Back to Details

keyword-research

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Keyword Research

关键词研究

Discovers, scores, and clusters keywords for SEO and GEO planning.
为SEO和GEO规划发现、评分并聚类关键词。

Quick Start

快速开始

Research keywords for [topic/product/service]
What keywords is [competitor URL] ranking for that I should target?
为[主题/产品/服务]研究关键词
[竞争对手URL]正在排名哪些我应该瞄准的关键词？

Skill Contract

技能协议

Expected output: a prioritized keyword brief plus the standard handoff summary for 
memory/research/
.
  • Reads: topic or seed keyword, target market/language, business goal, site DR, and any user-provided or tool metrics.
  • Writes: a user-facing research deliverable and reusable summary.
  • Promotes: durable keyword priorities, competitor facts, and pending strategy decisions to 
    memory/hot-cache.md
    , 
    memory/open-loops.md
    , and 
    memory/research/
    .
  • Done when: every shortlisted keyword carries volume + difficulty + intent (or a labeled N/A); keywords are grouped into pillar + cluster hubs; and the deliverable names at least 3 prioritized Quick Win / Growth / GEO opportunities.
  • Primary next skill: competitor-analysis when the keyword set is ready for market comparison.
预期输出：一份优先级排序的关键词简报，加上
memory/research/
的标准交接摘要。
  • 读取：主题或种子关键词、目标市场/语言、业务目标、网站DR，以及任何用户提供或工具生成的指标。
  • 写入：面向用户的研究交付成果和可复用摘要。
  • 推送：将持久的关键词优先级、竞品信息和待处理的战略决策推送到
    memory/hot-cache.md
    、
    memory/open-loops.md
    和
    memory/research/
    。
  • 完成标志：每个入围关键词都带有搜索量+难度+意图（或标记为N/A）；关键词被分组为核心主题+集群主题；交付成果至少列出3个优先级排序的快速获胜/增长/GEO机会。
  • 主要后续技能：当关键词集准备好进行市场对比时，使用competitor-analysis。

Handoff Summary

交接摘要

Emit the standard shape from skill-contract.md §Handoff Summary Format.
输出skill-contract.md §Handoff Summary Format中的标准格式内容。

Data Sources

数据源

Optional integrations: ~~SEO tool, ~~search console. Without tools, ask for seed keywords, audience, goals, and any known metrics. See CONNECTORS.md.
Zero-dependency local helper (no tool needed): 
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/connectors/suggest.py" "<seed>" --expand
harvests free keyword ideas from Google Autocomplete (⚠️ unofficial endpoint). Search volume / difficulty still needs 
~~SEO tool
or own Search Console data. See scripts/connectors/README.md.
Keyless live-SERP sampling: 
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/connectors/firecrawl.py" search "<candidate keyword>" --limit 10
(Firecrawl keyless free tier, ~1,000 credits/mo, no key needed) shows who actually ranks for a candidate — feed the top-10 domains and formats into the intent check and the difficulty read as Measured evidence instead of guessing. Volume still needs 
~~SEO tool
or GSC.
Keyless topic-demand proxy: 
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/connectors/pageviews.py" "<Topic_Article>" --months 12
returns a topic's real Wikipedia-attention series — Measured direction and seasonality evidence when no volume tool is connected. It is attention, not search volume: use it to rank topics against each other and time them, never to quote a volume number.
Striking-distance shortcut (when 
~~search console
is connected): before broad discovery, mine your own GSC query data for terms already ranking in positions ~5–20 — page-one tail and page two. These are proven demand a small push can convert, so they are the fastest opportunity set. The Search Analytics API sorts by clicks and has no position filter, so request a high 
rowLimit
and filter the 5–20 window client-side, then attach volume / difficulty / intent to that shortlist. Work this set first; treat its metrics as Measured.
可选集成：~~SEO工具、~~搜索控制台。若无工具，需询问种子关键词、受众、目标以及任何已知指标。详见CONNECTORS.md。
零依赖本地辅助工具（无需外部工具）：
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/connectors/suggest.py" "<seed>" --expand
从Google Autocomplete（⚠️非官方端点）获取免费关键词灵感。搜索量/难度仍需
~~SEO工具
或自有Search Console数据。详见scripts/connectors/README.md。
无密钥实时SERP采样：
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/connectors/firecrawl.py" search "<candidate keyword>" --limit 10
（Firecrawl无密钥免费层级，约1000积分/月，无需密钥）显示候选关键词的实际排名网站——将前10个域名和格式用于意图检查，并将难度读取为实测证据而非猜测。搜索量仍需
~~SEO工具
或GSC。
无密钥主题需求代理：
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/connectors/pageviews.py" "<Topic_Article>" --months 12
返回主题的维基百科真实关注度数据——当无搜索量工具连接时，可作为实测趋势和季节性证据。这是关注度，而非搜索量：用于主题间排名和时间规划，切勿引用为搜索量数值。
近在咫尺的捷径（当连接
~~search console
时）：在广泛发现之前，挖掘自有GSC查询数据中排名在~5–20位的关键词——即第一页尾部和第二页的关键词。这些是已被验证有需求的关键词，只需小幅推动即可转化，是最快的机会集合。Search Analytics API按点击量排序且无位置筛选，因此需请求较高的
rowLimit
并在客户端筛选5–20位的关键词，然后为该入围列表添加搜索量/难度/意图。优先处理此集合；将其指标视为实测。

Instructions

操作说明

When a user requests keyword research, run eight phases and announce each as 
[Phase X/8: Name]
:
  1. Scope — clarify product, audience, business goal, DR, geography, and language.
  2. Discover — seed from core, problem, solution, audience, and industry terms.
  3. Variations — expand with modifiers and long-tail patterns.
  4. Classify — tag by intent (informational, navigational, commercial, transactional).
  5. Score — assign difficulty (1-100) and compute 
    Opportunity = (Volume × Intent Value) / Difficulty
    , with Intent Value 
    1 / 1 / 2 / 3
    .
  6. GEO-Check — flag AI-answer-friendly queries such as questions, definitions, comparisons, lists, and how-tos.
  7. Cluster — group keywords into pillar + cluster topic hubs.
  8. Deliver — output an Executive Summary, Quick Wins / Growth / GEO opportunities, Topic Clusters, Content Calendar, and Next Steps.
Label every metric Measured (tool/export), User-provided, or Estimated (model inference); never present an estimate as measured; if a required metric is unavailable, mark it N/A — do not invent it.
当用户请求关键词研究时，执行八个阶段，并以
[第X/8阶段：名称]
的形式宣布每个阶段：
  1. 范围界定——明确产品、受众、业务目标、DR、地域和语言。
  2. 关键词发现——从核心术语、问题术语、解决方案术语、受众术语和行业术语中生成种子关键词。
  3. 变体扩展——使用修饰词和长尾模式扩展关键词。
  4. 意图分类——按意图标记关键词（信息型、导航型、商业型、交易型）。
  5. 评分排序——分配难度值（1-100）并计算
    机会值 = (搜索量 × 意图权重) / 难度
    ，其中意图权重为
    1 / 1 / 2 / 3
    （对应上述四种意图）。
  6. GEO适配检查——标记适合AI回答的查询，如问题、定义、对比、列表和教程类查询。
  7. 主题聚类——将关键词分组为核心主题+集群主题中心。
  8. 成果交付——输出执行摘要、快速获胜/增长/GEO机会、主题集群、内容日历和后续步骤。
为每个指标标记实测（工具/导出数据）、用户提供或估算（模型推断）；切勿将估算值呈现为实测值；若所需指标不可用，标记为N/A——不得编造数据。

Impact × Confidence lens (optional, layers onto Phase 5)

影响力×置信度视角（可选，叠加在第5阶段之上）

When you have richer signals than volume/difficulty alone, add a second pass on top of the 
Opportunity
score:
  • Impact = volume + CPC + funnel stage + trend direction (how much winning the term is worth).
  • Confidence = difficulty + current ranking position + topic authority (how likely you are to win it).
  • Priority = Impact × Confidence — surfaces terms that are both valuable and winnable, not just high-volume.
Tag each keyword by funnel stage from its pattern:
  • BOFU — commercial/transactional, or contains "pricing", "best", "vs", "services", "agency", "hire", "buy".
  • MOFU — informational with buying signals: "how to", "guide", "roi", "case study", "review".
  • TOFU — pure informational (definitions, broad questions).
Work BOFU first when revenue is the goal; use TOFU/MOFU for reach and GEO answer coverage. (Impact×Confidence + funnel-stage scoring adapted from an external SEO-ops competitive analysis.)
Quality bar: every recommendation includes at least one specific number. Rewrite generic advice into a concrete keyword + volume + difficulty + reason.
Reference: See references/instructions-detail.md for the full 8-phase templates, expansion patterns, intent table, difficulty tiers, opportunity matrix, GEO indicators, cluster template, actionable-vs-generic examples, and advanced usage.
当拥有比搜索量/难度更丰富的信号时，在
机会值
评分之上添加第二轮评估：
  • 影响力 = 搜索量 + CPC + 漏斗阶段 + 趋势方向（赢得该关键词的价值）。
  • 置信度 = 难度 + 当前排名位置 + 主题权威性（赢得该关键词的可能性）。
  • 优先级 = 影响力 × 置信度——筛选出既有价值又有可能获胜的关键词，而非仅高搜索量的关键词。
根据关键词模式标记其漏斗阶段：
  • BOFU——商业/交易型，或包含“pricing”“best”“vs”“services”“agency”“hire”“buy”等词汇。
  • MOFU——带有购买信号的信息型：“how to”“guide”“roi”“case study”“review”等。
  • TOFU——纯信息型（定义、宽泛问题）。
当以营收为目标时优先处理BOFU；使用TOFU/MOFU扩大覆盖范围和GEO答案覆盖。（影响力×置信度+漏斗阶段评分改编自外部SEO运营竞品分析。）
质量标准：每条建议至少包含一个具体数值。将通用建议改写为具体的关键词+搜索量+难度+理由。
参考：详见references/instructions-detail.md获取完整的8阶段模板、扩展模式、意图表、难度层级、机会矩阵、GEO指标、聚类模板、可操作vs通用示例以及高级用法。

Example

示例

See references/example-report.md for a full worked sample.
详见references/example-report.md获取完整的工作示例。

Save Results

保存结果

Write path: 
memory/research/keyword-research/YYYY-MM-DD-<topic>.md
; promote durable keyword priorities to 
memory/hot-cache.md
. See Skill Contract §Save Results Template.
写入路径：
memory/research/keyword-research/YYYY-MM-DD-<topic>.md
；将持久的关键词优先级推送到
memory/hot-cache.md
。详见技能协议 §保存结果模板。

Reference Materials

参考资料

  • Instructions Detail — Workflow, scoring, cluster template, advanced usage
  • Keyword Intent Taxonomy — Intent signals and content mapping
  • Topic Cluster Templates — Pillar and cluster patterns
  • Keyword Prioritization Framework — Scoring and prioritization rules
  • Example Report — Worked sample
  • 操作说明详情——工作流、评分、聚类模板、高级用法
  • 关键词意图分类——意图信号和内容映射
  • 主题聚类模板——核心主题和集群模式
  • 关键词优先级框架——评分和优先级规则
  • 示例报告——工作示例

Next Best Skill

推荐后续技能

Primary: competitor-analysis. Also: content-gap-analysis and serp-analysis.
主要：competitor-analysis。此外：content-gap-analysis和serp-analysis。