Skip to content
Get packs

Brand Voice

Builds a reusable writing-style profile from your real posts and docs so drafts sound consistent.

Source Download skill
Repository
affaan-m/ECC
Stars
295,127
Licence
MIT
Files
3 files

What it does

This skill teaches an AI agent to study real writing you already have, such as posts, essays, launch notes, emails that worked, and product docs, and to summarise its style into a short reusable profile covering rhythm, sentence length, capitalisation, use of numbers and questions, and what the author never does. Once the profile exists, the agent reuses it for social posts, emails, and launch copy instead of guessing a style each time. It also includes a default ECC/Affaan voice and a list of banned clichés such as fake hooks, bait questions, and 'Excited to share' phrasing.

Great for

  • Founders or marketers who want many posts and emails to sound like one consistent author
  • Developers maintaining an open-source project's public voice across X, LinkedIn, and launch notes
  • Teams that already have a body of good writing and want a repeatable style guide for AI-drafted copy

Skip it if

  • Imitating a person's voice without their consent, since the skill is built to mirror a specific author's writing from source samples
  • Situations with very little real writing to learn from, where the profile will be guesswork; the skill itself says to prefer real sources over generic exemplars
  • Anyone expecting it to fetch or post content automatically; it only shapes drafts, and optional live X access depends on a separate x-api skill

Try asking

  • “Build a voice profile from my last 15 X posts and launch notes, then draft a product update in that voice”
  • “Using the saved voice profile, rewrite this landing page announcement so it drops generic AI phrasing”
  • “Create a LinkedIn post and a cold outreach email in my established voice, avoiding bait questions”
  • “Summarise my writing style from these essays into a short profile the content-engine skill can reuse”
Step-by-step guide: how to use Brand VoiceInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 3 original files, the MIT licence and an attribution note.

    brand-voice.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip brand-voice.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip brand-voice.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Give 5 to 20 recent, representative samples rather than old or generic writing, since the skill prioritises recent original material.
  • Save the confirmed VOICE PROFILE in your own workspace; the skill avoids storing personal voice fingerprints in repo-tracked files unless you ask.
  • Review the generated profile before reuse, because it is inferred from your samples and may over- or under-state traits.

What's inside

  • agents/openai.yaml
  • references/voice-profile-schema.md
  • SKILL.md

Redistributed unmodified from affaan-m/ECC under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.