Skip to content

Skill · Blog Writing & SEO Team

Quality Review & Scorecard

Score a finished draft against the 100-point content, SEO, E-E-A-T, technical, and AI-citation rubric and produce a prioritized fix list.

What it is

Score a finished draft against the 100-point content, SEO, E-E-A-T, technical, and AI-citation rubric and produce a prioritized fix list.

A skill is a written procedure an agent loads when a job calls for it. This one is a single file, SKILL.md, and the whole file is on this page.

File
SKILL.md
Length
24 lines · 1 min read
Category
Marketing
License
MIT
Author
Brainwrite
Words
317

Paste it into any agent’s instructions (CLAUDE.md, AGENTS.md or a custom GPT), or add the team to Brainwrite and it arrives switched on.

Use it

Use this skill in Brainwrite.

  1. 1

    Add the Blog Writing & SEO Team

    Its agents carry this skill. You preview every agent and skill first; skills arrive switched on and routines paused.

    Install in Brainwrite →
  2. 2

    Brief your Chief of Staff

    “Use the Quality Review & Scorecard skill for this: [describe the job]. Show me the plan first, and send, post or change nothing.”

  3. 3

    Approve what matters

    The agent follows the skill and brings the result back. Anything that sends, posts or changes data waits for your approval in Ask mode.

    How approvals work →

Use this when

quality review, review the post, score this draft, content review, editorial review.

Process

Score the draft across five categories out of 100: Content Quality (30 — coverage of the reader's task 7, readability 7, originality/unique value 5, sentence & paragraph structure 4, engagement elements 4, grammar/clarity 3), SEO Optimization (25 — heading hierarchy 5, title clarity 4, semantic topic consistency 4, internal linking 4, URL structure 3, meta description 3, external linking 2), E-E-A-T Signals (15 — author attribution 4, source citations 4, trust indicators 4, evidence basis 3), Technical Elements (15 — schema 4, image optimization 3, structured data elements 2, page speed signals 2, mobile-friendliness 2, OG/social tags 2), and AI Citation Readiness (15 — evidence-backed citability 4, purpose fit 3, entity clarity 3, extraction-friendly structure 3, crawler accessibility 2).

Score honestly — an accurate 75 is more useful to the team than a flattering 85. For every issue, cite its exact location and give a concrete fix, ranked Critical, High, Medium, or Low.

Separately flag advisory style concerns as observations that never change the numeric score and never imply anything about who or what wrote the draft: repeated question-form H2s, three or more "Here" paragraph openers, more than half of sentences in a 200-word window following the same three-clause rhythm, more than 2 hedge words in a 20-word span, symmetric list-item lengths (SD below 5), more than 2 wrap-up rhetorical questions, and any of the configured generic AI-sounding phrases.

Report the total score, the category breakdown, and a short prioritized fix list. This is advisory: report the scorecard to the team and the user; do not attempt to gate or withhold the post yourself.

Attribution

This playbook's severity framing, distinguishing must-fix gaps from polish, is adapted from editorial heuristics that claude-blog itself ported from Nielsen's 10 Usability Heuristics via the impeccable plugin (Paul Bakaus, Apache License 2.0, https://github.com/pbakaus/impeccable).

Put this skill to work.

Download Brainwrite, add the team that carries it, and tell your Chief of Staff what needs doing.

macOS today. Windows and Linux are coming soon.