agentleFS
nisarthnisarth/claude-skills-store/skills/seo/seo-keywords/SKILL.md

seo-keywords

Skill1 starsChanged 7 months agoMITView on GitHub

Build a keyword plan with research ideas, competitor gap analysis, intent clustering, and URL mapping. Use when starting keyword research for a new site or section, finding content opportunities, analyzing competitor keywords, or building a content calendar. Trigger with "keyword research", "keyword plan", "find keywords for", or "competitor keyword gap".

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Modifier expansion: Add question words (how, what, why), qualifiers (best, top, free), and intent signals (buy, compare, review).

    line 34
  2. Distinctive:

    Competitor identification: Use SERP overlap to find true content competitors (not just business competitors).

    line 43
  3. Distinctive:

    Cannibalization check: Ensure existing pages do not already target the cluster.

    line 68
  4. Distinctive:

    Start with intent, not volume.

    line 133
  5. Distinctive:

    Check for cannibalization.

    line 135
  6. Distinctive:

    Use difficulty scores as relative guides, not absolute truths.

    line 136

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

SEO Keyword Plan

Build a keyword plan from seed topics: research keyword ideas, analyze competitor gaps, cluster by search intent, and map clusters to target URLs.

Workflow

Step 1: Seed Keyword Expansion

Generate a broad keyword list from the seed topic:

  • Seed variations: Synonyms, related terms, long-tail expansions.
  • Modifier expansion: Add question words (how, what, why), qualifiers (best, top, free), and intent signals (buy, compare, review).
  • Autocomplete mining: Capture Google autocomplete suggestions for the seed and key variations.
  • Related searches: Harvest related search suggestions from SERPs.
  • Existing rankings: Pull keywords the site already ranks for (positions 5-30 for quick wins).

Step 2: Competitor Gap Analysis

Identify keywords competitors rank for that the target site does not:

  • Competitor identification: Use SERP overlap to find true content competitors (not just business competitors).
  • Gap extraction: Keywords where competitors rank in the top 20 but the target site does not.
  • Shared keywords: Keywords both rank for where the competitor outranks the target.
  • Unique competitor content: Topics the competitor covers that the target site has no page for.
  • Opportunity sizing: Prioritize gaps by search volume and ranking difficulty.

Step 3: Intent Classification

Classify each keyword by search intent:

IntentSignalContent Type
Informationalhow, what, why, guide, tutorialBlog post, guide, documentation
Commercialbest, top, review, comparison, vsComparison page, review, listicle
Transactionalbuy, pricing, signup, demo, trialProduct page, pricing page, landing page
Navigationalbrand name, login, supportHomepage, support page

Step 4: Cluster Keywords

Group keywords into topically related clusters:

  • Primary keyword: The highest-volume keyword representing the cluster.
  • Supporting keywords: Semantically related terms to include in the same page.
  • Cluster size: Total combined search volume for the cluster.
  • Cluster intent: Dominant intent type within the group.
  • Cannibalization check: Ensure existing pages do not already target the cluster.

Step 5: Map to URLs

Assign each cluster to a target URL:

  • Existing pages: Map clusters to pages that already exist and can be optimized.
  • New pages needed: Identify clusters with no existing page to target.
  • Content calendar: Sequence new page creation by priority (volume, difficulty, business value).
  • Quick wins: Highlight pages ranking positions 5-20 that need minor optimization to improve.

Output Format

## Keyword Plan: <topic/domain>

**Total Keywords**: <count>
**Total Clusters**: <count>
**Estimated Opportunity**: <total monthly search volume>

### Keyword Clusters (ranked by priority)

#### Cluster 1: <primary keyword> (<intent>)
| Keyword | Volume | Difficulty | Current Rank |
|---------|--------|------------|-------------|
| <keyword> | <vol> | <score> | <rank or "not ranking"> |
| <keyword> | <vol> | <score> | <rank or "not ranking"> |

- **Target URL**: <existing URL or "new page needed">
- **Action**: <optimize existing / create new / no action>
- **Combined Volume**: <total>

#### Cluster 2: <primary keyword> (<intent>)
<same structure>

### Competitor Gap Summary
| Competitor | Unique Keywords | Top Gaps |
|-----------|----------------|----------|
| <domain> | <count> | <top 3 keyword gaps> |

### Quick Wins (positions 5-20, low difficulty)
| Keyword | Current Rank | Volume | Target URL | Action |
|---------|-------------|--------|------------|--------|
| <keyword> | <rank> | <vol> | <URL> | <specific optimization> |

### Content Calendar
| Priority | Cluster | Content Type | Target URL | Est. Publish |
|----------|---------|-------------|------------|-------------|
| 1 | <cluster> | <type> | <URL> | <date> |
| 2 | <cluster> | <type> | <URL> | <date> |

Examples

User: "Keyword research for a project management SaaS" Action: Expand seed keywords around project management, analyze competitors like Asana and Monday, cluster by intent, map to site pages.

User: "Find keyword gaps vs. competitor.com" Action: Pull competitor's ranking keywords, compare with the user's site, identify high-value gaps, cluster opportunities.

User: "Build a keyword plan for our blog targeting small business owners" Action: Focus on informational and commercial intent keywords, emphasize long-tail queries, prioritize by volume and difficulty.

Best Practices

  • Start with intent, not volume. A 500-volume transactional keyword often outperforms a 10,000-volume informational one for revenue.
  • Cluster keywords before mapping. One page should target a cluster, not a single keyword.
  • Check for cannibalization. If two existing pages target the same cluster, consolidate or differentiate.
  • Use difficulty scores as relative guides, not absolute truths. They vary by tool and methodology.
  • Prioritize quick wins for early momentum: pages already ranking 5-20 with minor optimization needed.
  • Validate search volume data with multiple sources. Single-tool estimates can be misleading.
  • Include branded keywords in the analysis but separate them from non-branded opportunities.
  • Revisit the keyword plan quarterly. Search trends, competitor content, and site authority change over time.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.