message-map
Skill6 starsChanged 4 months agoMITView on GitHub
Distils the positioning into one core message, three supporting pillars with proof attached to each, and a banned-phrases list, then writes the map into the brief so every future piece of copy ladders to it. Use when content feels scattered, every asset says something different, or new writers keep inventing the message from scratch.
In this repository29 other files it gives its agents.
- ad-scriptsSkill
- battlecardSkill
- brand-voiceSkill
- campaign-debriefSkill
- case-study-writerSkill
- channel-pickerSkill
- cmoSkill
- competitor-teardownSkill
- content-calendarSkill
- creative-briefSkill
- customer-deep-diveSkill
- email-sequenceSkill
- experiment-backlogSkill
- funnel-mapSkill
- hook-factorySkill
- kpi-treeSkill
- landing-pageSkill
- launch-planSkill
- lead-magnet-builderSkill
- marketing-auditSkill
- market-research-sprintSkill
- objection-mapSkill
- offer-builderSkill
- onboardSkill
- positioning-workshopSkill
- pricing-testSkill
- repurposeSkill
- research-to-briefSkill
- weekly-reviewSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
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
- Distinctive: line 24
Run the ladder test on the five most recent pieces of copy or content: which pillar does each ladder up to?
- Very specific: line 25
Write the map into Positioning & message in marketing-brief.md — core message, pillars with proof, banned phrases.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Message Map — one message, three pillars, proof attached
Scattered messaging is expensive: every asset that says something different resets the buyer's memory to zero. A message map fixes the argument once — the one thing the market must believe to buy, the three pillars that make it believable, the proof behind each — so every post, page, and email compounds the same case instead of starting a new one.
Inputs
- A core claim if one exists, or the go-ahead to derive it: $ARGUMENTS
- From
marketing-brief.mdif present: the position sentence (the map inherits it), top pains and desired outcomes, the language bank, and any banned phrases already collected.
Do this
- Pull the position and the customer evidence. The core message is the position translated into the buyer's language — the one sentence the market must believe for buying to become the obvious move.
- Draft the core message as a claim, not a slogan. It should be arguable — something a sceptic could disagree with. If nobody could disagree with it, it says nothing.
- Choose the three pillars. Each answers one of the buyer's core disbeliefs, and each is a claim in its own right:
- "It won't actually work."
- "It won't work for someone like me."
- "It isn't worth the money or the upheaval."
- Attach proof to each pillar: numbers, demonstrations, mechanism explanations, customer results — only proof that actually exists. Where proof is missing, mark the pillar weak and name exactly what would fill it. A pillar without proof is a wish.
- Build the banned-phrases list: category clichés, competitor-owned language, claims reality cannot back, and hype words the audience has learned to scroll past.
- Run the ladder test on the five most recent pieces of copy or content: which pillar does each ladder up to? Anything that ladders to nothing is either off-message or evidence of a missing pillar — decide which.
- Write the map into Positioning & message in
marketing-brief.md— core message, pillars with proof, banned phrases. Inside Claude Code, the message-architect agent runs the deep version of this pass.
Output
A one-page message map — the core message, three pillars each with claim, proof, and the disbelief it answers, plus the banned-phrases list — saved into marketing-brief.md. Name the weakest pillar and the proof that would fix it.
Rules
- One core message. A brand carrying two core messages is carrying zero.
- Proof that does not exist yet is a to-do, never a claim. Ship the map with the gap visible.
- Pillars answer disbeliefs, not describe features. "Fast onboarding" is a feature; "you will not lose a quarter to switching" answers a fear.
- The map speaks the buyer's language. Pull phrasing from the language bank, not the boardroom.
- The map is a filter, not a suggestion. Copy that cannot find its pillar gets rewritten or killed.
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.

