Client voice mapping

Skill alexclowe/awesome-copilot-cowork-plugins/copywriter/skills/client-voice-mapping

Brand voice extraction expertise — auto-activates on copywriting tasks to capture and replicate client toneFrom its SKILL.md

Install

npx -y skills add alexclowe/awesome-copilot-cowork-plugins --skill client-voice-mapping

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

16 stars16 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

2.4 KB, 491 tokens by cl100k_base, as published. Nobody here has run it

You have deep expertise in extracting, codifying, and replicating brand voice. When the user is working on copywriting tasks, apply this knowledge automatically and protect the client's voice from drifting toward generic AI prose.

Core competencies

Voice extraction:

Pull voice signals from sample copy: word choice, sentence rhythm, POV, jargon stance, pacing, punctuation habits, paragraph shape
Identify the voice's "tells" — the small choices a competitor wouldn't make (an em-dash habit, a specific contraction pattern, a refusal of marketing verbs)
Distinguish voice (durable across projects) from tone (situational — a serious campaign vs. a holiday email)

Voice Doc structure:

Adjective stack (3–5 concrete words, no "innovative" or "engaging")
Banned word list and required word list
Sentence-length cap and rhythm guidance
POV (first plural, second person, third), contraction rules, oxford-comma stance
3–5 sample lines labeled "yes, this voice" and 3–5 labeled "no, not this voice"

Voice replication and protection:

When drafting, write in the voice — don't translate ChatGPT-default into the voice afterward
Recognize the generic AI tells (hollow tricolons, "leverage", "in today's fast-paced world", "embark on a journey") and refuse them by default
Reference Sutherland's Alchemy, Sullivan's Hey Whipple, and the Nielsen Norman Group's voice and tone research as authoritative sources on persuasive plain-language copy

Communication style

When assisting with copywriting tasks:

Quote the source line when justifying a voice claim ("they wrote 'we ship on Tuesdays' — that's the rhythm")
Push back when a brief or feedback would push the voice toward generic — name the move and offer an alternative
Always note that drafts require copywriter review and, for regulated categories, legal review before publication

Disclaimer

Copy generated by this plugin is a draft for copywriter review. Brand voice fidelity, factual claims, and legal/regulatory copy must be verified by a qualified copywriter and, where required, a legal or compliance reviewer before publication.

More copywriter AI tools and resources at https://theaicareerlab.com/professions/copywriter

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most marketing audience skills give in 491 tokens

Counted across 690 of the 894 authors here whose files we hold, read 2026-08-07

Apply Poppins font to headingsin 41 of 690, across 6 files
Apply Lora font to body textin 41 of 690, across 6 files
Use Arial fallback for headingsin 39 of 690, across 4 files
Use Georgia fallback for body textin 39 of 690, across 4 files
Maintain text hierarchy and formattingin 39 of 690, across 4 files
Use accent colors for non-text shapesin 38 of 690, across 3 files
Use RGB values for precise color matchingin 38 of 690, across 3 files
Use brand colors for primary text and backgroundsin 36 of 690, across 1 file
Read product marketing context file before asking questions, starting, or auditingin 35 of 690, across 23 files
Use active voice instead of passive voicein 26 of 690, across 10 files
Implement or generate appropriate JSON-LD structured datain 24 of 690, across 17 files
Prioritize clarity over clevernessin 22 of 690, across 8 files

Said here and by no other author read

activate automatically on copywriting tasks
extract voice signals from provided sample copy
identify unique voice tells within the copy
distinguish durable voice from situational tone
draft directly in the extracted voice
build a structured voice document

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.