Memstack Seo Keyword Research logo

Memstack Seo Keyword Research

Community
cwinvestments
memstack-seo-keyword-research

Use this skill when the user says 'keyword research', 'find keywords', 'keyword strategy', 'search terms', 'keyword opportunities', or needs to identify target keywords with search volume, difficulty, and content mapping. Do NOT use for full site audits or ad keyword groups.

Overview

Publishercwinvestments
Repositorymemstack
Skill namememstack-seo-keyword-research
Stars
425
Forks
45
Bundled files
Instructions only
LicenseMIT
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 cwinvestments on GitHub. Read the source before you install it.

Installation

Install the Memstack Seo Keyword Research 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/cwinvestments/memstack/tree/master/skills/seo-geo/keyword-research
  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/cwinvestments/memstack.git /tmp/memstack
mkdir -p .claude/skills
cp -r /tmp/memstack/skills/seo-geo/keyword-research .claude/skills/memstack-seo-keyword-research
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Memstack Seo Keyword Research 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 Memstack Seo Keyword Research 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 Memstack Seo Keyword Research 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.

🔑 Keyword Research: Identifying target keywords and content gaps...

Analyzes the niche, existing content, and competitor landscape to produce a prioritized keyword map with search intent, difficulty estimates, and page assignments.

Activation

When this skill activates, output:

🔑 Keyword Research, Analyzing niche and identifying opportunities...

Then execute the protocol below.

ContextStatus
User says "keyword research" or "find keywords" or "SEO keywords"ACTIVE
User says "content gaps" or "keyword strategy" or "search terms"ACTIVE
Planning content strategy based on search demandACTIVE
Optimizing existing pages with better keywordsACTIVE
Writing content (keywords already chosen)DORMANT: use blog-post
Running a full site auditDORMANT: use site-audit

Anti-patterns

TrapReality Check
"Target the highest volume keywords"High volume = high competition. New sites rank faster on long-tail keywords with lower volume but higher intent.
"One keyword per page"Each page has a primary keyword and 3-5 semantically related keywords. Google understands topic clusters.
"Keyword research is a one-time task"Search trends shift. New competitors appear. Revisit quarterly at minimum.
"We need to rank for our brand name"You'll rank for brand terms naturally. Focus research on non-brand terms that bring new visitors.
"Volume is the only metric that matters"A keyword with 100 searches/month and high purchase intent beats 10,000 searches/month with informational intent for a product page.

Protocol

Step 1: Gather Niche Details

If the user hasn't provided details, ask:

I need context for keyword research:

  1. Niche/industry: what market are you in?
  2. Product or service: what do you sell or offer?
  3. Target audience: who are you trying to reach? (role, demographics, pain points)
  4. Competitors: 2-3 competitor domains (or I'll identify them)
  5. Current site: URL if live, or list of existing pages
  6. Goal: more traffic, more signups, more sales, thought leadership?

Step 2: Analyze Existing Content

Scan the project for current keyword coverage:

bash
# Find all content pages
find app/ pages/ content/ posts/ blog/ -name "*.tsx" -o -name "*.jsx" -o -name "*.md" -o -name "*.mdx" 2>/dev/null | grep -v node_modules

# Extract titles and meta descriptions
grep -rn "title\|description\|<h1\|<H1" --include="*.tsx" --include="*.jsx" --include="*.md" . | grep -v node_modules | head -30

# Find existing keyword targeting
grep -rn "keywords\|tags\|category" --include="*.md" --include="*.mdx" --include="*.json" . | grep -v node_modules | head -20

Document current coverage:

PageCurrent TitlePrimary Keyword (inferred)Content Type
/[homepage title][brand/product name]Landing
/about[about title][brand story]Informational
/blog/[slug][post title][topic keyword]Blog
/pricing[pricing title][product pricing]Commercial

Identify gaps: Pages that exist but have weak or no keyword targeting.

Step 3: Generate Primary Keywords

For each page or content opportunity, suggest a primary keyword:

Keyword evaluation criteria:

FactorWeightHow to Assess
Search intent matchHighDoes the keyword match what the page offers?
Achievable difficultyHighCan this site realistically rank? (domain authority, competition)
Search volumeMediumEnough monthly searches to justify the effort
Business relevanceHighDoes ranking for this drive revenue or signups?
Current rankingMediumAlready ranking 10-50? Optimize. Not ranking at all? Harder path.

Primary keyword research process:

  1. Seed keywords: Start with 5-10 obvious terms the audience would search
  2. Expand: For each seed, identify variations using these patterns:
    • How to [topic]
    • Best [product category]
    • [Topic] for [audience]
    • [Topic] vs [alternative]
    • [Topic] examples / templates / tools
    • What is [topic]
  3. Filter: Remove keywords where the SERP is dominated by major brands (unless you are one)
  4. Prioritize: Rank by intent match + achievable difficulty

Step 4: Suggest Long-Tail Variations

For each primary keyword, generate 3-5 long-tail variations:

markdown
### Primary: "project management software"
Long-tail variations:
- "project management software for small teams" (audience modifier)
- "free project management software 2026" (qualifier + year)
- "project management software with time tracking" (feature modifier)
- "project management software for remote teams" (use case modifier)
- "best project management software for startups" (intent + audience)

Long-tail pattern formulas:

PatternExampleIntent
[keyword] for [audience]"CRM for freelancers"Commercial
best [keyword] [year]"best CRM 2026"Commercial
[keyword] vs [alternative]"Notion vs Airtable"Commercial (comparison)
how to [action] with [keyword]"how to manage leads with a CRM"Informational
[keyword] [feature]"CRM with email automation"Commercial
free [keyword]"free CRM software"Transactional
[keyword] examples"CRM workflow examples"Informational
[keyword] template"CRM spreadsheet template"Transactional

Step 5: Identify Content Gaps

Compare your content against what competitors rank for:

markdown
## Content Gap Analysis

### Topics competitors cover that you don't:
| Topic | Competitor Ranking | Your Coverage | Opportunity |
|-------|-------------------|--------------|-------------|
| [topic 1] | competitor.com ranks #3 | No page | Create blog post |
| [topic 2] | competitor.com ranks #7 | Mentioned briefly | Expand into dedicated page |
| [topic 3] | competitor.com ranks #1 | Not covered | Create comparison page |

### Topics you cover but could improve:
| Your Page | Current Ranking (est.) | Issue | Fix |
|-----------|----------------------|-------|-----|
| /blog/[slug] | ~page 3 | Thin content (500 words) | Expand to 1,500+ with more depth |
| /features | Not ranking | Missing target keyword in title | Optimize title and H1 |

Gap identification methods:

  1. Review competitor sitemaps for content they produce
  2. Search for primary keywords and note who ranks in top 10
  3. Look for "People Also Ask" questions that no one answers well
  4. Check competitor blog categories for topics you haven't covered

Step 6: Map Keywords to Pages

Assign each keyword to a specific page (existing or to be created):

markdown
## Keyword Map

| Primary Keyword | Volume Est. | Difficulty | Intent | Assigned Page | Status |
|----------------|-------------|-----------|--------|--------------|--------|
| project management tool | High | Hard | Commercial | / (homepage) | Optimize |
| best project management for startups | Medium | Medium | Commercial | /blog/best-pm-startups | Create |
| how to manage remote team projects | Medium | Easy | Informational | /blog/remote-pm-guide | Create |
| project management template free | Low-Med | Easy | Transactional | /templates | Create |
| [brand] vs [competitor] | Low | Easy | Commercial | /blog/brand-vs-competitor | Create |
| what is agile project management | Medium | Medium | Informational | /blog/agile-guide | Create |

Mapping rules:

  • One primary keyword per page: no keyword cannibalization
  • Group related keywords on the same page (primary + 3-5 secondary)
  • Homepage targets the broadest commercial keyword
  • Blog posts target informational and long-tail keywords
  • Landing/product pages target transactional keywords
  • Comparison pages target "[brand] vs [competitor]" keywords

Step 7: Prioritize by Search Intent

Classify and prioritize every keyword:

IntentDescriptionContent TypePriority for
TransactionalReady to buy/sign upProduct page, pricing, CTA landing pageRevenue-focused sites
CommercialResearching optionsComparison, review, "best of"SaaS, e-commerce
InformationalLearning about a topicBlog post, guide, tutorialTraffic + authority building
NavigationalLooking for a specific siteHomepage, brand pagesAlready established brands

Priority matrix:

Low DifficultyHigh Difficulty
High Intent✅ Do first (quick wins with revenue impact⏳ Worth the investment) build authority content
Low Intent⚡ Easy traffic (good for brand awareness❌ Skip) high effort, low return

Step 8: Output Keyword Map

🔑 Keyword Research: Complete

Niche: [industry/market]
Site: [domain]
Pages analyzed: [count] existing
Keywords identified: [count] primary + [count] long-tail

Keyword map summary:
  Transactional: [count] keywords → [count] pages
  Commercial:    [count] keywords → [count] pages
  Informational: [count] keywords → [count] pages

Content to create: [count] new pages recommended
Content to optimize: [count] existing pages with improvements

Top 5 priority keywords:
  1. [keyword], [volume] / [difficulty], [action: create/optimize] [page]
  2. [keyword], [volume] / [difficulty], [action] [page]
  3. [keyword], [volume] / [difficulty], [action] [page]
  4. [keyword], [volume] / [difficulty], [action] [page]
  5. [keyword], [volume] / [difficulty], [action] [page]

Quick wins (low difficulty, high intent):
  - [keyword] → [page to create/optimize]
  - [keyword] → [page to create/optimize]

Next steps:
1. Create content for top 5 priority keywords (use blog-post skill)
2. Optimize existing pages with assigned keywords (use meta-tag-optimizer)
3. Build internal links between related keyword pages
4. Track rankings monthly in Google Search Console
5. Revisit keyword map quarterly

Level History

  • Lv.1: Base: Niche gathering, existing content analysis, primary keyword generation with evaluation criteria, long-tail variations, competitor content gap analysis, keyword-to-page mapping, search intent classification and prioritization, formatted keyword map output. (Origin: MemStack Pro v3.2, Mar 2026)

Frequently asked questions

What does the Memstack Seo Keyword Research AI skill do?

Use this skill when the user says 'keyword research', 'find keywords', 'keyword strategy', 'search terms', 'keyword opportunities', or needs to identify target keywords with search volume, difficulty, and content mapping. Do NOT use for full site audits or ad keyword groups.

Why use Memstack Seo Keyword Research on TypingMind?

Because you install it once and use it with any model. Memstack Seo Keyword Research 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 Memstack Seo Keyword Research in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/cwinvestments/memstack/tree/master/skills/seo-geo/keyword-research. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Memstack Seo Keyword Research?

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 Memstack Seo Keyword Research?

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

Is the Memstack Seo Keyword Research AI skill free?

Yes. It is published on GitHub by cwinvestments under the MIT license. 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 👇