Find Keywords logo

Find Keywords

Community
FlorianBruniaux
find-keywords

Build a prioritized keyword list for a website, topic, or campaign. Use when the user asks about keyword research, finding keywords to target, building a keyword list, search demand, keyword difficulty, intent mapping, or which keywords to prioritize. For writing content around keywords, see brief. For grouping keywords into clusters, see build-clusters.

Overview

PublisherFlorianBruniaux
Repositoryclaude-code-ultimate-guide-landing
Skill namefind-keywords
Stars
13
Forks
2
Bundled files
Instructions only
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by FlorianBruniaux on GitHub. Read the source before you install it.

Installation

Install the Find Keywords AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/FlorianBruniaux/claude-code-ultimate-guide-landing/tree/main/.agents/skills/find-keywords
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/FlorianBruniaux/claude-code-ultimate-guide-landing.git /tmp/claude-code-ultimate-guide-landing
mkdir -p .claude/skills
cp -r /tmp/claude-code-ultimate-guide-landing/.agents/skills/find-keywords .claude/skills/find-keywords
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Find Keywords in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Find Keywords on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Find Keywords is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Find Keywords

Build a prioritized keyword universe from a seed topic using intent mapping, difficulty-adjusted opportunity scoring, and cluster seeding.

Before You Start

Gather this context (ask if not provided):

  1. Domain and goal. What site is this for? What is the primary conversion (leads, sign-ups, sales, traffic)?
  2. Seed topic. The core subject area — not a single keyword but the business category (e.g., "project management software", "personal injury law Chicago").
  3. Existing rankings. Does the site already rank for terms in this area? Existing rankings tell you where to defend vs. expand.
  4. Constraints. Budget, team size, content velocity — these determine whether to chase head terms or focus on long-tail.

Step 0: Cannibalization Screen

Before building a new keyword list, check what the site already targets. Creating a new page for a keyword you already rank for can split authority and hurt both pages.

For each keyword you're considering:

  1. Search site:yourdomain.com [keyword] — does an existing page already target this term?
  2. Check Google Search Console — is an existing page already getting impressions for this keyword?
  3. If yes: update the existing page instead of creating a new one.
  4. If multiple pages rank for the same keyword: you have a cannibalization problem. Consolidate before expanding.

Low-Hanging Fruit Check

Before chasing new keywords, look for existing wins:

  • Positions 11-20 — You're almost on page 1. These keywords need content improvements or better internal linking, not new pages.
  • High impressions, low clicks — Title/meta description optimization can unlock traffic without new content.
  • Declining positions — Keywords where you're losing ground may need content refreshes (see recover-content).

Address these before building net-new keyword lists.

Keyword Universe Construction

Build the universe in three tiers:

Tier 1 — Head Terms (high volume, high difficulty)

  • Typically 1-2 words
  • Define the category
  • Target with pillar pages or the homepage
  • Realistic timeline: 6-18 months for new sites

Tier 2 — Body Terms (medium volume, medium difficulty)

  • Typically 2-3 words, specific enough to indicate intent
  • Target with dedicated landing pages or cluster articles
  • 3-6 month window for established sites

Tier 3 — Long-tail Terms (lower volume, low difficulty)

  • 3+ words, specific intent
  • Fastest to rank, highest conversion rate
  • Target with blog posts, FAQ sections, supporting content
  • 4-12 week window for fresh content

For each tier, produce:

KeywordMonthly VolumeDifficulty (0-100)IntentTierPriority
.........informational / transactional / navigational / commercial1/2/3high / medium / low

Intent Classification

Classify every keyword by search intent and sub-category:

Informational (user wants to learn)

Sub-categorySignal WordsExampleContent Type
Educationalwhat, why, definition, explain"what is SEO"Guide, explainer
Instructionalhow to, steps, tutorial, guide"how to set up GA4"Step-by-step tutorial
Exploratorytypes of, techniques, strategies"link building techniques"Comprehensive roundup
Troubleshootingnot working, fix, error, why is"why is my site not ranking"Diagnostic guide

Commercial Investigation (user is evaluating)

Sub-categorySignal WordsExampleContent Type
Comparisonvs, compared to, or"Ahrefs vs SEMrush"Side-by-side comparison
Review-seekingreview, worth it, honest"Ahrefs review"In-depth review
Best-ofbest, top, tools for"best SEO tools"Curated list
Evaluationfor [audience], features, pricing"SEO tools for small business"Buyer's guide

Transactional (user is ready to act)

Sub-categorySignal WordsExampleContent Type
Purchasebuy, price, discount, deal"buy Ahrefs subscription"Product/pricing page
Signup/Trialfree trial, sign up, demo"Ahrefs free trial"Landing page
Downloaddownload, template, PDF, checklist"SEO checklist PDF"Gated resource
Hire/Engagehire, agency, near me, book"SEO agency near me"Service page

Navigational (looking for a specific brand)

Sub-categorySignal WordsExampleContent Type
Brand search[brand name]"HubSpot"Homepage/brand page
Feature search[brand] + [feature]"Ahrefs keyword explorer"Feature page
Support/docs[brand] + login, docs, help"Ahrefs API docs"Support content

SERP Feature Correlation by Intent

Use this to anticipate which SERP features you can target per keyword:

SERP FeatureInformationalCommercialTransactionalNavigational
Featured SnippetVery HighHighLowLow
People Also AskVery HighVery HighLowMedium
AI OverviewVery HighHighLow-MediumLow
Shopping ResultsVery LowMediumVery HighLow
Local PackLowLowHighLow
SitelinksLowLowMediumVery High

Conversion Potential by Intent

IntentAvg Conversion RateNurture Length
Informational0.5-2%Long (weeks to months)
Commercial Investigation2-5%Medium (days to weeks)
Transactional5-15%Short (immediate to days)
NavigationalN/A — brand-dependentN/A

Common Classification Mistakes

MistakeCorrect Classification
Treating "best CRM software" as informationalCommercial Investigation
Treating "how much does X cost" as informationalCommercial / Transactional
Ignoring local intent in "SEO services"Transactional (local)
Assuming single intent for "SEO tools"Mixed — check the SERP to confirm

Two keywords with different intents should never target the same page.

Opportunity Scoring

Score each keyword:

Opportunity Score = (Volume x (1 - Difficulty/100)) x Intent Multiplier

Intent multipliers:

  • Transactional: 1.5
  • Commercial investigation: 1.3
  • Informational: 1.0
  • Navigational: 0.2

This surfaces low-competition, high-intent targets over vanity volume plays.

Cluster Seeding

Group the keyword universe into topic clusters:

Cluster NamePillar KeywordSupporting Keywords (3-5)Total Volume
............

Each cluster needs one pillar page (head term) and 3-8 supporting pages (body + long-tail).

Output Format

Keyword Research: [topic or domain]

Summary

  • Total keywords: [count]
  • Total addressable volume: [sum]
  • Difficulty range: [min]-[max]
  • Clusters identified: [count]

Priority Matrix [Tiered keyword table]

Cluster Seeds [Cluster table]

Start Here — Top 5 Keywords

For each of the 5 highest-opportunity keywords:

  • Why this keyword now (difficulty, intent, business value)
  • What page type to create
  • Which cluster it anchors or supports

Pro Tip: Use the free Blog Keyword Generator and Autocomplete Research tools at seojuice.com for seed keyword discovery. SEOJuice MCP users can run /seojuice:keyword-analysis for live ranking data and /seojuice:content-strategy to see content gaps — keywords your competitors rank for that you don't.

Frequently asked questions

What does the Find Keywords AI skill do?

Build a prioritized keyword list for a website, topic, or campaign. Use when the user asks about keyword research, finding keywords to target, building a keyword list, search demand, keyword difficulty, intent mapping, or which keywords to prioritize. For writing content around keywords, see brief. For grouping keywords into clusters, see build-clusters.

Why use Find Keywords on TypingMind?

Because you install it once and use it with any model. Find Keywords is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Find Keywords in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/FlorianBruniaux/claude-code-ultimate-guide-landing/tree/main/.agents/skills/find-keywords. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Find Keywords?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Find Keywords?

As many as you like. As long as a model supports skills, you can use Find Keywords with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Find Keywords AI skill free?

It is published on GitHub by FlorianBruniaux. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇