Skip to content

rampstackco/claude-skills / skills/seo-keyword

seo-keyword

Verified

Run keyword research, classify by search intent, cluster into topical groups, and prioritize for content production. Use this skill whenever the user asks to do keyword research, find target keywords, identify ranking opportunities, classify search intent, build a topical map, or plan a content strategy around what people search for. Triggers on keyword research, keyword strategy, search intent, keyword clustering, topic clusters, keyword difficulty, search volume, ranking opportunity, content gap, what should I write about, target keyword, primary keyword, secondary keyword, long-tail. Also triggers when planning a content calendar or new site without keywords yet defined.

FileKindSize
README.mdmarkdown352 B
SKILL.mdskill md7.8 KB
references/intent-classification-guide.mdmarkdown10.6 KB
references/keyword-research-template.mdmarkdown3.0 KB

references/keyword-research-template.md

View on GitHub
# Keyword Research: [Site or Topic Area]

**Date:** [YYYY-MM-DD]
**Scope:** [What this research covers]
**Audience:** [Who we are writing for]
**Tools used:** [Which keyword tools were used]

---

## Summary

**Total keywords analyzed:** [N]
**Clusters identified:** [N]
**Priority clusters (top 20%):** [N]

[2 to 3 sentence overview. The headline themes, the surprising finds, the strategic priorities.]

---

## Top priority clusters

The following clusters scored highest on opportunity, strategic fit, and reasonable difficulty. Produce these first.

### Cluster 1: [Cluster name]
- **Primary keyword:** [keyword] (volume: X, difficulty: Y)
- **Intent:** [Informational / Commercial / Transactional / Navigational]
- **Recommended page type:** [Article / guide / comparison / product page / category]
- **Secondary keywords:** [list 5 to 15]
- **Suggested URL:** [/proposed-slug]
- **Estimated effort:** [Hours or days]
- **Why this cluster:** [1 to 2 sentences on strategic fit]

### Cluster 2: [Cluster name]
- **Primary keyword:**
- **Intent:**
- **Recommended page type:**
- **Secondary keywords:**
- **Suggested URL:**
- **Estimated effort:**
- **Why this cluster:**

[Continue for top 10 to 20 clusters.]

---

## Full keyword sheet

[Link to or attach the spreadsheet.]

Columns:
1. Keyword
2. Volume
3. Difficulty
4. Intent (I/N/C/T)
5. SERP features (featured snippet, AI overview, PAA, video, image, local pack)
6. Cluster
7. Cluster role (primary / secondary / long-tail)
8. Opportunity score (1-5)
9. Strategic fit (1-5)
10. Priority (composite)
11. Notes

---

## Topic map

A visual or hierarchical view of how the clusters relate. This becomes the basis for internal linking and information architecture.

```
[Top-level topic]
  ├── [Cluster A]
  │   ├── Primary: [keyword]
  │   └── Subtopics: [keywords]
  ├── [Cluster B]
  │   ├── Primary: [keyword]
  │   └── Subtopics: [keywords]
  └── [Cluster C]
      └── ...
```

---

## Quick wins

Existing pages that already rank on page 2 or low page 1 for high-value keywords. Optimizing these is faster than producing new content.

| URL | Current rank | Target query | Volume | Recommended action |
|---|---|---|---|---|
| | | | | |
| | | | | |

(Pull from search console: queries with average position 5 to 20 and impressions over 100/month.)

---

## Deferred clusters

Clusters that did not make the priority cut and why.

| Cluster | Reason |
|---|---|
| [Cluster name] | Too competitive for current authority |
| [Cluster name] | Low commercial value |
| [Cluster name] | Audience mismatch |
| [Cluster name] | Better suited for paid acquisition |

---

## Refresh schedule

This research should be revisited:
- **Quarterly** for fast-moving topics (tech, news, trends, finance)
- **Annually** for evergreen topics
- **After any major SERP feature change** (e.g., AI overviews appearing on key queries)
- **After authority increases** that unlock harder keywords (e.g., domain rating going up by 10+ points)
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall