarifying questions if not provided:
- What is your product/service/topic?
- Who is your target audience?
- What is your business goal? (traffic, leads, sales)
- What is your current domain authority? (new site, established, etc.)
- Any specific geographic targeting?
- Preferred language?
Phase 2/8: Discover
Start with:
- Core product/service terms
- Problem-focused keywords (what issues do you solve?)
- Solution-focused keywords (how do you help?)
- Audience-specific terms
- Industry terminology
Phase 3/8: Variations
For each seed keyword, generate variations:
CODEBLOCK5
Phase 4/8: Classify
Categorize each keyword:
| Intent | Signals | Example | Content Type |
|--------|---------|---------|--------------|
| Informational | what, how, why, guide, learn | "what is SEO" | Blog posts, guides |
| Navigational | brand names, specific sites | "google analytics login" | Homepage, product pages |
| Commercial | best, review, vs, compare | "best SEO tools [current year]" | Comparison posts, reviews |
| Transactional | buy, price, discount, order | "buy SEO software" | Product pages, pricing |
Phase 5/8: Score
Score each keyword (1-100 scale):
CODEBLOCK6
Opportunity Score
Formula: INLINECODE8
Intent Value assigns a numeric weight by search intent:
- Informational = 1
- Navigational = 1
- Commercial = 2
- Transactional = 3
CODEBLOCK7
Phase 6/8: GEO-Check — AI Answer Overlap
Keywords likely to trigger AI responses:
CODEBLOCK8
Phase 7/8: Cluster
Group keywords into content clusters:
CODEBLOCK9
Phase 8/8: Deliver
Produce a report containing: Executive Summary, Top Keyword Opportunities (Quick Wins, Growth, GEO), Topic Clusters, Content Calendar, and Next Steps.
Quality bar — every recommendation must include at least one specific number. If it reads like the left column, rewrite it before including.
| ❌ Generic (rewrite before including) | ✅ Actionable |
|---|---|
| "Target long-tail keywords for better results" | "Target 'project management for nonprofits' (vol: 320, KD: 22) — no DR>40 sites in top 10" |
| "This keyword has good potential" | "Opportunity 8.4: vol 4,800, KD 28, transactional intent — gap analysis shows no content updated since 2023 in top 5" |
| "Consider creating content around this topic" | "Write '[Tool A] vs [Tool B] for small teams' — 1,200/mo searches, current #1 is a 2022 article with 12 backlinks" |
| "Optimize your page for this keyword" | "Add primary keyword to H1 (currently missing), write a 40-word direct answer in paragraph 1, add 3 internal links from your /blog/ cluster" |
> Reference: See references/example-report.md for the full report template and example.
Validation Checkpoints
Input Validation
- - [ ] Seed keywords or topic description clearly provided
- [ ] Target audience and business goals specified
- [ ] Geographic and language targeting confirmed
- [ ] Domain authority or site maturity level established
Output Validation
- - [ ] Every recommendation cites specific data points (not generic advice)
- [ ] Search volume and difficulty scores included for each keyword
- [ ] Keywords grouped by intent and mapped to content types
- [ ] Topic clusters show clear pillar-to-cluster relationships
- [ ] Source of each data point clearly stated (~~SEO tool data, user-provided, or estimated)
Example
Reference: See references/example-report.md for a complete example report for "project management software for small businesses".
Advanced Usage
- - Intent Mapping: INLINECODE9
- Seasonal Analysis: INLINECODE10
- Competitor Gap: INLINECODE11
- Local Keywords: INLINECODE12
Tips for Success
- 1. Start with seed keywords that describe your core offering
- Don't ignore long-tail - they often have highest conversion rates
- Match content to intent - informational queries need guides, not sales pages
- Group into clusters for topical authority
- Prioritize quick wins to build momentum and credibility
- Include GEO keywords in your strategy for AI visibility
- Review quarterly - keyword dynamics change over time
Save Results
After delivering findings to the user, ask:
"Save these results for future sessions?"
If yes, write a dated summary to memory/research/keyword-research/YYYY-MM-DD-<topic>.md containing:
- - One-line headline finding
- Top 3-5 actionable items
- Open loops or blockers
- Source data references
If any findings should influence ongoing strategy, recommend promoting key conclusions to memory/hot-cache.md.
Reference Materials
Next Best Skill
Related Skills in This Suite
seo-content-writer,
geo-content-optimizer,
meta-tags-optimizer,
schema-markup-generator |
|
Optimize |
on-page-seo-auditor,
technical-seo-checker,
internal-linking-optimizer,
content-refresher |
|
Monitor |
rank-tracker,
backlink-analyzer,
performance-reporter,
alert-manager |
|
Cross-cutting |
content-quality-auditor,
domain-authority-auditor,
entity-optimizer,
memory-management |
Install the full suite: See README for one-command install of all 20 skills.
关键词研究
自动发现高流量、低竞争关键词 — 为这项技能提供一个主题,它将返回一个按搜索量、难度评分、意图分类和即用型主题集群排序的优先级列表。停止猜测该写什么;开始为你的受众实际搜索的术语排名。
快速示例:研究非营利组织项目管理软件的关键词 → 获得30多个按投资回报率评分的机会,分组为支柱+集群内容,并包含可触发AI回答的GEO关键词。
系统角色:研究层技能。它将市场信号转化为可重复使用的战略输入,供库中其他技能使用。
属于 SEO & GEO 技能库 · 20项技能 · ClawHub · skills.sh
何时必须触发
当对话涉及以下任何情况时使用此技能 — 即使使用者未使用SEO术语:
当任务需要可重复使用的市场情报来影响战略,而不仅仅是临时答案时,请使用此技能。
- - 启动新的内容策略或活动
- 扩展到新的主题或市场
- 为特定产品或服务寻找关键词
- 识别长尾关键词机会
- 了解所在行业的搜索意图
- 规划内容日历
- 研究用于GEO优化的关键词
此技能的功能
- 1. 关键词发现:从种子词生成全面的关键词列表
- 意图分类:按用户意图对关键词进行分类(信息型、导航型、商业型、交易型)
- 难度评估:评估竞争水平和排名难度
- 机会评分:按潜在投资回报率对关键词进行优先级排序
- 聚类:将相关关键词分组为主题集群
- GEO相关性:识别可能触发AI响应的关键词
快速开始
从以下提示之一开始。使用技能合约中的仓库格式,以简短的交割摘要结束。
基础关键词研究
研究 [主题/产品/服务] 的关键词
为面向 [受众] 的 [行业] 企业寻找关键词机会
带特定目标
寻找 [主题] 具有商业意图的低竞争关键词
识别 [主题] 中AI系统可能回答的基于问题的关键词
竞争研究
[竞争对手URL] 正在排名的哪些关键词是我应该瞄准的?
技能合约
预期输出:一份优先级研究简报、有证据支持的发现,以及一份准备存入 memory/research/ 的简短交割摘要。
- - 读取:用户目标、目标市场输入、可用工具数据,以及来自 CLAUDE.md 和共享 状态模型 的先前策略(如可用)。
- 写入:面向用户的研究交付物,以及一份可存入 memory/research/ 的可重用摘要。
- 提升:将持久的关键词优先级、竞争对手事实、实体候选和战略决策提升到 CLAUDE.md、memory/decisions.md 和 memory/research/;将规范实体工作移交给 entity-optimizer。
- 下一步交接:当研究结果准备好驱动行动时,使用下面的下一个最佳技能。
数据来源
注意: 所有集成都是可选的。此技能无需任何API密钥即可工作 — 当没有连接工具时,用户手动提供数据。
工具类别占位符请参见 CONNECTORS.md。
连接了 ~~SEO工具 + ~~搜索控制台时:
自动拉取历史搜索量数据、关键词难度评分、SERP分析、来自 ~~搜索控制台的当前排名,以及竞争对手关键词重叠。该技能将获取种子关键词指标、相关关键词建议和搜索趋势数据。
仅使用手动数据时:
要求用户提供:
- 1. 种子关键词或主题描述
- 目标受众和地理位置
- 业务目标(流量、线索、销售)
- 当前域名权威(如已知)或网站年龄
- 任何已知的关键词表现数据或搜索量估算
使用提供的数据进行完整分析。在输出中注明哪些指标来自自动收集,哪些来自用户提供的数据。
指令
当用户请求关键词研究时:
在每个阶段开始时,宣布:[阶段 X/8:名称] 以便用户跟踪进度。
阶段 1/8:范围界定
如未提供,提出澄清性问题:
- 您的产品/服务/主题是什么?
- 您的目标受众是谁?
- 您的业务目标是什么?(流量、线索、销售)
- 您当前的域名权威如何?(新站、成熟站等)
- 是否有特定的地理定位?
- 首选语言?
阶段 2/8:发现
从以下开始:
- 核心产品/服务术语
- 问题导向的关键词(您解决什么问题?)
- 解决方案导向的关键词(您如何提供帮助?)
- 受众特定术语
- 行业术语
阶段 3/8:变体
为每个种子关键词生成变体:
markdown
## 关键词扩展模式
### 修饰词
- 最佳 [关键词]
- 顶级 [关键词]
- 面向 [受众] 的 [关键词]
- 我附近的 [关键词]
- [关键词] [年份]
- 如何 [关键词]
- 什么是 [关键词]
- [关键词] 对比 [替代方案]
- [关键词] 示例
- [关键词] 工具
### 长尾变体
- 面向初学者的 [关键词]
- 面向小企业的 [关键词]
- 免费 [关键词]
- [关键词] 软件/工具/服务
- [关键词] 模板
- [关键词] 清单
- [关键词] 指南
阶段 4/8:分类
对每个关键词进行分类:
| 意图 | 信号词 | 示例 | 内容类型 |
|--------|---------|---------|--------------|
| 信息型 | 什么、如何、为什么、指南、学习 | 什么是SEO | 博客文章、指南 |
| 导航型 | 品牌名称、特定网站 | 谷歌分析登录 | 首页、产品页 |
| 商业型 | 最佳、评价、对比、比较 | 最佳SEO工具 [当前年份] | 对比文章、评价 |
| 交易型 | 购买、价格、折扣、订购 | 购买SEO软件 | 产品页、定价页 |
阶段 5/8:评分
对每个关键词进行评分(1-100分制):
markdown
### 难度因素
高难度(70-100)
- 主要品牌排名
- 高域名权威竞争对手
- 成熟内容(1000+反向链接)
- 付费广告主导SERP
中等难度(40-69)
- 权威网站与利基网站混合
- 优质内容有一定机会
- 中等反向链接要求
低难度(1-39)
- 权威竞争对手少
- 排名内容单薄或过时
- 长尾变体
- 新兴主题
机会评分
公式:机会 = (搜索量 × 意图价值) / 难度
意图价值 按搜索意图分配数值权重:
- 信息型 = 1
- 导航型 = 1
- 商业型 = 2
- 交易型 = 3
markdown
### 机会矩阵
| 场景 | 搜索量 | 难度 | 意图 | 优先级 |
|----------|--------|------------|--------|----------|
| 速赢 | 低-中 | 低 | 高 | ⭐⭐⭐⭐⭐ |
| 增长 | 高 | 中 | 高 | ⭐⭐⭐⭐ |
| 长期 | 高 | 高 | 高 | ⭐⭐⭐ |
| 研究 | 低 | 低 | 低 | ⭐⭐ |
阶段 6/8:GEO检查 — AI回答重叠
可能触发AI响应的关键词:
markdown
### GEO相关关键词
高GEO潜力
- 问题格式:什么是...、如何...、为什么...
- 定义查询:[术语] 含义、[术语] 定义
- 对比查询: