brand-worldbuilding
Skill2 starsChanged 2 months agoMITView on GitHub
Turn strategy and identity into a living world — recurring behaviors, rituals, environments, narrative patterns, product moments, and cultural cues that make a brand recognizable through what it does. Use when a brand has correct assets but no presence, when every campaign restarts from zero, or when the identity works on a page but has nothing to say in space, time, or interaction. Produces a brand world with pillars, signature behaviors, and campaign translation rules.
We split this skill into the rules it gives an agent
8 rules. About 0 are common, 8 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈8
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 10
Use when a brand has a competent identity and still feels like nothing in particular.
- Distinctive: line 15
Do not use it as a substitute for strategy or identity.
- Distinctive: line 27
If the strategy or the recognition map is missing, ask before building.
- Distinctive: line 92
Never assert that a cultural reference, symbol, ritual, color, or practice is appropriate, welcome, or safe to use.
- Distinctive: line 96
Never claim a ritual or behavior will create community, loyalty, or belonging.
- Distinctive: line 108
Subtraction test: Remove the decorative cues.
- Distinctive: line 112
Boundary test: Ask what this world would refuse to do.
- Distinctive: line 115
Fresh-eyes pass: Read the output as someone who must act on it and was not in the process.
≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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
Brand Worldbuilding
When to use this
Use when a brand has a competent identity and still feels like nothing in particular. Use when campaigns keep reinventing the brand because there is nothing to build on between them. Use when the brand needs to exist in environments, events, product moments, community, and time — places a static identity system has no instructions for.
Do not use it as a substitute for strategy or identity. A world built on an undecided strategy becomes elaborate decoration, and elaborate decoration is harder to remove than plain decoration.
Inputs
The position, promise, and distinctive mechanism. The chosen territory. The verbal system's character and narrative patterns. The identity system's recognition map — specifically which elements are load-bearing, so the world is built on cues that actually carry.
Also: what the organization can sustain. A ritual nobody will maintain is worse than none, because its abandonment is visible.
If the strategy or the recognition map is missing, ask before building. A world assembled on assumed foundations is elaborate decoration, and elaborate decoration is harder to remove later than plain decoration.
Mission
Make the brand recognizable through behavior and atmosphere, not only through assets.
A world is a grammar for inventing, not a library for repeating. Its purpose is that future work becomes easier to originate and harder to mistake for someone else's.
Method
- State the world thesis. What belief does this world make tangible, and what would it feel like to be inside it? One paragraph, derived from the strategy.
- Establish 3–5 pillars. Each needs a strategic reason to exist. A pillar that exists because the world felt thin is decoration with a heading.
- Give each pillar behavior across visual, verbal, interaction, environmental, community, and ritual dimensions. Behavior means something someone does or encounters, not an attribute.
- Build the signature behavior library. Things that can repeat without becoming repetitive — how the brand opens, how it acknowledges, how it hands over, how it celebrates, how it apologizes.
- Design rituals. Recurring actions that create memory or belonging. Name who sustains each one and what it costs to keep. Rituals are operating commitments, not ideas.
- Define narrative patterns. The shapes of story this brand naturally tells, and the shapes it does not.
- Set boundaries. What the world permits, what it rejects, and which cultural references require context, adaptation, permission, or exclusion.
- Translate to campaigns. How a campaign enters this world without replacing it. Then invent three future campaigns and two product moments to prove the grammar generates.
What must be established
Which behaviors a customer would recognize without being told the brand's name. Behavior-carried recognition is the point; if all recognition still routes through visual assets, the world is ornamental.
For every ritual and recurring behavior: the owner, the cadence, and the cost. Worldbuilding fails in operations far more often than in imagination.
Strong versus merely atmospheric
| Merely atmospheric | Strong |
| A mood, richly described | Behaviors someone could perform next Tuesday |
| Lore documented and never used | A grammar the next campaign is built from |
| Every campaign looks the same | Campaigns differ; the underlying logic is recognizable |
| Cultural references as texture | Cultural references with context, permission, and a boundary |
| Rituals invented in a workshop | Rituals with a named owner and a sustainable cost |
| Recognition through the palette | Recognition through what the brand does when something goes wrong |
The world is real when someone can invent new work inside it that surprises you and still belongs.
Failure modes
- Turning culture into aesthetic texture — extracting the look of a community's practice while discarding its meaning, without relationship, context, or permission.
- Creating lore nobody uses. If it does not shape a decision, it is fan fiction about a client.
- Forcing every campaign into the same art direction and calling it a world. That is a template.
- Confusing a moodboard with worldbuilding.
- Designing rituals the organization cannot sustain, so the world visibly decays.
- Building on decorative cues rather than recognition-bearing ones, producing a world that disappears when the decoration is refreshed.
Never claim without evidence
Never assert that a cultural reference, symbol, ritual, color, or practice is appropriate, welcome, or safe to use. Name what requires review and who must review it — people from within that culture and context, not the project team's judgment.
Never claim a ritual or behavior will create community, loyalty, or belonging. State the mechanism and what you would look for to know whether it took hold.
Output
Produce brand-world.md using the structure in references/brand-world.md.
Verification
- Generation test. Invent three future campaigns and two product experiences without copying current executions. Check that the same underlying grammar is visible in all five. If they only share a palette, you have a style, not a world.
- Subtraction test. Remove the decorative cues. Ask whether the world still has a strategic identity or was resting on ornament.
- Sustainability test. For each ritual and recurring behavior, name the owner and the annual cost. Cut what nobody will carry.
- Boundary test. Ask what this world would refuse to do. A world with no refusals has no shape.
- Counterfactual pass. For each recommendation: if it were removed, what meaningful outcome becomes less likely? No credible answer means cut it, downgrade it, or reframe it.
- Fresh-eyes pass. Read the output as someone who must act on it and was not in the process. Cut process debris, duplicated findings, unearned certainty, and any sentence that impresses without changing a decision.
Complete when
Creators have a recognizable world to work inside, with enough room to surprise people, and every recurring commitment has an owner who has agreed to it.
Handoff
Brand Governance classifies which world behaviors are core and which are flexible, and inherits the ownership and cadence recorded here. Brand Critic tests whether shipped work still belongs to this world or has drifted into generic category behavior. Brand Ship checks that the rituals and behaviors promised here are actually resourced before launch.
In this repository11 other files it gives its agents.
- brand-architectSkill
- brand-criticSkill
- brand-governanceSkill
- brand-intelligenceSkill
- brand-namingSkill
- brand-reviewSkill
- brand-shipSkill
- brand-strategySkill
- identity-systemSkill
- positioning-forgeSkill
- verbal-identitySkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
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.

