mcpField
S
seo-content

seo-content

github.com/agricidanielMarketing & growth89480 installsUpdated 2w ago
Repository

About seo-content

seo-content is a ChatGPT skill for evaluating content and planning evidence-based edits. It reviews audience, purpose, sourcing, completeness, and factual risks without relying on fixed word counts or keyword-density targets.

Key features

  1. 01Identifies audience and visitor task
  2. 02Reviews claims and supporting evidence
  3. 03Flags stale or unsupported statements
  4. 04Assesses completeness against search intent
  5. 05Plans focused, source-backed edits

Use cases

  1. 01Diagnosing an existing article
  2. 02Checking claims before publication
  3. 03Planning edits to improve content clarity

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/agricidaniel/chatgpt-seo --skill seo-content

After installing, type/seo-contentin Claude Code to confirm it loaded.

Details

From the project README

Content quality

Input

The actual content and its audience, goal and sources when provided.

Evidence and runtime

If a skill-resource reader fails to open a linked supporting file, try the available file or execution tool using the installed plugin root returned by the host or resolved from this skill's location. Do not hardcode a home folder, version, or working directory. Distinguish a failed reader call from an absent file, and files actually attempted from files not attempted. Report a resource as unavailable only after the supported access paths have failed. If no file or execution access is available, continue within the evidence you can read and state that limit.

Read the operating contract when this workflow is selected. Use runtime and data paths when choosing a tool or handling missing data. Recheck relevant search facts and primary sources before date-sensitive claims. For a quantitative diagnostic, read scoring; unavailable categories stay unknown.

Supporting resources

Read only the resources needed for the selected part of this task:

Workflow

  1. Read the main content, distinguish it from navigation and boilerplate, and identify the task a visitor should complete.
  2. Evaluate who created it, how claims can be checked, why it exists, and which original examples, methods or experiences improve the answer.
  3. Find unsupported statistics, vague expertise claims, stale prices or policies, and contradictions. Verify volatile claims against primary sources or mark them unresolved.
  4. Assess completeness against the task and observed search intent. Do not use a universal word-count minimum, keyword-density target or AI detector as a quality verdict.
  5. Propose the smallest useful improvements: source-backed passages, a clearer structure, evidence or examples, author accountability, and natural internal links.
  6. When rewriting, retain the user's product facts and voice. Flag missing facts instead of inventing testimonials, experience or credentials.

Deliverable

A content diagnosis, a claim/evidence ledger and an edit plan. Supply the revised content only when requested, with unresolved facts clearly identified.

Boundary

E-E-A-T is a review framework here, not a directly measured ranking score. Originality claims require comparison evidence.

Adapted from the public Claude SEO seo-content workflow.

Comments

Markdown supported