seo-content

An agent skill by AgriciDaniel, from AgriciDaniel/claude-seo. Tags: analysis, copy-editing, documentation, seo, validation.

What it does

Content quality and E-E-A-T analysis with AI citation readiness assessment, plus last-mile draft cleanup (AI-typical phrasing and invisible Unicode watermark characters). Use when user says "content quality", "E-E-A-T", "content analysis", "readability check", "thin content", "content audit", "humanize", "AI phrasing", "remove watermarks", or "invisible characters".

Install

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

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

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-content ~/.claude/skills/seo-content

Safety box score

Grade B, low risk: 21 of 100 risk points, rated 2026-10-20. 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 is a content-analysis skill that inspects a user-supplied URL and can also run bundled local helper scripts for draft cleanup and Google-update lookups. The main risks are moderate network access to remote pages/services and moderate local code execution through the shipped scripts; it does not request elevated privileges or secrets.

Category levels, from 0 (none) to 3 (high)
Category	Level	Why
Code & shell execution	2 (moderate)	The skill explicitly runs local helper scripts via `"${CLAUDE_PLUGIN_ROOT}/scripts/claude-seo" run content_humanize.py ...` and `... run seo_updates.py ...`, so installing it grants script execution on the machine.
Network access	2 (moderate)	It is designed around a user-provided `argument-hint: "[url]"` and optionally uses DataForSEO MCP tools, so page content and query metadata can leave the machine to fetch/analyze remote resources.
Filesystem reach	1 (low)	The cleanup workflow writes a local output file with `-o cleaned.md`, which stays in the working directory but can create or overwrite files there.
Secrets & credentials	0 (none)	The skill does not ask for or read tokens, passwords, browser sessions, `.env` files, or keychain material.
Privilege & persistence	0 (none)	There is no sudo, global install, service registration, shell-profile editing, or OS-level configuration change in the visible files.
Instruction hijack surface	0 (none)	I did not find instructions to ignore higher-priority rules, hide behavior, follow remote prompt content, or otherwise subvert the agent.
Irreversible actions	0 (none)	The skill analyzes content and prepares reports; it does not publish, send messages, deploy, pay, book, or delete on its own.
Transparency	1 (low)	Key behavior depends on external files not included in the supplied bundle, such as `${CLAUDE_PLUGIN_ROOT}/skills/seo/references/eeat-framework.md`, `${CLAUDE_PLUGIN_ROOT}/skills/seo/references/eeat-scoring-guide.md`, and `${CLAUDE_PLUGIN_ROOT}/scripts/claude-seo`.

Before installing

Read the referenced helper files under `${CLAUDE_PLUGIN_ROOT}` and confirm what `claude-seo`, `content_humanize.py`, and `seo_updates.py` actually do.
Test it first on a throwaway public URL and a scratch `draft.md`; verify the only local write is the expected `cleaned.md`.
If you do not want third-party calls, disable DataForSEO MCP tools and check what network access the URL fetcher performs.

Rated 2026-10-20 by an automated review of 2 files from the skill's repository.

Source

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

seo — Comprehensive SEO analysis for any website or business type.
seo-page — Deep single-page SEO analysis covering on-page elements, content quality, technical meta tags, schema, images, and performance.
seo-technical — Technical SEO audit across 9 categories: crawlability, indexability, security, URL structure, mobile, Core Web Vitals, structured data, JavaScript rendering.
verify-this — Verify a claim with fresh local evidence: restate it falsifiably, capture baseline and treatment, compare artifacts, and return VERIFIED, NOT VERIFIED.
deep-research — Generate format-controlled research reports with evidence tracking, citations, source governance, and multi-pass synthesis.
prompt-optimizer — Transform vague prompts into precise, well-structured specifications using EARS (Easy Approach to Requirements Syntax) methodology.