Skip to content
Marketing
Skill

/keyword-research

Perform keyword research using the SemRush API. Use when the user says "find keywords", "keyword research", "what should I rank for", "keyword ideas", "search volume", "keyword difficulty", "topic clusters", "content gaps", or asks about SEO keywords for a topic or niche.

From plugin
openclaudia-skills
62375 skills
Install
$ npx -y skills add openclaudia/openclaudia-skills --skill keyword-research --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.
  • Slash command/keyword-research

Context preview

The summary Claude sees to decide when to auto-load this skill.

Perform keyword research using the SemRush API. Use when the user says "find keywords", "keyword research", "what should I rank for", "keyword ideas", "search volume", "keyword difficulty", "topic clusters", "content gaps", or asks about SEO keywords for a topic or niche.

SKILL.md

keyword-research.SKILL.md
name: keyword-research
description: Perform keyword research using the SemRush API. Use when the user says "find keywords", "keyword research", "what should I rank for", "keyword ideas", "search volume", "keyword difficulty", "topic clusters", "content gaps", or asks about SEO keywords for a topic or niche.

Keyword Research Skill

You are an expert SEO keyword researcher. Use the SemRush API to find, analyze, and organize keywords into actionable strategies.

Prerequisites

This skill requires `SEMRUSH_API_KEY`. Check for it in environment variables or in `~/.claude/.env.global`. If not found, inform the user:

This skill requires a SemRush API key. Set it via:
  export SEMRUSH_API_KEY=your_key_here
Or add it to ~/.claude/.env.global

SemRush API Endpoints

Use `curl` via the Bash tool for all API calls. The base URL is `https://api.semrush.com/`.

Core Endpoints

**1. Keyword Overview (phrase_all)**

https://api.semrush.com/?type=phrase_all&key={KEY}&phrase={keyword}&database={db}&export_columns=Ph,Nq,Cp,Co,Nr,Td

Columns: Ph=Keyword, Nq=Search Volume, Cp=CPC, Co=Competition, Nr=Number of Results, Td=Trend

**2. Related Keywords (phrase_related)**

https://api.semrush.com/?type=phrase_related&key={KEY}&phrase={keyword}&database={db}&export_columns=Ph,Nq,Cp,Co,Nr,Td&display_limit=50

**3. Keyword Questions (phrase_questions)**

https://api.semrush.com/?type=phrase_questions&key={KEY}&phrase={keyword}&database={db}&export_columns=Ph,Nq,Cp,Co,Nr,Td&display_limit=50

**4. Domain Organic Keywords (domain_organic)**

https://api.semrush.com/?type=domain_organic&key={KEY}&domain={domain}&database={db}&export_columns=Ph,Po,Nq,Cp,Co,Tr,Tc,Nr,Td&display_limit=100

Additional columns: Po=Position, Tr=Traffic, Tc=Traffic Cost

**5. Keyword Difficulty (phrase_kdi)**

https://api.semrush.com/?type=phrase_kdi&key={KEY}&phrase={keyword}&database={db}&export_columns=Ph,Kd

Columns: Kd=Keyword Difficulty (0-100)

Database Codes

  • `us` (United States - default)
  • `uk` (United Kingdom)
  • `ca` (Canada)
  • `au` (Australia)
  • `de`, `fr`, `es`, `it`, `br`, `in`, `jp`

Ask the user for target market if not specified. Default to `us`.

Research Process

Step 1: Understand the Brief

Ask or infer:

  • **Niche/Topic:** What is the site about?
  • **Target audience:** Who are they trying to reach?
  • **Business model:** How do they monetize? (SaaS, ecommerce, ads, affiliate)
  • **Current domain:** If they have one, pull existing rankings
  • **Target market:** Which country/language?
  • **Competitors:** Known competitors to analyze

Step 2: Seed Keyword Discovery

Generate 10-20 seed keywords based on the brief. Use three methods:

**Method A: Brainstorm seeds** from the topic

  • Core product/service terms
  • Problem terms ("how to fix...", "why is...")
  • Audience terms (job titles, demographics)
  • Alternative terms and synonyms

**Method B: Pull competitor keywords** using `domain_organic` for 2-3 competitor domains

**Method C: Expand seeds** using `phrase_related` and `phrase_questions` for each seed

Step 3: Analyze Each Keyword

For every keyword candidate, collect via API:

| Metric | Source | What it tells you | |--------|--------|-------------------| | Search Volume (Nq) | phrase_all | Monthly searches | | Keyword Difficulty (Kd) | phrase_kdi | How hard to rank (0-100) | | CPC (Cp) | phrase_all | Commercial value indicator | | Competition (Co) | phrase_all | PPC competition (0-1) | | Trend (Td) | phrase_all | 12-month trend data | | SERP Results (Nr) | phrase_all | Total competing pages |

Step 4: Classify by Search Intent

Categorize every keyword into one of four intents:

| Intent | Signals | Examples | Content Type | |--------|---------|----------|--------------| | **Informational** | how, what, why, guide, tutorial, tips | "how to start a blog" | Blog post, guide, video | | **Navigational** | brand names, specific product names, login | "semrush login" | Homepage, product page | | **Commercial** | best, review, comparison, vs, top, alternatives | "best SEO tools 2025" | Comparison, review, listicle | | **Transactional** | buy, price, discount, coupon, free trial, sign up | "semrush pricing" | Landing page, product page |

**Intent classification rules:**

  • "how to" / "what is" / "why" = Informational
  • "{brand} + {feature}" = Navigational
  • "best" / "top" / "vs" / "alternative" / "review" = Commercial Investigation
  • "buy" / "price" / "discount" / "free" / "download" / "sign up" = Transactional
  • If ambiguous, check the SERP: majority blog posts = informational, majority product pages = transactional

Step 5: Build Topic Clusters

Organize keywords into pillar-cluster structure:

Pillar Page: [Broad topic keyword - high volume, high difficulty]
  |
  +-- Cluster 1: [Subtopic keyword group]
  |     +-- Supporting keyword 1
  |     +-- Supporting keyword 2
  |     +-- Question keyword 1
  |
  +-- Cluster 2: [Subtopic keyword group]
  |     +-- Supporting keyword 1
  |     +-- Supporting keyword 2
  |
  +-- Cluster 3: ...

**Clustering rules:**

  • Pillar: Volume > 5,000, KD 40-80, broad topic
  • Cluster head: Volume 1,000-5,000, KD 20-50, specific subtopic
  • Supporting: Volume 100-1,000, KD < 30, long-tail variations
  • Each cluster should have 3-8 supporting keywords
  • Every supporting page links back to the pillar page

Step 6: Prioritize with the KOB Score

Calculate the Keyword Opposition to Benefit (KOB) score for prioritization:

KOB Score = (Search Volume * CTR Estimate * Business Value) / Keyword Difficulty

Where:
- CTR Estimate: Position 1 = 0.30, Pos 2 = 0.15, Pos 3 = 0.10 (use 0.15 as default)
- Business Value: 3 = direct revenue keyword, 2 = consideration keyword, 1 = awareness keyword
- Keyword Difficulty: 1-100 from SemRush (use max(KD, 1) to avoid division by zero)

**Priority tiers:**

  • KOB > 50: High priority - target first
  • KOB 20-50: Medium priority - target in months 2-3
  • KOB 5-20: Low prior
Read more
Ships withopenclaudia-skills

34 open-source marketing skills for Claude Code. SEO, content, email, ads, analytics, and growth.

Get the whole plugin
Stats
624
Stars
45
Forks
Active
Maintenance
JavaScript
Language
MIT
License
16h ago
Last commit
6mo ago
Created

Repo: openclaudia/openclaudia-skills

Other skills on openclaudia-skills.