Keyword Research
Discovers, scores, and clusters keywords for SEO and GEO planning.
Quick Start
Research keywords for [topic/product/service]
What keywords is [competitor URL] ranking for that I should target?
Skill Contract
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.
Handoff Summary
Emit the standard shape from skill-contract.md §Handoff Summary Format.
Data Sources
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.
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.
Instructions
When a user requests keyword research, run eight phases and announce each as [Phase X/8: Name]:
- Scope — clarify product, audience, business goal, DR, geography, and language.
- Discover — seed from core, problem, solution, audience, and industry terms.
- Variations — expand with modifiers and long-tail patterns.
- Classify — tag by intent (informational, navigational, commercial, transactional).
- Score — assign difficulty (1-100) and compute
Opportunity = (Volume × Intent Value) / Difficulty, with Intent Value 1 / 1 / 2 / 3.
- GEO-Check — flag AI-answer-friendly queries such as questions, definitions, comparisons, lists, and how-tos.
- Cluster — group keywords into pillar + cluster topic hubs.
- 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.
Impact × Confidence lens (optional, layers onto Phase 5)
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.
Example
See references/example-report.md for a full worked sample.
Save Results
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.
Reference Materials
- 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
Next Best Skill
Primary: competitor-analysis. Also: content-gap-analysis and serp-analysis.
1---2name: keyword-research-123description: Use when the user asks to "find keywords", "挖词", or "搜什么词"; prioritizes search volume, keyword difficulty, intent, and topic clusters from provided or connected data. Not for competitor-relative coverage gaps — use content-gap-analysis. 关键词研究/内容选题4license: Apache-2.05---6
7# Keyword Research
8
9Discovers, scores, and clusters keywords for SEO and GEO planning.
10
11## Quick Start
12
13```
14Research keywords for [topic/product/service]
15```
16
17```
18What keywords is [competitor URL] ranking for that I should target?
19```
20
21## Skill Contract
22
23**Expected output**: a prioritized keyword brief plus the standard handoff summary for `memory/research/`.
24
25- **Reads**: topic or seed keyword, target market/language, business goal, site DR, and any user-provided or tool metrics.
26- **Writes**: a user-facing research deliverable and reusable summary.
27- **Promotes**: durable keyword priorities, competitor facts, and pending strategy decisions to `memory/hot-cache.md`, `memory/open-loops.md`, and `memory/research/`.
28- **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.
29- **Primary next skill**: [competitor-analysis](../competitor-analysis/SKILL.md) when the keyword set is ready for market comparison.
30
31### Handoff Summary
32
33> Emit the standard shape from [skill-contract.md §Handoff Summary Format](../../../references/skill-contract.md).
34
35## Data Sources
36
37Optional integrations: ~~SEO tool, ~~search console. Without tools, ask for seed keywords, audience, goals, and any known metrics. See [CONNECTORS.md](../../../CONNECTORS.md).
38
39**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](../../../scripts/connectors/README.md).
40
41**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**.
42
43## Instructions
44
45When a user requests keyword research, run eight phases and announce each as `[Phase X/8: Name]`:
46
471. **Scope** — clarify product, audience, business goal, DR, geography, and language.
482. **Discover** — seed from core, problem, solution, audience, and industry terms.
493. **Variations** — expand with modifiers and long-tail patterns.
504. **Classify** — tag by intent (informational, navigational, commercial, transactional).
515. **Score** — assign difficulty (1-100) and compute `Opportunity = (Volume × Intent Value) / Difficulty`, with Intent Value `1 / 1 / 2 / 3`.
526. **GEO-Check** — flag AI-answer-friendly queries such as questions, definitions, comparisons, lists, and how-tos.
537. **Cluster** — group keywords into pillar + cluster topic hubs.
548. **Deliver** — output an Executive Summary, Quick Wins / Growth / GEO opportunities, Topic Clusters, Content Calendar, and Next Steps.
55
56Label 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.
57
58### Impact × Confidence lens (optional, layers onto Phase 5)
59
60When you have richer signals than volume/difficulty alone, add a second pass on top of the `Opportunity` score:
61
62- **Impact** = volume + CPC + funnel stage + trend direction (how much winning the term is worth).
63- **Confidence** = difficulty + current ranking position + topic authority (how likely you are to win it).
64- **Priority = Impact × Confidence** — surfaces terms that are both valuable *and* winnable, not just high-volume.
65
66Tag each keyword by funnel stage from its pattern:
67
68- **BOFU** — commercial/transactional, or contains "pricing", "best", "vs", "services", "agency", "hire", "buy".
69- **MOFU** — informational with buying signals: "how to", "guide", "roi", "case study", "review".
70- **TOFU** — pure informational (definitions, broad questions).
71
72Work 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.)
73
74**Quality bar**: every recommendation includes at least one specific number. Rewrite generic advice into a concrete keyword + volume + difficulty + reason.
75
76> **Reference**: See [references/instructions-detail.md](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.
77
78## Example
79
80See [references/example-report.md](references/example-report.md) for a full worked sample.
81
82## Save Results
83
84Write path: `memory/research/keyword-research/YYYY-MM-DD-<topic>.md`; promote durable keyword priorities to `memory/hot-cache.md`. See [Skill Contract](../../../references/skill-contract.md) §Save Results Template.
85
86## Reference Materials
87
88- [Instructions Detail](references/instructions-detail.md) — Workflow, scoring, cluster template, advanced usage
89- [Keyword Intent Taxonomy](references/keyword-intent-taxonomy.md) — Intent signals and content mapping
90- [Topic Cluster Templates](references/topic-cluster-templates.md) — Pillar and cluster patterns
91- [Keyword Prioritization Framework](references/keyword-prioritization-framework.md) — Scoring and prioritization rules
92- [Example Report](references/example-report.md) — Worked sample
93
94## Next Best Skill
95
96Primary: [competitor-analysis](../competitor-analysis/SKILL.md). Also: [content-gap-analysis](../content-gap-analysis/SKILL.md) and [serp-analysis](../serp-analysis/SKILL.md).
majiayu000