design-system-reconnaissance
Skill2 starsChanged 25 days agoApache-2.0View on GitHub
Use when about to create or change any visible UI in a project, such as a 404 page, legal page, consent control, or footer link, to record the design tokens, components, layout patterns, and copy tone already in use so new pieces look native. Do not use it to design a new visual style, to redesign the site, or when no visible UI will be created or changed.
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
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
- Very specific: line 38
Only an optional working note, .readyvibe/design.md: a short list of the tokens, components, behavior patterns, and the component ladder …
≈ “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
design-system-reconnaissance
Fixes that look bolted on erode the trust they were meant to build: a 404 in a different font, a cookie control in someone else's blue, a privacy page with default browser styles. This skill records what already exists so new UI is built from it.
Activate when
- About to add or modify visible UI:
error-pages,privacy-policy/terms-of-servicepages,consent-managementcontrols, footer/nav links, empty/error states, forms. - Skip it when the change is invisible (metadata, robots, headers) or when a fresh, recent
.readyvibe/design.mdexists.
Inspect
- Tokens. CSS variables, Tailwind config (
theme.extend), theme files,tokens.json: colors (brand, neutrals, semantic), type scale and families, spacing, radii, shadows, breakpoints. Note dark-mode handling. - Components. Existing Button, Link, Heading, Container, Card, Dialog, Form field, Footer, Header, Alert. Prefer reuse over new markup. Note variants and how they are composed (Tailwind classes, CSS modules, styled-components, shadcn/ui, MUI).
- Layout patterns. Page shell (header/main/footer), max content width, section rhythm, how text pages (about, blog) are laid out; this is the template for legal pages.
- Voice. Tone and person in existing copy ("we" vs. "Acme"), casing of headings and buttons, punctuation. Legal or policy copy still needs to be clear; match register without adopting jokes in legal text.
- Assets. Logo files, favicon, illustration style, icon set.
- Rendered check. Open the running site at desktop and 375px to see it as visitors do; source can mislead (a component may be overridden).
- The component ladder (write it into your note, and follow it when building): (1) reuse an existing component as is; (2) compose existing components; (3) extend an existing primitive with a variant or prop; (4) only when nothing fits, create a new component that matches the tokens, spacing, and behavior of its neighbors. Never introduce a "ReadyVibe style", and never casually add another UI library, CSS framework, or icon set; if the project already uses one, use it.
- Behavior patterns too, not just looks: how dialogs, menus, forms, validation errors, toasts, loading states, and empty states already behave (focus handling, motion, dark mode, RTL/locale handling); new UI must behave the same way.
Evidence that counts
Label each claim OBSERVED, SOURCE-INDICATED, DECLARED, INFERRED, UNKNOWN, or REVIEW REQUIRED. UNKNOWN is never a pass and never a failure.
- Token in source, but unused or overridden: SOURCE-INDICATED. Confirm in the rendered page.
- A style guide in the docs is DECLARED. If the site diverges, the site's actual look wins for consistency.
May change
Only an optional working note, .readyvibe/design.md: a short list of the tokens, components, behavior patterns, and the component ladder the specialist should use, with file paths. Never product code.
Must not claim
That the site "has a design system" when it has ad-hoc styles; say "no consistent system found; these are the most-used values". Never invent a new palette, typeface, or component library.
Verify
A specialist that follows the notes should produce UI that uses existing tokens and components. After the UI is built, compare it with an existing page at desktop and 375px; the difference should be the content, not the styling.
Escalate
Contradictory styles across the site (three buttons, four grays): note it and pick the dominant one for new UI; flag the inconsistency for the owner instead of "fixing" the whole site.
No change is valid when
The change is not visual, or the project has one page with inline styles you can mirror directly. Then skip the file and match that page.
In this repository54 other files it gives its agents.
- wcag-readinessSkill
- admin-audit-logSkill
- admin-authorizationSkill
- admin-dashboardSkill
- payments-readinessSkill
- subscription-readinessSkill
- ai-features-readinessSkill
- analytics-privacySkill
- consent-managementSkill
- consumer-protection-readinessSkill
- cookie-and-storage-auditSkill
- data-flow-mappingSkill
- data-rightsSkill
- email-complianceSkill
- jurisdiction-applicabilitySkill
- legal-identity-noticesSkill
- minors-readinessSkill
- policy-consistencySkill
- privacy-policySkill
- privacy-readinessSkill
- regulated-domain-triggersSkill
- terms-of-serviceSkill
- third-party-privacySkill
- user-content-safetySkill
- compliance-allSkill
- compliance-diffSkill
- discoverability-allSkill
- launch-allSkill
- launch-verificationSkill
- production-allSkill
- quality-allSkill
- site-reconnaissanceSkill
- trust-allSkill
- search-console-readinessSkill
- seo-readinessSkill
- social-sharingSkill
- structured-dataSkill
- multilingual-readinessSkill
- rtl-readinessSkill
- content-trustSkill
- error-pagesSkill
- failure-resilienceSkill
- faq-readinessSkill
- forms-readinessSkill
- launch-identitySkill
- legal-navigationSkill
- link-integritySkill
- mobile-readinessSkill
- performance-readinessSkill
- public-supportSkill
- dependency-securitySkill
- deployment-cleanupSkill
- security-headersSkill
- web-securitySkill
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.

