Guides keyword research for SEO: finding target keywords, assessing difficulty, understanding search intent, and building topical maps. ~95% of keywords get fewer than 10 searches/month; low-volume, high-intent terms often yield faster rankings and conversion.
Works with
AI-first code editor with Composer
Before installing skills in Cursor, ensure your development environment meets these requirements:
node --versionkeyword-researchExecute the skills CLI command in your project's root directory to begin installation:
Fetches keyword-research from kostja94/marketing-skills and configures it for Cursor.
The CLI shows a list of agents. Use arrow keys and space to select Cursor:
Confirm successful installation by checking the skill directory location:
Restart Cursor to activate keyword-research. Access via /keyword-research in your agent's command palette.
We perform automated surface-level scans (Gen AI Scanner, Socket, Snyk) during installation. These checks detect common vulnerabilities but do not guarantee complete security. Always review skill source code and verify the publisher's reputation before production use.
Skills execute code in your environment. Always review source, verify the publisher, and test in isolation before production.
Submit your Claude Code skill and start earning
Create detailed user stories, acceptance criteria, and feature specs
Example
Generate user stories for 'password reset feature' with acceptance criteria, edge cases, and test scenarios
Reduce spec writing time by 50%, ensure comprehensive coverage
Research competitors, compare features, identify gaps
Example
Analyze 5 competitor products, create feature comparison matrix, suggest differentiation opportunities
Complete competitive research in 2 hours instead of 2 days
Evaluate features using frameworks (RICE, ICE, Kano) and create prioritized backlogs
Example
Score 20 feature ideas using RICE framework, generate prioritized roadmap with rationale
8
total installs
8
this week
309
GitHub stars
0
upvotes
Run in your terminal
8
installs
8
this week
309
stars
Guides keyword research for SEO: finding target keywords, assessing difficulty, understanding search intent, and building topical maps. ~95% of keywords get fewer than 10 searches/month; low-volume, high-intent terms often yield faster rankings and conversion.
When invoking: On first use, if helpful, open with 1–2 sentences on what this skill covers and why it matters, then provide the main output. On subsequent use or when the user asks to skip, go directly to the main output.
Check for project context first: If .claude/project-context.md or .cursor/project-context.md exists, read it for product, audience, and positioning.
Identify:
| Method | Purpose |
|---|---|
| User perspective | What pain points? What would they search? Customer language from product context |
| Tool expansion | Related keywords, questions, suggestions; Google autocomplete, PAA, Related Searches |
| Competitor reverse | Analyze competitor titles, H1, URL; identify topics they rank for; find gaps (#4–10 = opportunity) — see competitor-research |
| Google PAA | People Also Ask and Related Searches; high-value signals from real user behavior |
| Extract from article | When auditing existing content: extract seed keywords from title, H1, H2s, meta keywords, first 100 words; then search "[primary keyword]" or "[primary keyword] related keywords" for opportunities; use "[primary keyword]" site:competitor.com if competitors known |
Google autocomplete reflects real user searches; suggestions only appear if queries have actual traffic. Free; often uncovers low-volume long-tail that keyword tools miss. ~70% of search traffic is long-tail; lower competition, higher conversion.
Alphabet method (seed + space + letter):
keyword a, keyword b, ... keyword zSEO a -> "SEO audit," "SEO agency"; SEO b -> "SEO basics," "SEO best practices"Position variants (seed in different positions):
a keyword, b keyword (discover what users add before)keyword a, keyword b (most common; alphabet method)how to keyword a, best keyword for (question + modifier combos)Question modifiers:
how to keyword, what is keyword, why keyword, when to keyword, keyword vskeyword for beginners, keyword for small business, keyword withoutWhy it works: Keyword tools filter low-volume terms; autocomplete only shows queries with real traffic. Use with PAA and Related Searches for full coverage. Categorize results by intent (informational, commercial, transactional).
| Intent | Content type | Example |
|---|---|---|
| Informational | Blog, guide, FAQ | "how to optimize sitemap" |
| Navigational | Brand page | "alignify login" |
| Commercial | Comparison, review | "SEO tools comparison" |
| Transactional | Product, pricing | "best SEO tool pricing" |
Modifier words (often signal intent):
| Intent | Modifiers |
|---|---|
| Informational | "how," "what," "why," "guide," "tutorial" |
| Commercial | "best," "compare," "vs," "review," "top" |
| Transactional | "buy," "price," "cheap," "coupon," "free shipping" |
| Local | Location names |
SERP check: Search the term—knowledge cards/Wiki → informational; product lists/reviews → commercial; brand sites → navigational. Broader terms often show mixed SERP. See serp-features for feature types.
| Method | Use |
|---|---|
| SERP overlap | Keywords with overlapping top-ranking pages → same cluster |
| Semantic | Group by meaning, LSI, related concepts |
| Intent-based | Group by intent; separate pages if intent differs within cluster |
Pillar–cluster (map keywords to structure):
| Factor | Consider |
|---|---|
| Search volume | Monthly searches; ~100+/month typical floor; niche can relax |
| Keyword difficulty (KD) | New sites target lower KD |
| CPC | Higher CPC often = stronger commercial intent |
| SERP features | Featured Snippet, PAA, zero-click; SERP features can satisfy intent without click—affects real traffic; see serp-features (Zero-Click section), featured-snippet |
| Screening order | 1) Remove irrelevant 2) Filter very low volume 3) Assess achievability 4) Prioritize commercial/transactional |
Test if positioning is clear enough for search:
Agent/Copilot products: Pure native Agent hard to grow via SEO; users rarely search "agent." Release related features first (e.g., CRM, sales bot for sales agent) to build traffic, then funnel to Agent product.
Keyword research serves both SEO and Google Ads. Align both channels to avoid duplication, cannibalization, and wasted spend.
| Data flow | Use |
|---|---|
| keyword-research → google-ads | Keyword list, clusters, intent; support terms (login, forum, pricing) → negative keywords for PPC |
| google-ads → keyword-research | PPC conversion rate, Search Terms report → SEO priority; high-converting PPC terms = worth ranking organically |
| keyword-research → landing-page | Clusters → dedicated LP per intent; PAA questions → FAQ sections |
| GSC organic rank 4+ | If you rank well organically, consider reducing/pausing PPC on those terms to avoid cannibalization |
PPC data for SEO priority: SEO ROI ≈ (Organic clicks × PPC conversion rate × Customer value) − SEO cost. Use PPC conversion data to validate which keywords to pursue in organic.
Reference: Backlinko – SEO and PPC: 8 Smart Ways to Align
| Source | Use |
|---|---|
| Ahrefs | Keywords Explorer, Site Explorer |
| SEMrush | Keyword Overview, Organic Research |
| GSC | Search queries, impressions, clicks |
| GA | Traffic by landing page |
| PostHog | Feature/search usage |
project-context.md if present| Section | Content |
|---|---|
| Executive Summary | Priorities (top 3) |
| Keyword Overview | Total keywords, primary intent, avg KD, content gaps count |
| Keyword List | Keyword, volume, KD, intent, priority, target page |
| Keyword Mapping | Page/URL, target keywords, status |
| Content Gaps | Keywords competitors rank for that you don't |
| Action Plan | Priority, action, impact, effort |
| Appendix | Search intent reference (Informational, Commercial, Transactional, Navigational) |
Make data-driven prioritization decisions faster
Draft PRDs, status updates, and stakeholder presentations
Example
Create executive summary of Q3 roadmap, monthly progress report, feature launch announcement
Save 3-5 hours/week on communication overhead
Prerequisites
Time Estimate
30-60 minutes to see productivity improvements
Steps
Common Pitfalls
✓ Do
✗ Don't
💡 Pro Tips
✓ Use when
Use for user story writing, competitive research, roadmap prioritization, stakeholder communication, and PRD drafting. Best for reducing repetitive documentation and research work.
✗ Avoid when
Avoid for strategic product vision (requires deep customer empathy), pricing decisions (needs market and financial expertise), or when face-to-face customer discovery is more valuable than speed.
kostja94/marketing-skills
mattpocock/skills
parcadei/continuous-claude-v3
cursor/plugins
ailabs-393/ai-labs-claude-skills
pproenca/dot-skills
Registry listing for keyword-research matched our evaluation — installs cleanly and behaves as described in the markdown.
I recommend keyword-research for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.
keyword-research is among the better-maintained entries we tried; worth keeping pinned for repeat workflows.
keyword-research reduced setup friction for our internal harness; good balance of opinion and flexibility.
Solid pick for teams standardizing on skills: keyword-research is focused, and the summary matches what you get after install.
keyword-research reduced setup friction for our internal harness; good balance of opinion and flexibility.
Useful defaults in keyword-research — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.
I recommend keyword-research for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.
keyword-research is among the better-maintained entries we tried; worth keeping pinned for repeat workflows.
Registry listing for keyword-research matched our evaluation — installs cleanly and behaves as described in the markdown.
showing 1-10 of 50