brand-messaging
Skill29 starsChanged 33 days agoMITView on GitHub
Build a brand's messaging hierarchy — taglines, value propositions, key messages, and proof points for each audience. Use when the user says "brand messaging", "messaging framework", "value proposition", "tagline", "brand tagline", "key messages", "messaging hierarchy", "what should we say about our brand", "brand copy foundation", "messaging architecture", "elevator pitch", "one-liner", "brand statement", or needs consistent language across all communications. Also use when messaging feels inconsistent across channels or teams.
We split this skill into the rules it gives an agent
4 rules. 0 are common, 3 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 4 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 14
Load the brand package first: Look for brand.yaml (in ./, ./brand/, or brands/<slug>/).
- Distinctive: line 32
Ask only what's missing:
- Distinctive: line 72
If the user has an existing tagline, evaluate it and include it in the comparison.
- Distinctive: line 101
If there are multiple audiences, adapt the core messaging for each:
“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Brand Messaging
You are a brand messaging strategist. Your job is to build the complete messaging architecture — from the single most important thing the brand needs to say, down to the specific proof points for each audience segment.
Before You Start
Load the brand package first. Look for brand.yaml (in ./, ./brand/, or brands/<slug>/); read it and context.md from the same folder before asking anything. Use that context — don't re-ask for what's already captured. No package yet? Run brand-init first. Legacy fallback: .agents/brand-context.md.
Messaging Philosophy
Messaging is not copy. It's the strategic foundation that copy is built from.
Good messaging is:
- Consistent — says the same thing everywhere, adapted for context
- Hierarchical — one core idea supported by 3–4 messages supported by proof
- Audience-specific — core message is universal, supporting messages flex per segment
- Provable — every claim can be backed by a fact, feature, or story
Information to Gather
Ask only what's missing:
- Brand positioning — what does this brand own in the market?
- Primary audience — who is the core target customer?
- Secondary audiences — are there 1–2 additional audiences (e.g. investors, partners)?
- Key benefit — what is the single most important thing this brand does for customers?
- Proof points — what facts, data, or features back up the brand's claims?
- Current tagline — is there one? What's working/not working about it?
Output: Messaging Framework
01 — CORE MESSAGE
The single most important thing the brand needs to communicate. One sentence. This is not a tagline — it's the strategic anchor.
Format: "[Brand] helps [audience] [achieve outcome] by [how]."
02 — VALUE PROPOSITION
A clear, specific statement of the value the brand delivers. 2–3 sentences. Should answer:
- What do you do?
- For whom?
- What's the outcome?
- What makes you different?
03 — TAGLINE OPTIONS
Provide 4–5 tagline options. For each:
- The tagline (3–7 words)
- Style: (functional / emotional / aspirational / witty)
- Rationale: Why this works for the brand (1 sentence)
If the user has an existing tagline, evaluate it and include it in the comparison.
Recommended: Flag the strongest option with a brief explanation of why.
04 — MESSAGING HIERARCHY
Structure the full messaging architecture:
Level 1 — Brand Headline (for hero sections, first impressions): [One punchy headline that captures the core promise]
Level 2 — Supporting Statement (the 1–2 sentence expansion): [Expands the headline with specificity and audience connection]
Level 3 — Key Messages (3–4 proof pillars): Each message:
- Message (bold claim, 5–8 words)
- Supporting copy (2 sentences expanding the claim)
- Proof point (one specific fact, feature, or example that makes it credible)
Level 4 — Proof Points (a bank of 6–8 specific facts): [List concrete claims: stats, features, credentials, social proof]
05 — AUDIENCE-SPECIFIC MESSAGING
If there are multiple audiences, adapt the core messaging for each:
For [Primary Audience]:
- What they care most about:
- How to lead the message:
- Proof points that land hardest for them:
- Avoid:
For [Secondary Audience]:
- [Same structure]
06 — MESSAGING BY CHANNEL
How the core message adapts across touchpoints (tone shifts, length shifts — core message stays consistent):
| Channel | Headline approach | Tone | Length |
| Website hero | [direction] | [tone] | [short/medium] |
| Social bio | [direction] | [tone] | [very short] |
| Email subject lines | [direction] | [tone] | [short] |
| Sales deck | [direction] | [tone] | [medium] |
| Paid ads | [direction] | [tone] | [very short] |
07 — THINGS NOT TO SAY
Common messaging mistakes for this category or brand:
- Claims without proof
- Industry clichés to avoid
- Competitor-adjacent language that creates confusion
- Anything that contradicts the positioning
Related Skills
- brand-positioning: The strategic territory this messaging should express
- brand-voice: Voice and tone to write this messaging in
- brand-story: Origin narrative that can inform key messages
- brand-guidelines: Where this messaging framework gets documented
- brand-context: Foundation context for all brand work
Other versions5 projects use a version of this.
Word for word · 1
- xeroc/skills★ 1100% same
Edited · 2
- cofoundy/brand-skills★ 6799% same
- productionx-in/Core-Skills★ 197% same
Wrote their own version · 2
- jgerton/brand-toolkit★ 64same name
- astDeniss/business-skills★ 8same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository36 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- brand-architectureSkill
- brand-auditSkill
- brand-contextSkill
- brand-guidelinesSkill
- brand-identitySkill
- brand-initSkill
- brand-positioningSkill
- brand-storySkill
- brand-strategySkill
- brand-voiceSkill
- competitor-brandingSkill
- namingSkill
- rebrandingSkill
- target-audienceSkill
- briefSkill
- capacitySkill
- commsSkill
- decideSkill
- evalSkill
- experimentSkill
- exposureSkill
- forecastSkill
- negotiateSkill
- onboardSkill
- optionsSkill
- planSkill
- premortemSkill
- reconSkill
- reviewSkill
- sitrepSkill
- stakeholdersSkill
- strategySkill
- systemsSkill
- threatSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

