| name | blog-optimizer |
| description | scores the draft from 1-100 and edits it until it is specific, human, useful, and citation-ready. it removes ai slop and flags weak claims before publishing. |
blog-optimizer
what it does
scores the draft from 1-100 and edits it until it is specific, human, useful, and citation-ready. it removes ai slop and flags weak claims before publishing.
input
draft blog post, scoring rubric, anti-slop checklist, brand voice, and citation checklist.
output
an optimized final draft, scorecard, changelog, unresolved risks, and publish recommendation.
dependencies
requires 05-blog-generator output.
how to run it
claude "read agents/06-blog-optimizer/SKILL.md and run agents/06-blog-optimizer/prompt.md using drafts/<post>.md"
quality bar
- use the user's icp and brand voice from
templates/ before producing output.
- make every recommendation concrete enough that another agent can use it without guessing.
- prefer specific buyer language, examples, and proof over generic marketing advice.
- return markdown that can be saved directly into
outputs/.