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.
What this skill does
# 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 priority - target later
- KOB < 5: Deprioritize unless strategically important
### Step 7: Find Content Gaps
Compare the user's domain against competitors:
1. Pull top 100 keywords for each competitor via `domain_organic`
2. Identify keywords where competitors rank but user does not
3. Filter for keywords with KOB > 20
4. These are content gap opportunities
## Output Format
Present results in this structure:
```markdown
# Keyword Research Report: {Topic/Niche}
**Date:** {date}
**Target Market:** {country}
**Total Keywords Found:** {count}
**Total Monthly Search Volume:** {sum}
## Top 20 Keywords by KOB Score
| # | Keyword | Volume | KD | CPC | Intent | KOB Score |
|---|---------|--------|-----|-----|--------|-----------|
| 1 | {keyword} | {vol} | {kd} | ${cpc} | {intent} | {kob} |
| ... | ... | ... | ... | ... | ... | ... |
## Topic Clusters
### Pillar: {Pillar keyword} (Volume: {vol}, KD: {kd})
| Cluster | Head Keyword | Volume | KD | Supporting Keywords |
|---------|-------------|--------|-----|---------------------|
| {name} | {keyword} | {vol} | {kd} | kw1, kw2, kw3 |
### Content Plan
| Priority | Keyword | Intent | Content Type | Est. Monthly Traffic |
|----------|---------|--------|-------------|---------------------|
| 1 | {keyword} | {intent} | {type} | {vol * 0.15} |
| ... | ... | ... | ... | ... |
## Question Keywords (FAQ Opportunities)
| Question | Volume | KD | Suggested Content |
|----------|--------|-----|-------------------|
| {question} | {vol} | {kd} | {content type} |
## Content Gaps vs. Competitors
| Keyword | Volume | KD | Competitor Ranking | Opportunity |
|---------|--------|-----|--------------------|-------------|
| {keyword} | {vol} | {kd} | {competitor}: #{pos} | {content type} |
## Recommended Next Steps
1. {Specific action item with keyword target}
2. ...
```
## Tips for Better Results
- **Batch API calls** to conserve API credits. Query related keywords in groups.
- **Always check trends.** A keyword with declining volume may not be worth targeting.
- **CPC indicates money intent.** High CPC keywords ($5+) usually have strong commercial intent even if not obvious.
- **Low KD is not always easy.** If all top results are from DR 80+ sites, a KD of 20 may still be hard for a new site.
- **Local vs. national.** For local businesses, apRelated in Ads & Marketing
ads
IncludedMulti-platform paid advertising audit and optimization skill. Analyzes Google, Meta, YouTube, LinkedIn, TikTok, Microsoft, and Apple Ads. 250+ checks with scoring, parallel agents, industry templates, and AI creative generation.
banana
IncludedAI image generation Creative Director powered by Google Gemini Nano Banana models. Use this skill for ANY request involving image creation, editing, visual asset production, or creative direction. Triggers on: generate an image, create a photo, edit this picture, design a logo, make a banner, visual for my anything, and all /banana commands. Handles text-to-image, image editing, multi-turn creative sessions, batch workflows, and brand presets.
rpg-migration-analyzer
IncludedAnalyzes legacy RPG (Report Program Generator) programs from AS/400 and IBM i systems for migration to modern Java applications. Extracts business logic from RPG III/IV/ILE source code, identifies data structures (D-specs), file operations (F-specs), program dependencies (CALLB/CALLP), and converts RPG constructs to Java equivalents. Generates migration reports, complexity estimates, and Java implementation strategies with POJO classes, JPA entities, and service methods. Use when modernizing AS/400 or IBM i legacy systems, analyzing RPG source files (.rpg, .rpgle, .RPGLE), converting RPG to Java, mapping data specifications to Java classes, planning legacy system migration, or when user mentions RPG analysis, Report Program Generator, RPG III/IV/ILE, AS/400 modernization, IBM i migration, packed decimal conversion, or mainframe application rewrite.
brand-library-architect
IncludedBuild a complete brand library for a product — visual asset render pipeline, brand documentation set (BRAND, COPY, MANIFESTO, BIOS, FAQ, GLOSSARY, TONE, PRICING), open-source convention files (README, CONTRIBUTING, SECURITY, CODE_OF_CONDUCT), and a self-contained press kit. This skill should be used when the user asks to "build a brand library / brand kit / press kit / brand assets" for a product, "set up a brand library workflow," "create a positioning manifesto plus visual identity," or any combination of brand documentation + visual asset pipeline. Apply phase-by-phase or run end-to-end. Templates are product-agnostic and use {{TOKEN}} placeholders the skill prompts the user to fill.
writing-tech-post
IncludedAuthors engineering blog posts end-to-end: launch deep-dives, incident postmortems, architecture migrations, performance case studies, tutorials, AI/agent system writeups, security disclosures, and research-to-product translations. Picks the correct archetype, plans the abstraction ladder, enforces an evidence cadence (diagrams, benchmarks, profiles, traces, code, ablations), tunes voice against publisher house styles (Datadog, Vercel, GitHub, AWS, Meta, Cloudflare, Jane Street), and runs a pre-publish gate for narrative momentum and disclosure ethics. Use when drafting a new engineering post, restructuring a draft that feels flat, deciding which evidence form belongs where, validating that depth and product context are balanced, or preparing a postmortem, migration, or performance narrative for external publication. Do not use for API reference documentation, README authoring, marketing copy, release notes, generic SEO content, ghost-written executive thought leadership, or non-engineering long-form essays.
blog-google
IncludedGoogle API integration for blog performance: PageSpeed Insights, CrUX Core Web Vitals with 25-week history, Search Console performance, URL Inspection, Indexing API, GA4 organic traffic, NLP entity analysis for E-E-A-T, YouTube video search for embedding, and Google Ads Keyword Planner. Progressive feature availability based on credential tier (API key, OAuth/service account, GA4, Ads). Shares config with claude-seo at ~/.config/claude-seo/google-api.json. Use when user says "google data", "page speed", "core web vitals", "search console", "indexation", "GA4", "keyword research", "nlp entities", "blog performance", "youtube search", "google api setup".