Skip to content
Agentmart
Submit a tool

keyword-research

Strategic keyword research powered by web search and brand context.

Skill by MoizIbnYousaf

IndexedMIT★ 32
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/moizibnyousaf-keyword-research

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Strategic keyword research powered by web search and brand context. Use this skill whenever the user mentions keywords, keyword research, SEO topics, content topics, 'what should I write about', content strategy, blog ideas, search traffic, or content planning. Also trigger when the user wants to plan what content to create, when existing content isn't attracting search traffic, when any skill needs keyword-plan.md but it doesn't exist, or when the user asks about SEO in the context of content creation. Even casual mentions like 'I need blog post ideas' or 'what topics should I cover' warrant this skill. 8-phase process from seed to content brief.

Use cases: design, writing, marketing, research

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/keyword-research

What's inside

Skill name
keyword-research
Description
Strategic keyword research powered by web search and brand context. Use this skill whenever the user mentions keywords, keyword research, SEO topics, content topics, 'what should I write about', content strategy, blog ideas, search traffic, or content planning. Also trigger when the user wants to plan what content to create, when existing content isn't attracting search traffic, when any skill needs keyword-plan.md but it doesn't exist, or when the user asks about SEO in the context of content creation. Even casual mentions like 'I need blog post ideas' or 'what topics should I cover' warrant this skill. 8-phase process from seed to content brief.
License
MIT
Instructions
457 lines in SKILL.md · view on GitHub

Files (3)

  • SKILL.md
  • dr-cap-and-confidence.md · references/
  • keyword-examples.md · references/

SKILL.md (first lines)

## On Activation

1. Check if `brand/` directory exists in the project root.
2. If it does, read available files: `voice-profile.md`, `positioning.md`, `audience.md`, `creative-kit.md`, `stack.md`, `learnings.md`.
3. Apply any loaded brand context to enhance output quality.
4. If `brand/` does not exist, proceed without it — this skill works standalone.

> **Note:** Examples below use fictional brands (Acme, Lumi, Helm). Replace with your own brand context.

## Backend Selection

Prefer measured KD/volume/CPC/intent/SERP/GSC via `openseo-keyword-research` when OpenSEO is configured; otherwise Exa-stack validation with metrics marked `unknown`. Full contract: `skills/openseo/references/backend-contract.md`.

# /keyword-research -- Data-Backed Keyword Strategy

Most keyword research is backwards. People start with tools, get overwhelmed by
data, and end up with a spreadsheet they never use.

This skill starts with strategy. What does your business need? Who are you trying
to reach? What would make them find you? Then it validates with live search data
and builds a content plan that actually makes sense.

No expensive tools required. Systematic thinking plus web search.

**Reads:** `positioning.md`, `audience.md`, `competitors.md`, `learnings.md`
**Writes:** `brand/keyword-plan.md`, `campaigns/content-plan/*.md`

---

## Iteration Detection

Before starting, check whether `./brand/keyword-plan.md` already exists.

### If keyword-plan.md EXISTS --> Refresh Mode

Do not start from scratch. Instead:

1. Read the existing plan.
2. Present a summary of the current keyword strategy:
   ```
   EXISTING KEYWORD PLAN (last updated {date})
   Pillars: {Pillar 1} {N} clusters {priority} · {Pillar 2} {N} {priority} · {Pillar 3} {N} {priority}
   Top keywords: {kw1} {priority} · {kw2} {priority} · {kw3} {priority}
   Content briefs: {N} created, {N} published

   What would you like to do?
   ① Refresh with new SERP data  ② Add a new topic area  ③ Re-prioritize clusters
   ④ Full rebuild from scratch   ⑤ Generate briefs for top keywords
   ```

3. Process the user's choice:
   - Option ① --> Re-run web search for existing keywords, update priorities based on fresh data
   - Option ② --> Gather new seed keywords, run full expansion, merge into existing plan
   - Option ③ --> Re-score all clusters with updated business context
   - Option ④ --> Full process from scratch
   - Option ⑤ --> Skip to content brief generation for highest-priority unfilled clusters

4. Before overwriting, show a compact diff of what changed (new clusters, priority changes, removals) and ask: "Save these changes? (y/n)"

5. Only overwrite after explicit confirmation.

### If keyword-plan.md DOES NOT EXIST --> Full Research Mode

Proceed to the full process below.

---

## The Core Job

Transform a business context into a **prioritized content plan** with:
- Keyword clusters organized by topic
- Priority ranking based on opportunity and live SERP data
- Content type recommendations
- Individual content briefs for top keywords
- A clear "start here" action

**Output format:** Clustered keywords mapped to content pieces, prioritized by
business value, competitive opportunity, and search demand. Saved to disk as
a keyword plan and individual content briefs.

---

## The Process

```
SEED --> EXPAND --> SEARCH --> CLUSTER --> VALIDATE --> PRIORITIZE --> MAP --> BRIEF
```

1. **Seed** -- Generate initial keywords from business context and brand memory
2. **Expand** -- Use the 6 Circles Method to build the full list
3. **Search** -- Pull live SERP data: autocomplete, People Also Ask, competitor rankings
4. **Cluster** -- Group related keywords into content pillars
5. **Validate** -- Run 4-check pillar validation with live competitive data
6. **Prioritize** -- Score by opportunity, business value, and search evidence
7. **Map** -- Assign clusters to specific content pieces
8. **Brief** -- Generate individual content briefs for top priorities

---

## Before Starting: Gather Context

Get these inputs before generating anything. If brand memory files exist, pre-fill
what you can and confirm with the user.

1. **What do you sell/offer?** (1-2 sentences)
   - Pre-fill from: ./brand/positioning.md
2. **Who are you trying to reach?** (Be specific)
   - Pre-fill from: ./brand/audience.md
3. **What is your website?** (To understand current content)
4. **Who are 2-3 competitors?** (Or help identify them)
   - Pre-fill from: ./brand/competitors.md
5. **What is the goal?** (Traffic? Leads? Sales? Authority?)
6. **Timeline?** (Quick wins or long-term plays?)

If brand memory supplies 3+ of these, present what you found and ask for
confirmation rather than re-asking:

```

From MoizIbnYousaf/marketing-cli, MIT.

More from MoizIbnYousaf/marketing-cli

Signals

Stars
32
Forks
5
Open issues
1
Last commit (this folder)
Aug 31, 2026 (1 month ago)
Last release
Aug 16, 2026 (2 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from MoizIbnYousaf

Cite this page

keyword-research skill. Agent Mart. https://agentmart.dev/skills/moizibnyousaf-keyword-research (last updated 2026-10-24)