brand-voice

Name: brand-voice
Author: MoizIbnYousaf

27stars5forks

How to install brand-voice?

moizibnyousaf/marketing-cli/brand-voice

$npx -y skills add MoizIbnYousaf/marketing-cli --skill brand-voice

Installs into the current project.

Summary

Define or extract a consistent brand voice that other skills can use. Three modes: Extract (analyze existing content), Build (interview-based), Auto-Scrape (from URL). Use when copy sounds generic, when starting any new project, when voice feels inconsistent across channels, when

Files · 1

View on GitHub

SKILL.md

1	# /brand-voice -- Brand Voice Engine
2
3	Generic copy converts worse than copy with a distinct voice. Not because the
4	words are different -- because the reader feels like they're hearing from a
5	PERSON, not a marketing team.
6
7	This skill defines that voice. Either by extracting it from existing content,
8	building it strategically from scratch, or auto-scraping a URL to analyze a
9	brand's public presence.
10
11	For output formatting, see /cmo [rules/output-format.md](../cmo/rules/output-format.md).
12
13	---
14
15	## On Activation
16
17	1. Read `brand/` context:
18	- positioning.md — If available, use market angles to inform voice differentiation. A brand positioned as "the anti-course course" needs a different voice than one positioned as "enterprise-grade."
19	- audience.md — If available, tailor vocabulary and tone to the target reader. Technical builders get different language than busy executives.
20	- If neither exists, proceed with defaults. Ask the user about their market and audience during the question sequence.
21	2. Check if `./brand/voice-profile.md` already exists:
22	- Exists → Update mode: show current profile summary, ask what to change.
23	- Does not exist → Proceed to Mode Selection below.
24	3. Assess the user's request to determine which mode to use (Extract, Build, or Auto-Scrape).
25
26	## Three Modes
27
28	### Mode 1: Extract (analyze existing content)
29
30	User provides 3-5 pieces of existing content (blog posts, emails, social posts, about page, etc).
31
32	The analysis process:
33
34	1. Read all provided content -- look for patterns, not individual word choices
35	2. Identify the voice DNA:
36	- Sentence structure (short/punchy vs. flowing/complex)
37	- Vocabulary level (everyday vs. technical vs. academic)
38	- Emotional register (warm/friendly vs. authoritative vs. irreverent)
39	- Perspective (first-person storytelling vs. objective analysis)
40	- Rhythm (varies sentence length? staccato? musical?)
41	3. Map the personality axes (see Voice DNA Framework below)
42	4. Generate the voice profile
43	5. Write to ./brand/voice-profile.md
44
45	### Mode 2: Build (construct from scratch)
46
47	No existing content. Build voice strategically through guided questions.
48
49	The question sequence:
50
51	1. "If your brand were a person at a dinner party, how would they talk?"
52	2. "Who is your audience? Technical builders, creative professionals, busy executives, everyday consumers, or a mix?"
53	3. "Name 2-3 brands whose tone you admire (not their product -- their VOICE)."
54	4. "What words should NEVER appear in your marketing? What feels off-brand?"
55	5. "Show me something you've written that felt 'right' -- even a Slack message or email."
56
57	### Mode 3: Auto-Scrape (URL analysis)
58
59	User provides a URL. Skill uses Exa MCP to research the brand's public presence.
60
61	1. Use Exa MCP to search for the brand's website content, social profiles, and public-facing copy
62	2. Analyze homepage, about page, social bios, recent posts
63	3. Extract voice patterns using the same DNA framework as Mode 1
64	4. Present findings and ask user to confirm/adjust
65	5. Generate voice profile
66
67	## Mode Selection
68
69	Not sure which mode? Here's the decision tree:
70	- Have 3+ pieces of existing content (blog posts, emails, landing pages) → Mode 1: Extract
71	- Starting fresh with no content → Mode 2: Build via interview
72	- Have a live website URL → Mode 3: Auto-Scrape
73
74	If the brand has both a website AND existing content, prefer Mode 1 (Extract) — it captures the voice the brand already uses, which is more authentic than what a URL scan reveals.
75
76	---
77
78	## Voice DNA Framework
79
80	Every voice maps across these axes:
81
82	### Personality Spectrum
83
84	Rate each 1-10 with brief justification:
85	- Formal / Casual
86	- Reserved / Expressive
87	- Serious / Playful
88	- Traditional / Progressive
89	- Complex / Simple
90	- Cautious / Bold
91
92	### Voice Markers
93
94	Sentence patterns: Average length, variation, structure (simple/compo

People who liked this also viewed

6 picks

Type

brand-voice

27stars5forks

View on GitHub

How to install brand-voice?

moizibnyousaf/marketing-cli/brand-voice

$npx -y skills add MoizIbnYousaf/marketing-cli --skill brand-voice

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# /brand-voice -- Brand Voice Engine
2
3	Generic copy converts worse than copy with a distinct voice. Not because the
4	words are different -- because the reader feels like they're hearing from a
5	PERSON, not a marketing team.
6
7	This skill defines that voice. Either by extracting it from existing content,
8	building it strategically from scratch, or auto-scraping a URL to analyze a
9	brand's public presence.
10
11	For output formatting, see /cmo [rules/output-format.md](../cmo/rules/output-format.md).
12
13	---
14
15	## On Activation
16
17	1. Read `brand/` context:
18	- positioning.md — If available, use market angles to inform voice differentiation. A brand positioned as "the anti-course course" needs a different voice than one positioned as "enterprise-grade."
19	- audience.md — If available, tailor vocabulary and tone to the target reader. Technical builders get different language than busy executives.
20	- If neither exists, proceed with defaults. Ask the user about their market and audience during the question sequence.
21	2. Check if `./brand/voice-profile.md` already exists:
22	- Exists → Update mode: show current profile summary, ask what to change.
23	- Does not exist → Proceed to Mode Selection below.
24	3. Assess the user's request to determine which mode to use (Extract, Build, or Auto-Scrape).
25
26	## Three Modes
27
28	### Mode 1: Extract (analyze existing content)
29
30	User provides 3-5 pieces of existing content (blog posts, emails, social posts, about page, etc).
31
32	The analysis process:
33
34	1. Read all provided content -- look for patterns, not individual word choices
35	2. Identify the voice DNA:
36	- Sentence structure (short/punchy vs. flowing/complex)
37	- Vocabulary level (everyday vs. technical vs. academic)
38	- Emotional register (warm/friendly vs. authoritative vs. irreverent)
39	- Perspective (first-person storytelling vs. objective analysis)
40	- Rhythm (varies sentence length? staccato? musical?)
41	3. Map the personality axes (see Voice DNA Framework below)
42	4. Generate the voice profile
43	5. Write to ./brand/voice-profile.md
44
45	### Mode 2: Build (construct from scratch)
46
47	No existing content. Build voice strategically through guided questions.
48
49	The question sequence:
50
51	1. "If your brand were a person at a dinner party, how would they talk?"
52	2. "Who is your audience? Technical builders, creative professionals, busy executives, everyday consumers, or a mix?"
53	3. "Name 2-3 brands whose tone you admire (not their product -- their VOICE)."
54	4. "What words should NEVER appear in your marketing? What feels off-brand?"
55	5. "Show me something you've written that felt 'right' -- even a Slack message or email."
56
57	### Mode 3: Auto-Scrape (URL analysis)
58
59	User provides a URL. Skill uses Exa MCP to research the brand's public presence.
60
61	1. Use Exa MCP to search for the brand's website content, social profiles, and public-facing copy
62	2. Analyze homepage, about page, social bios, recent posts
63	3. Extract voice patterns using the same DNA framework as Mode 1
64	4. Present findings and ask user to confirm/adjust
65	5. Generate voice profile
66
67	## Mode Selection
68
69	Not sure which mode? Here's the decision tree:
70	- Have 3+ pieces of existing content (blog posts, emails, landing pages) → Mode 1: Extract
71	- Starting fresh with no content → Mode 2: Build via interview
72	- Have a live website URL → Mode 3: Auto-Scrape
73
74	If the brand has both a website AND existing content, prefer Mode 1 (Extract) — it captures the voice the brand already uses, which is more authentic than what a URL scan reveals.
75
76	---
77
78	## Voice DNA Framework
79
80	Every voice maps across these axes:
81
82	### Personality Spectrum
83
84	Rate each 1-10 with brief justification:
85	- Formal / Casual
86	- Reserved / Expressive
87	- Serious / Playful
88	- Traditional / Progressive
89	- Complex / Simple
90	- Cautious / Bold
91
92	### Voice Markers
93
94	Sentence patterns: Average length, variation, structure (simple/compo

People who liked this also viewed

6 picks

Type