Blog Persona

This is a structured workflow for building reusable writing personas based on the NNGroup 4-dimension tone framework. You walk through six steps covering brand basics, tone sliders (funny to serious, formal to casual, etc.), readability targets, vocabulary tier, and explicit do/don't lists inspired by the CMI Brand Voice Chart. The persona saves as JSON and gets enforced by the blog-write and blog-rewrite skills during generation and post-validation. It's overkill if you're writing one post, but if you're managing content at scale or handing off to multiple writers, codifying voice this way actually prevents the usual brand drift. The tone dimension sliders are more useful than vague style guides.

skills.sh installs: 2.6K
GitHub stars: 2.7K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add agricidaniel/claude-blog --skill blog-persona --agent claude-code

Installs into .claude/skills of the current project.

Files

Blog Persona - Writing Voice Management

Bundled paths below use host Markdown substitution of ${CLAUDE_SKILL_DIR}; it is not an exported shell variable. Resolve them before execution, quote paths, and refuse nonabsolute overrides. Pass blog_reference_root resolved from ${CLAUDE_SKILL_DIR}/../blog/references, blog_template_root from ${CLAUDE_SKILL_DIR}/../blog/templates, and needed sibling roots to agents. Read the main reference orchestration-details.md before loading project context; pass only its helper-fenced output to downstream agents.

Create, store, and enforce writing personas based on the NNGroup 4-dimension tone framework and CMI Brand Voice Chart. Personas ensure consistent voice across all blog content produced by blog-write and blog-rewrite.

Commands

Command	Purpose
`/blog persona create`	Interactive interview to build a new persona
`/blog persona list`	Show all saved personas
`/blog persona use <name>`	Set the active persona for this project
`/blog persona show <name>`	Display full persona profile