What types of source material can I use?

You can use recent posts, essays, launch notes, and product documentation. The skill prioritizes original content from the strongest available sources.

How do I gather the samples needed for the voice profile?

Collect between 5 to 20 representative samples that reflect the desired voice. Recent material is preferred, unless older content is more canonical.

Can I use this skill for creative writing?

This skill is focused on maintaining a specific voice and is best suited for structured content like outreach and professional communication, rather than creative writing.

What happens if I have multiple voices to manage?

You can create separate voice profiles for different voices, allowing you to switch between them as needed for various tasks.

Is there a limit to how many voice profiles I can create?

There is no specific limit, but each profile should be distinct and based on relevant source material to ensure clarity and usability.

Brand Voice

Name: Brand Voice
Availability: InStock
Author: affaan-m

Free

Create a consistent writing style from real sources.

by affaan-m239.3k stars on affaan-m/ecc

2 views

Updated Aug 10, 2026

Get this skill

Free · Opens the source repo

What Brand Voice does

Brand Voice is designed for users who need to maintain a consistent voice across various content types without relying on generic AI writing tropes. By building a voice profile from actual source material, such as posts, essays, and product documentation, this skill allows users to create a reusable style that reflects the intended tone and rhythm of their brand. This is particularly useful for marketers, content creators, and anyone involved in outreach or communication who wants to ensure their messaging is coherent and aligned with their brand identity.

The skill operates by gathering a set of representative samples from the strongest available sources, prioritizing recent material. Users can collect between five to twenty samples that best represent the desired voice. The skill then analyzes these samples to extract key characteristics such as sentence length, rhythm, and specific stylistic choices. The output is a structured VOICE PROFILE that can be utilized across various tasks, ensuring that the generated content maintains the same voice and tone.

Brand Voice is especially beneficial when writing for platforms like LinkedIn, email, or during product launches, where a consistent and recognizable voice can enhance engagement and clarity. It also serves to adapt an established author's tone across different channels, making it a versatile tool for any content workflow that demands a specific voice.

However, users should be aware that this skill is not intended for generating creative content from scratch or for scenarios where a more fluid, less structured approach is needed. It excels in environments where voice consistency is paramount, but may not be suitable for more casual or experimental writing tasks.

When to use it

Use this skill when you need to create content or outreach materials in a specific, consistent voice.

When not to use it

Avoid this skill for casual writing or when a more flexible, creative approach is needed.

What you can build with it

Creating Consistent Marketing Emails

Utilize the skill to develop a voice profile that ensures all marketing emails reflect the same tone and style, enhancing brand recognition.

Adapting Author's Tone for Social Media

Use the skill to extract and apply a known author's voice to social media posts, maintaining consistency across different platforms.

Streamlining Product Launch Communications

Implement the skill to create a reusable voice profile for product updates and launch notes, ensuring clear and consistent messaging.

How to install Brand Voice

View source

1. Install with the skills CLI

npx skills add affaan-m/ecc/brand-voice --agent claude-code

2. Or install it manually

Download the skill folder and drop it into ~/.claude/skills/ for all projects, or .claude/skills/ to scope it to one repo. Restart Claude Code so it picks up the new skill.

Anthropic's agentic coding CLI, and the reference implementation of Agent Skills. Drop a skill folder into ~/.claude/skills and Claude Code loads it automatically whenever a task matches the skill's description. Claude Code docs

Inside SKILL.md

Written by affaan-m

Brand Voice

Build a durable voice profile from real source material, then use that profile everywhere instead of re-deriving style from scratch or defaulting to generic AI copy.

When to Activate

the user wants content or outreach in a specific voice
writing for X, LinkedIn, email, launch posts, threads, or product updates
adapting a known author's tone across channels
the existing content lane needs a reusable style system instead of one-off mimicry

Source Priority

Use the strongest real source set available, in this order:

recent original X posts and threads
articles, essays, memos, launch notes, or newsletters
real outbound emails or DMs that worked
product docs, changelogs, README framing, and site copy

Do not use generic platform exemplars as source material.

Collection Workflow

Gather 5 to 20 representative samples when available.
Prefer recent material over old material unless the user says the older writing is more canonical.
Separate "public launch voice" from "private working voice" if the source set clearly splits.
If live X access is available, use x-api to pull recent original posts before drafting.
If site copy matters, include the current ECC landing page and repo/plugin framing.

What to Extract

rhythm and sentence length
compression vs explanation
capitalization norms
parenthetical use
question frequency and purpose
how sharply claims are made
how often numbers, mechanisms, or receipts show up
how transitions work
what the author never does

Output Contract

Produce a reusable VOICE PROFILE block that downstream skills can consume directly. Use the schema in references/voice-profile-schema.md.

Keep the profile structured and short enough to reuse in session context. The point is not literary criticism. The point is operational reuse.

Affaan / ECC Defaults

If the user wants Affaan / ECC voice and live sources are thin, start here unless newer source material overrides it:

direct, compressed, concrete
specifics, mechanisms, receipts, and numbers beat adjectives
parentheticals are for qualification, narrowing, or over-clarification
capitalization is conventional unless there is a real reason to break it
questions are rare and should not be used as bait
tone can be sharp, blunt, skeptical, or dry
transitions should feel earned, not smoothed over

Hard Bans

Delete and rewrite any of these:

fake curiosity hooks
"not X, just Y"
"no fluff"
forced lowercase
LinkedIn thought-leader cadence
bait questions
"Excited to share"
generic founder-journey filler
corny parentheticals

Persistence Rules

Reuse the latest confirmed VOICE PROFILE across related tasks in the same session.
If the user asks for a durable artifact, save the profile in the requested workspace location or memory surface.
Do not create repo-tracked files that store personal voice fingerprints unless the user explicitly asks for that.

Downstream Use

Use this skill before or inside:

content-engine
crosspost
lead-intelligence
article or launch writing
cold or warm outbound across X, LinkedIn, and email

If another skill already has a partial voice capture section, this skill is the canonical source of truth.

Frequently asked questions about Brand Voice

Similar skills

LinkedIn Post Formatter

Create engaging LinkedIn posts with Unicode styling.

Brand Voice Enforcement

Ensure all content aligns with your brand's voice.

Answer Engine Optimization

Optimize your content for AI citation.

Copywriting

Craft clear, compelling marketing copy that drives action.

Ad Creative

Generate and iterate ad copy for performance marketing.

X/Twitter运营导师

Optimize your Twitter strategy with expert guidance.