zensink/zens-ink-seo-package/keyword-research
Claude Code and agent skill by zensink/zens-ink-seo-package
- community
Checking that the SKILL.md file is still in the repository.
Find low-competition keyword opportunities without paid tools (Ahrefs, Semrush). Runs real zero-dependency Python CLIs: Google Autocomplete discovery (with a-z long-tail expansion), semantic clustering, Bing volume lookup, and automated KGR opportunity scoring. Use when the user wants keyword ideas for a niche, asks "find low competition keywords", wants to cluster a keyword list, or wants keyword volume without an SEO subscription. No API keys needed for discovery and clustering; volume lookup needs an optional free Bing Webmaster key.
Install
npx vskill@latest install zensink/zens-ink-seo-package/keyword-researchSKILL.md
Keyword research without paid tools
Discover keywords, cluster them into topics, score them for opportunity — all from free data sources (Google Autocomplete, Bing Webmaster API). No Ahrefs/Semrush subscription required.
When to use
- "Find keyword ideas for my niche / my SaaS / my blog"
- "Which long-tail keywords should I target?"
- "Cluster this keyword list into topics"
- "Score these keywords — which ones are worth writing?"
When NOT to use
- The user already pays for Ahrefs/Semrush and wants their numbers — use their tool.
- They want backlink data — this skill has none (that is a paid-data problem).
Setup (one-time)
Zero dependencies beyond Python 3.9+. All commands run as python3 -m zens_ink.<tool>.
Commands
1. Discover keywords (no key needed)
Real output:
Add --expand for a-z long-tail discovery (slower, much deeper). --lang zh for Chinese autocomplete. --json for machine-readable output.
2. Cluster a keyword list into topics
Groups semantically related keywords so one page can target one cluster. Use the output of step 1 (save suggestions to a file, one per line).
3. Volume lookup (optional, free Bing Webmaster key)
Language must be a full locale (en-us, not en), country lowercase — the CLI normalizes this for you. Needs BING_WMT_API_KEY in .env.
4. Score opportunities: KGR (no key needed)
KGR = allintitle count / monthly search volume.
How to read the results
- KGR < 0.25 — low-competition, a new site can rank for it. Write it.
- KGR 0.25–1.0 — possible with some authority; pair with internal links.
- KGR > 1.0 — skip unless the user's domain is strong.
- Autocomplete
high-activityseeds = live demand;low-activityseeds are
usually too thin to build on.
- One cluster = one page. Never target two clusters with one URL.
Next steps
- Check how hard the survivors are: the
keyword-difficultyskill. - Confirm intent before writing: the
search-intentskill.
Going deeper
ZensInk Pro adds personalized Winability Scores (difficulty relative to YOUR domain's GSC data) and a Content Radar editorial calendar: https://zens.ink/pricing/
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/keyword-research/SKILL.md
Popularity
- 7-day trend score
- 0
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/zensink/zens-ink-seo-package/keyword-research)