design-register-bootstrap
Skill16 starsChanged 5 months agoMITView on GitHub
Establish frontend design context before implementation, including creator intent and preserve-theirs constraints. Use when a project lacks a clear PRODUCT.md or DESIGN.md, when the model needs to distinguish brand surfaces from product UI, or when design direction keeps drifting because audience, intent, register, anti-references, and visual constraints are not explicit.
In this repository94 other files it gives its agents.
- agent-friction-ledgerSkill
- agent-learning-layer-triageSkill
- agent-operations-contractSkill
- agents-best-practicesSkill
- agent-tool-contract-reviewSkill
- anti-slop-reviewSkill
- architecture-deepening-reviewSkill
- assumption-excavationSkill
- authorized-security-routerSkill
- book-to-skillSkill
- bounded-evaluationSkill
- bounded-growth-loopSkill
- bounded-orchestration-contractSkill
- brief-first-executionSkill
- browser-verificationSkill
- bug-evidence-protocolSkill
- codex-review-loopSkill
- compaction-survivalSkill
- complexity-optimizerSkill
- confidence-fragility-reviewSkill
- context-degradation-reviewSkill
- corporate-surfaceSkill
- delivery-baseline-auditSkill
- delivery-preflight-gateSkill
- design-critique-polishSkill
- designmd-brand-kitSkill
- diagnoseSkill
- doc-grounded-grillingSkill
- doc-to-lora-evaluatorSkill
- durable-context-maintenanceSkill
- dynamic-workflow-packetsSkill
- editorial-surfaceSkill
- evidence-ledger-researchSkill
- filesystem-context-disciplineSkill
- fluid-interaction-reviewSkill
- frontend-product-builderSkill
- frontend-taste-layerSkill
- git-native-context-contractSkill
- goal-loop-designerSkill
- graph-guided-code-readingSkill
- handoffSkill
- happy-handoffSkill
- html-brief-artifactSkill
- html-diagram-artifactSkill
- hypothesis-diversificationSkill
- idea-to-ship-gatesSkill
- knowledge-base-enrichmentSkill
- lean-context-layoutSkill
- local-inference-tuningSkill
- loop-hardening-contractSkill
- loopops-protocolSkill
- loop-readiness-reviewSkill
- lottie-motion-builderSkill
- minimal-diff-builderSkill
- motion-review-gateSkill
- overengineering-reviewSkill
- personal-workspace-routerSkill
- phase-spec-executionSkill
- pipeline-readiness-gateSkill
- plan-to-issuesSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
12 rules. About 0 are common, 11 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈11
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 30
Do not treat these as interchangeable.
- Distinctive: line 37
Write a compact design register:
- Distinctive: line 49
If context files are missing, create or update:
- Very specific: line 54
Ask one clarifying question only when either the branch between brand and product is genuinely unclear or creator intent is too vague to …
- Distinctive: line 57
Use the register as a constraint system for later frontend work.
- Distinctive: line 61
When working inline, summarize:
- Distinctive: line 73
When creating files, prefer concise machine-usable docs over long essays.
- Distinctive: line 80
Do not default every warm or “premium” brief to beige paper backgrounds.
- Distinctive: line 81
Do not default every technical product to dark mode.
- Distinctive: line 82
Do not choose palette or typography before writing the surface classification.
- Distinctive: line 83
If existing project tokens are coherent, preserve them and document them instead of replacing them.
- Distinctive: line 84
If the repo already has a stable design system, this skill should describe and reinforce it, not invent a second one.
≈ “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
Design Register Bootstrap
Set the design register before styling anything substantial.
This skill exists for cases where the model is about to generate UI from vague vibes, default templates, or half-remembered brand intent.
Use For
- new frontend projects without
PRODUCT.mdorDESIGN.md; - redesigns where the surface is unclear: marketing brand page vs. app/product UI;
- teams that keep getting mismatched typography, palette, density, or motion across tasks;
- sessions where the agent should create or refresh design context before implementation.
Core Rule
Classify the surface first:
brand: marketing site, landing page, portfolio, campaign, editorial page, investor page, event page;product: dashboard, admin UI, internal tool, settings, onboarding flow, forms, data-heavy app shell.
Do not treat these as interchangeable. Brand surfaces can lead with identity and emotion. Product surfaces must optimize comprehension, workflow, and control clarity.
Workflow
- Read current evidence:
- project files, CSS tokens, component library, screenshots, references, user brief;
- any existing
PRODUCT.md,DESIGN.md, brand notes, or design tokens.
- Write a compact design register:
- surface type:
brandorproduct; - audience;
- first-screen job;
- creator intent: what the person is actually trying to make possible;
- preserve-theirs: what must remain recognizably theirs;
- brand/product lane;
- anti-references: what this should explicitly not resemble;
- color strategy: restrained, committed, full palette, or drenched;
- typography direction;
- motion tolerance;
- density and radius rules.
- surface type:
- If context files are missing, create or update:
PRODUCT.mdfor audience, product lane, workflow, tone, creator intent, preserve-theirs, and anti-references;DESIGN.mdfor colors, typography, spacing, component patterns, creator intent, preserve-theirs, and do/don't rules.
- Ask one clarifying question only when either the branch between
brandandproductis genuinely unclear or creator intent is too vague to guide a real design choice. If neither blocks a real choice, move. - Use the register as a constraint system for later frontend work. Do not restyle pages in the same pass unless the task explicitly includes implementation.
Output Shape
When working inline, summarize:
registeraudiencecreator intentdesign thesispreserve-theirsanti-referencescolor strategytypography directionmotion and density
When creating files, prefer concise machine-usable docs over long essays.
Guardrails
- Skip this skill when an existing design register is coherent and the task only needs implementation or a narrow visual fix; preserve the existing context instead of recreating it.
- Do not default every warm or “premium” brief to beige paper backgrounds.
- Do not default every technical product to dark mode.
- Do not choose palette or typography before writing the surface classification.
- If existing project tokens are coherent, preserve them and document them instead of replacing them.
- If the repo already has a stable design system, this skill should describe and reinforce it, not invent a second one.
Final Report
Include:
- whether the surface was classified as
brandorproduct; - files created or updated;
- unresolved uncertainty;
- downstream skills recommended, such as
frontend-taste-layer,frontend-product-builder, orweb-quality-audit.
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.

