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.

Files2

2 files · 2.1 KB

Select a file to preview

Overall Score

88/100

Grade

A

Excellent

Safety

95

Quality

87

Clarity

89

Completeness

82

Summary

This skill guides agents to build reusable voice profiles from real source material (posts, articles, emails, docs) and then apply those profiles consistently across content workflows. It extracts stylistic patterns like rhythm, compression, capitalization, and tone from representative samples, outputs a structured VOICE PROFILE artifact, and enables downstream skills to reuse that profile instead of re-deriving style from scratch.

Detected Capabilities

Analyze writing samples for stylistic patterns and toneExtract rhythm, compression, capitalization, and claim style from source materialIdentify banned moves and preferred moves in a voiceStructure voice profiles in a reusable schema formatIntegrate with downstream content skills via VOICE PROFILE artifacts

Trigger Keywords

Phrases that MCP clients use to match this skill to user intent.

voice consistencyextract writing stylereusable voice profileadapt tone across channelsbuild author fingerprint

Use Cases

Build a consistent writing style profile from founder or author samples
Extract voice patterns from existing posts, articles, and emails for reuse
Create a canonical style guide for outreach across X, LinkedIn, and email
Adapt a known author's tone across multiple content channels
Generate a reusable voice profile for content-engine or crosspost workflows

Quality Notes

Excellent source prioritization: provides a clear 4-tier hierarchy (X posts → articles → emails → docs) that guides agent behavior when multiple sources exist.
Well-defined extraction targets: lists 8 concrete stylistic dimensions (rhythm, compression, capitalization, parentheticals, questions, claim style, transitions, negations) instead of vague 'tone' guidance.
Strong domain defaults for Affaan/ECC: provides specific fallback voice characteristics (direct, concrete, mechanisms-first, skeptical) that give the agent a foundation when live sources are thin.
Hard bans section is actionable: lists 8 specific patterns to delete and rewrite rather than saying 'avoid clichés', enabling deterministic filtering.
Clear output contract: skill explicitly references a schema file and emphasizes operational reuse over literary criticism, focusing on agent usability downstream.
Persistence rules are well-scoped: reuse in same session, save only if user asks, never repo-track personal fingerprints without explicit consent.
Downstream integration points are documented: maps this skill to five downstream consumers (content-engine, crosspost, lead-intelligence, article writing, outbound).
Schema file is minimal and well-structured: uses short bullets and source-backed specifics rather than essay paragraphs, matching the skill's operational philosophy.
Use case triggers are well-defined: skill activates on specific intents (voice consistency, multi-channel adaptation, reusable style system) rather than generic content writing.
Reference to x-api shows integration with live tooling when available, but does not require it.

Model: claude-haiku-4-5-20251001Analyzed: Apr 20, 2026

Reviews

Add this skill to your library to leave a review.

No reviews yet

Be the first to share your experience.

Version History

v1.1

Content updated

2026-04-20

Latest

v1.0

No changelog

2026-04-12

brand-voice