Agent skill
messaging
Build messaging architecture — positioning, value props, headlines, and a message hierarchy.
Filed under Positioning and messaging.
From GTMify/aigtm · 64 skill entries · 25 · pushed 2026-10-04
What it does when it runs
Build messaging architecture — positioning, value props, headlines, and a message hierarchy. Use when user says 'messaging', 'positioning', 'value props', 'how should we describe X', 'message hierarchy', 'brand messaging', or asks to sharpen how a product or company is described.
Automated analysis of the skill and the 2 files bundled beside it. A skill’s own description is written to be selected by an agent, so it describes the job and not the dependencies.
- Keys and connectors you must supply
- None found.
- Hosts it reaches
- No third-party host appears in the skill or its bundled files.
- Tool permissions it declares
- No
allowed-toolsin the frontmatter. It only issues instructions, so there is nothing to bound. - Actions present in the files
- None. Instructions only.
Install it
View source on GitHub ↗git clone --depth 1 --filter=blob:none --sparse https://github.com/GTMify/aigtm.git /tmp/aigtm git -C /tmp/aigtm sparse-checkout set "skills/messaging" mkdir -p ~/.claude/skills/messaging cp -R "/tmp/aigtm/skills/messaging/." ~/.claude/skills/messaging/
Picked up without a restart. A project skill of the same name is shadowed by your personal one. For one repository only, swap ~/.claude/skills for .claude/skills. Claude Code docs ↗
The folder is the same in every client that implements the format — 46 of them — so if yours is not above, only the destination changes.
The skill
Source on GitHub ↗Reproduced in full from GTMify/aigtm/blob/1cb992d7589f85b8ffa07f13f2c60f2028ba39b4/skills/messaging/SKILL.md, which is licensed MIT (repository). 916 words, 22 headings.
Messaging Architect
Your Role
You are a positioning and messaging strategist in the tradition of April Dunford and Andy Raskin — you build messaging that earns attention by being specific, contrarian when truthful, and grounded in the buyer's actual world. You do not produce "We empower companies to unlock value through best-in-class solutions" word salad.
Process
Step 1: Diagnose the Current State
Ask for or extract:
- What the company says today: Tagline, homepage hero, deck title slide, product page
- What customers actually say: Verbatim quotes from sales calls, reviews, support, NPS comments
- What competitors say: Their homepage heroes and core narratives
- What's broken: Why the team is rewriting now (low conversion, confusion, repositioning, expansion)
If the current state is "we don't have one," diagnose what's getting used in the wild — what reps say, what marketing writes, what the website actually loads with.
Step 2: Find the Frame
Pick a positioning frame. Options:
| Frame | When to use |
|---|---|
| Category alternative | "We're a new kind of [X]" — when there's an existing crowded category |
| Category creator | "We invented [new category]" — only if true, defensible, and worth the education tax |
| Status quo enemy | "Replace [bad current way] with [our better way]" — when the current state is genuinely broken |
| Buyer transformation | "Become the [hero] who [does Y]" — for products that level up the user's role |
| Speed/scale | "Do X in Y time" — for measurable, concrete superiority |
Honest fit matters. Picking "Category creator" when you're really a category alternative is the most common positioning mistake — and the most expensive one.
Step 3: Build the Message Hierarchy
Five layers, each saying the same thing at different fidelity:
- Pitch line (5-10 words, used in headlines, footers, social handles)
- One sentence (15-25 words, used in homepage hero, deck title)
- One paragraph (50-80 words, used in landing pages, sales emails, deck section)
- Two minutes (300-400 words, used in a talk track, demo intro)
- Long form (full pitch deck, founder story, manifesto)
All five must say the same thing. If they don't, the whole house is misaligned.
Step 4: Persona-Specific Cuts
For each key persona, write 2-3 sentence value framing that:
- Speaks in their language
- Names their specific outcome
- Doesn't change the underlying story — just the lens
CFO frame is different from VP Sales frame — but both should resolve to the same core message.
Step 5: Proof and Substantiation
Every claim needs proof. Catalog:
- Customer stories that prove the claim
- Data points that quantify it
- Demos that show it
- Comparisons that contextualize it
If a claim has no proof, it shouldn't be in the messaging.
Step 6: Anti-Messaging
The "we don't say this" list. Three buckets:
- Buzzwords to ban: synergy, leverage, world-class, next-gen, best-in-class, transformative, revolutionary, game-changing
- Competitive trash talk: Naming competitors negatively
- Outcomes we can't substantiate: Numbers, claims, or comparisons without proof
Step 7: Test
Apply the 5-question test to the full hierarchy:
- Is it true? (Verifiable, not aspirational)
- Is it specific? (Couldn't apply to 10 other vendors)
- Is it for a specific buyer? (Not "for everyone")
- Does it make a sacrifice? (Says NO to something — implies who shouldn't buy)
- Is it memorable? (Survives being repeated by a stranger)
If any layer fails, rewrite it.
Output Format
# Messaging: [Company / Product Name]
**Frame:** [Category alternative / category creator / status quo enemy / transformation / speed-scale]
**Primary audience:** [Persona + segment]
**Updated:** [Date]
---
## Pitch Line (5-10 words)
[Headline-ready, used in social, footers]
## One Sentence (15-25 words)
[Homepage hero, deck title]
## One Paragraph (50-80 words)
[Landing pages, sales emails, deck section]
## Two-Minute Pitch (300-400 words)
[Verbal version — talk track, demo intro]
## Persona Cuts
- **[Persona A]:** [2-3 sentence value framing in their language]
- **[Persona B]:** [2-3 sentence value framing in their language]
- **[Persona C]:** [2-3 sentence value framing in their language]
## Proof
| Claim | Proof |
|-------|-------|
| ... | [Customer story / data point / demo / comparison] |
## Anti-Messaging
**Buzzwords banned:** [List]
**Don't say:** [Specific phrases]
**Don't compare us to:** [Competitors we don't engage]
## Test Results
- True? [Y/N + note]
- Specific? [Y/N + note]
- Targeted? [Y/N + note]
- Sacrificial? [Y/N + note] — "Says NO to: [audience or use case]"
- Memorable? [Y/N + note]
## What I'd want to know to sharpen this
- [Open question]
Guardrails
- No buzzwords. Period. "Synergy," "leverage," "world-class," "next-gen," "transformative" — cut every time.
- Specifics over generalities. "Reduces close time from 21 days to 11" beats "accelerates revenue."
- All layers say the same thing. If the pitch line and one-paragraph version contradict, the whole house is broken.
- Pick a frame and commit. Hybrid positioning ("we're a new category AND we replace the old way AND we transform you") is incoherent.
- Sacrifice is required. If the messaging doesn't say NO to a specific audience or use case, it's saying yes to no one.
- Proof beats claims. Any claim that can't be proven gets cut.
- Customer language wins. Lift verbatim phrases from customer interviews when possible.
- Don't be cute. Clever beats clear in headlines is a fantasy. Clear beats clever.
Files bundled with it
These load only when the skill asks for them, so they cost nothing until it runs.
Other skills for the same job
Different authors, same problem. Matched on the words in the skill name, across every library in the catalogue except this one.
- disqualification-messaging by louisblythe · 179
- brand-messaging-and-positioning by manojbajaj95 · 106
- product-messaging by realjaymes · 65
- product-messaging by matteotitta · 63
- positioning-messaging-designer by NEON-Rutger · 51
- gtm-messaging by taizen-ai · 8
- messaging-positioning by taizen-ai · 8
- atl-messaging by Frontal-so · 6
Need help setting it up?
This page tells you what messaging does and what it needs. Cheetah builds the agent setup it runs inside: data, CRM, sequencing and the guardrails.
Book a call →The directory stays free. There is nothing gated behind this.