Skip to main content
skill CX Codex

keyword-research · kostja94 — Claude Code skill: what it does, how to install

Coordinates keyword research from discovery through intent clustering and page mapping. Runs during site semantic structure planning.

MIT 1,600 installs ★ 1,129 updated 2026-10-21

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add kostja94/marketing-skills --skill keyword-research -a claude-code
Open on GitHub

What keyword-research does

The skill structures keyword research using seed queries or existing site inventory. The agent steps through discovery, intent clustering, opportunity assessment, and page mapping.

The workflow connects sibling skills for discovery, clustering, and mapping. Secrets are retrieved via the 1Password integration when configured, keeping credentials out of reports.

US search volume and prioritization are skipped by default unless requested and third-party data is available.

What it helps with

  • gather keyword research from seed terms
  • cluster search queries by intent
  • assess keyword opportunities and gaps
  • map keyword clusters to target pages
  • check indexability of existing URL inventory

Example prompts for the agent

  • Run keyword research for seed phrase “coffee machine repair”
  • Cluster these search queries by user intent
  • Map keyword clusters to the proposed page structure

How to install keyword-research

1Skills CLI (Vercel)

npx skills add kostja94/marketing-skills --skill keyword-research -a claude-code

2Manually: put the files in place

~/.claude/skills/keyword-research/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/keyword-research/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about keyword-research

How to install keyword-research in Claude Code?

Run npx skills add kostja94/marketing-skills --skill keyword-research -a claude-code, then use ~/.claude/skills/keyword-research/SKILL.md.

What does keyword-research do?

Coordinates keyword research through discovery, intent clustering, opportunity assessment, and page mapping.

What is required to run keyword-research?

An environment configured for 1Password to retrieve credentials for authenticated sources.

Source text

SKILL.md · MIT
---
name: keyword-research
description: Coordinates keyword research from a seed or existing keyword data through discovery, intent clustering, opportunity assessment and page mapping.
metadata:
  version: 2.3.0
---

# Keyword Research

For a market or category, start with [category research](references/category-research.md) to identify demand branches and seeds. For an existing website, start with its URL inventory and check indexability before diagnosing weak keyword performance. For a single seed, begin directly with the workflow below. Establish the decision, product capabilities, market, language and channel. Reuse relevant project context (including {project}.md when available), existing queries, URLs and CSV exports. State reasonable assumptions. A single seed is enough. When exploring several seeds one at a time, complete the current one before continuing.

Read the relevant sibling skills by name from the installed collection or local repository. Start at the earliest missing input and stop at the requested deliverable.

| Request | Skill | Handoff |
|---|---|---|
| Find demand or long-tail expressions | keyword-discovery | Candidate queries with provenance |
| Decide whether queries serve one page | keyword-clustering | Task, same-page variants, separate or uncertain branches |
| Choose what to pursue first | keyword-opportunity | Priorities, reasons and evidence gaps |
| Decide where validated demand belongs | keyword-mapping | Existing asset or proposed action per cluster |

By default, skip US search volume and keyword prioritization. Run keyword-opportunity for US rankings only when requested and suitable third-party data is available. Otherwise pass clusters directly to mapping. For a full study, pass these outputs forward in order. Return to discovery for a specific unresolved branch. If a sibling skill is unavailable, identify the missing step and use the handoff above to provide a bounded result. Keep source observations distinguishable from hypotheses throughout. For ads or product research, stop at the requested demand or opportunity decision. Hand content architecture and scheduling to content-strategy.

Default to concise findings, decision-relevant clusters and outstanding checks in the conversation. Produce full inventories or files on request. Stop when additional sources yield no material new tasks or variants, or at the agreed scope limit.

In a full report, show the base expression family before modifier clusters. Carry each material action, process and tool form into the page map or explain its pending placement. Report the concrete keyword strings, and mark observed versus inferred wording.

For a general keyword research request, deliver a decision report even if site inventory is missing. Lead with the main search task and proposed destination. Provide one row per candidate page cluster with a primary term, same-page variants, intent, landing page / blog / other type, proposed URL, decision and evidence or gap. Distinguish proposed paths from existing URLs. Separate confirmed observations from inferred expansions and show pending clusters. Respect a discovery-only request.

## Completion check for a full study

Before delivery, account for each research node as observed, inferred, blocked or outside the requested scope. A blocked source is an evidence gap. Resume at the first unresolved decision when more evidence becomes available.

1. Establish the seed, market, audience and product task. Identify useful parents while preserving the seed.
2. Run discovery across base word forms and task branches. Record competitor URLs and the status of Autocomplete, People Also Ask and related searches separately. Preserve provenance when deduplicating.
3. Hand discovery evidence to clustering. Resolve same-page variants, separate tasks and uncertain relationships against user goals, product capability and available search results. Send ambiguous high-impact branches back for targeted research.
4. Check product fit and evidence at cluster level. Apply the optional prioritization rule above. Label unknown metrics and unsupported capabilities explicitly.
5. Map each actionable cluster to a current or provisional destination, page type and reason. Distinguish an independent intent from a decision to create a new URL.
6. Deliver findings, cluster decisions, open checks and any explicitly requested, data-backed priorities. If a missing step prevents a decision, label that part provisional. For a narrower request, stop at its agreed node.

For authenticated sources use the configured credential provider. In an environment configured for 1Password, retrieve credentials through that integration and keep secret values out of files, logs and reports.

© kostja94 · MIT · kostja94/marketing-skills

Similar skills

All skills for SEO and GEO →

keyword-research by other authors comes first.

keyword-research every-app keyword-research finds search query opportunities via OpenSEO MCP tools, evaluates SERP metrics, and saves vetted keywords to the project. CX Codex +1 7,800installs keyword-research appeeky keyword-research is a Claude Code skill that finds and prioritizes App Store keywords, scores ranking opportunities, and maps terms to metadata fields. CX Codex +1 4,000installs keyword-research aaron-he-zhu keyword-research collects keywords for a page or campaign, scores them by volume, difficulty and intent, and groups them into topic clusters. Runs eight phases and returns a prioritized brief with Quick Wins and a content calendar. CX Codex +1 2,200installs keyword-research kostja94 keyword-research — an SEO research skill that finds target keywords, reads search intent and builds a topical map. Useful when you need a content plan tied to search demand. CX Codex +1 1,600installs keyword-research OpenClaudia Runs automated keyword research via the SemRush API, clusters terms by intent, and identifies competitor content gaps. Useful for SEO audits and content planning. CX Codex +1 496installs etsy-keyword-research nexscope-ai etsy-keyword-research provides Etsy search optimization guidance, helping sellers uncover long-tail keywords and plan seasonal listing updates. CX Codex +1 1,300installs developer-keyword-research Samuel Berthe developer-keyword-research — a skill for Claude Code and Codex that generates prioritized technical keyword maps. It extracts real developer search patterns from support tickets, documentation logs, and issue trackers. CX Codex +1 13,400installs linkfox-sif-keyword-overview linkfox-ai linkfox-sif-keyword-overview — a skill for Claude Code and Codex that checks Amazon keyword competition through SIF. It retrieves search volumes, supply-demand ratios, and ad positions. CX Codex +1 396installs keyword-analysis vivy-yi keyword-analysis structures keyword research for Xiaohongshu, helping identify high-intent search terms and trending topics for content. CX Codex +1 197installs seo-keyword-strategist Seth Hobson seo-keyword-strategist — a subagent for Claude Code, Codex and Cursor that digs into finished copy, counts keyword density and builds semantic variations from the topic. Feed it a draft and it shows where keywords are overdone. CX Codex ★ 42,780repo stars keyword-clustering akii-technologies-ltd The keyword-clustering Claude Code skill sorts keywords into topic groups and maps them to search intent. It activates on a keyword list or a request to plan site content. CX Codex +1 ★ 80repo stars

From the same set132

The whole set →
podcast-marketing podcast-marketing walks a podcast from planning to promotion: niche, episode formats, distribution, SEO and repurposing. Useful when the show exists but nobody hears it. CX Codex +1 1,900installs grokipedia-recommendations grokipedia-recommendations guides proposals for new articles and edits on Grokipedia without direct promotion. Helps gain backlinks and citations across AI answer engines. CX Codex +1 1,900installs github A skill for marketing on GitHub: repos, READMEs, GitHub Pages and Awesome lists used for SEO and AI citation. CX Codex +1 1,900installs google-ads Guides Google Ads setup, keyword targeting, and campaign structure. It helps run ads to validate early product demand or scale acquisition. CX Codex +1 1,700installs keyword-research keyword-research — an SEO research skill that finds target keywords, reads search intent and builds a topical map. Useful when you need a content plan tied to search demand. CX Codex +1 1,600installs privacy-page-generator privacy-page-generator — a skill for building privacy policy pages in AI code editors. This project moved to Pagina — use page-builder instead. CX Codex +1 1,600installs terms-page-generator terms-page-generator — a stub skill for building a Terms page. The rules moved to Pagina, and this entry only points you at page-builder. CX Codex +1 1,600installs legal-page-generator legal-page-generator — a stub skill: legal page construction moved to Pagina, and this entry only points at the replacement package. CX Codex +1 1,600installs

Project sponsors

Companies that keep this analytics open