Skills Explorer Add Skills

seo-cluster

An agent skill by AgriciDaniel, from AgriciDaniel/claude-seo. Tags: analysis, planning, seo, strategy, visual-art.

What it does

SERP-based semantic topic clustering for content architecture planning. Groups keywords by actual Google SERP overlap (not text similarity), designs hub-and-spoke content clusters with internal link matrices, and generates interactive visualizations. Optionally executes content creation if claude-blog is installed. Use when user says "topic cluster", "content cluster", "semantic clustering", "pillar page", "hub and spoke", "content architecture", "keyword grouping", or "cluster plan".

Install

With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:

npx skills add AgriciDaniel/claude-seo --skill seo-cluster

Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):

git clone --depth 1 https://github.com/AgriciDaniel/claude-seo
cp -r claude-seo/skills/seo-cluster ~/.claude/skills/seo-cluster

Safety box score

Grade C, moderate risk: 28 of 100 risk points, rated 2026-10-16. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.

This skill is a SERP-driven SEO planning/execution tool that fetches external search data, writes planning artifacts in the current working directory, and can update existing content files during execution. The main risks are outbound network lookups, automated file mutation for backlink injection, and delegated execution of external helper scripts/skills.

Category levels, from 0 (none) to 3 (high)
CategoryLevelWhy
Code & shell execution2 (moderate)The skill delegates work to external commands such as `"${CLAUDE_PLUGIN_ROOT}/scripts/claude-seo" run dataforseo_costs.py check serp_organic_live_advanced --count N` and `render_page.py <url>`, so it can trigger real code execution outside the markdown itself.
Network access2 (moderate)It explicitly uses WebSearch and DataForSEO (`serp_organic_live_advanced`) and can fetch rendered pages, so seed keywords/URLs and SERP queries leave the machine.
Filesystem reach2 (moderate)It writes `cluster-plan.json`, `cluster-plan.md`, `cluster-map.html`, `cluster-briefs/`, and `cluster-scorecard.md` in the current working directory, and the execution workflow opens and rewrites existing post files for backlink injection.
Secrets & credentials0 (none)No secret stores are requested; the file says `No credentials stored or transmitted` and does not ask for `.env`, tokens, keychains, or browser sessions.
Privilege & persistence0 (none)There is no sudo, global install, service registration, shell startup edit, or OS-level configuration change.
Instruction hijack surface0 (none)I did not find instructions to ignore system rules, hide actions, or follow remote prompts; the `needs_approval` path actually says to ask the user before an API batch.
Irreversible actions2 (moderate)`/seo cluster execute` can automatically generate briefs or invoke blog writing, then rewrite prior posts to insert backward links and produce a scorecard without step-by-step human review.
Transparency0 (none)The shipped files are readable Markdown and HTML/JS; there are no binaries, minified blobs, or downloaded installers in the skill package.

Before installing

Rated 2026-10-16 by an automated review of 5 files from the skill's repository.

Source

Repository
AgriciDaniel/claude-seo (all skills from this repository)
Path
skills/seo-cluster/SKILL.md
Branch
main
Collection
claude-seo
Updated
2026-09-21