ui-business-apps
Skill0 starsChanged 4 months agoMITView on GitHub
Applies owner priorities and original design skills to working dashboards, CRM, ERP and admin screens.
We split this skill into the rules it gives an agent
9 rules. About 0 are common, 7 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈7
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Use this owner profile for working product screens.
- Distinctive: line 28
Use native Product Design, Figma or Superdesign for an explicitly requested workflow they support, including their prerequisites.
- Distinctive: line 33
Use UI UX Pro Max for targeted UX, chart or stack lookup against the actual business brief.
- Distinctive: line 40
Start from the actual role, task and product objects.
- Distinctive: line 46
Treat form validation, dirty state, save progress, failure and recovery as product behavior.
- Distinctive: line 49
Keep KPI labels, units, periods, chart encoding and refresh/stale state tied to real data contracts.
- Very specific: line 56
Use templates/business-ui-brief.md from the repository or installed Bible current/ snapshot when the brief needs durable product …
- Distinctive: line 65
Follow original runtime procedures only within the authorized UI task and host execution boundary.
- Very specific: line 70
Use be skills check and be skills update for reviewed author updates.
≈ “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
Business Application UI Policy
Use this owner profile for working product screens. Preserve the original author trees unchanged; this profile holds personal constraints and selection guidance, not an extracted author design workflow.
Author Selection
Select one primary provider and at most one support when it resolves a distinct
need. Read the provider's complete SKILL.md and required references from the
current-session catalog. Reviewed files and native plugins keep their own update
ownership; disk installation alone does not establish exposure.
| Task | Original provider |
| Dense working screens, application identity, design-system consistency | interface.interface-design |
| Specific UI pattern, chart, typography or stack research | uipro.ui-ux-pro-max |
| UX shape, critique, audit, polish or hardening | impeccable.impeccable, with the matching author reference and Operate mode |
| Analytics and visualization are the main deliverable | build-web-data-visualization:data-visualization |
| Frontend implementation | build-web-apps:frontend-app-builder |
| Existing shadcn composition or React/Next.js performance | The corresponding exposed build-web-apps:shadcn or build-web-apps:react-best-practices leaf |
Use native Product Design, Figma or Superdesign for an explicitly requested workflow they support, including their prerequisites. Missing providers remain unavailable until reviewed dependency or official plugin setup and host exposure are established; do not replace them with a Bible summary.
Use UI UX Pro Max for targeted UX, chart or stack lookup against the actual business brief. A generic product-category result or automatic CRM design-system output is not an authority for a working application; keep the verified task, table and data requirements as the source of truth.
Owner Priorities
- Start from the actual role, task and product objects. Preserve an existing design system when it fits the requested scope. Do not invent screens, workflow steps, business metrics or access rights for visual completeness.
- Make relevant list, detail and edit tasks usable at the intended density. Include filters, saved views, bulk actions or drill-down only when the product requires them; do not add a generic dashboard card grid by default.
- Treat form validation, dirty state, save progress, failure and recovery as product behavior. Make permissions and unavailable actions understandable without claiming client UI enforces authorization.
- Keep KPI labels, units, periods, chart encoding and refresh/stale state tied to real data contracts. Label fixtures as demonstration data. Support the loading, empty and error states relevant to the actual task.
- Preserve readable density, keyboard and focus behavior, accessible semantics and responsive usability on the supported devices. Decoration must support scanning and task completion.
Use templates/business-ui-brief.md from the repository or installed Bible
current/ snapshot when the brief needs durable product constraints; omit
irrelevant sections and record unknowns.
An existing screen or design system can provide visual direction without
generated images or a fresh approval step for every change.
Scope And Evidence
Installing author files does not run launchers, hooks, setup or authentication. Follow original runtime procedures only within the authorized UI task and host execution boundary. Selecting a native design workflow does not authorize uploading private customer data, creating external connections or publishing.
For Bible-managed Impeccable invocations, set IMPECCABLE_NO_UPDATE_CHECK=1.
Use be skills check and be skills update for reviewed author updates; do not
run npx impeccable update over a Bible-managed tree. Resolve author command
path placeholders, including Pro Max's CLAUDE_PLUGIN_ROOT, against the verified
provider installation returned by the route. Pro Max --persist or --force
applies only when the requested task calls for writing those project artifacts.
Choose ui-qa evidence for the requested slice: rendered supported layouts and
the affected list/form/navigation/data states. Preserve artifact pointers,
actual checks and unresolved gaps. Screenshots prove appearance; interaction
and data checks establish the relevant behavior. Reuse this route on same-task
follow-ups instead of rerouting or reloading unchanged instructions.
In this repository62 other files it gives its agents.
- AGENTS.mdAGENTS.md
- accessibility-ui-reviewSkill
- agent-retrospectiveSkill
- agents-md-retrospectiveSkill
- agent-squadSkill
- architecture-mapSkill
- architecture-normalizerSkill
- architecture-principlesSkill
- authz-boundary-reviewSkill
- c-cppSkill
- code-qualitySkill
- code-reviewSkill
- code-to-figmaSkill
- code-wiki-ruSkill
- context-packSkill
- core-engineeringSkill
- debuggingSkill
- dependency-advisory-auditSkill
- deserialization-parser-reviewSkill
- design-system-extractorSkill
- documentationSkill
- engineering-standardsSkill
- esp32Skill
- esphomeSkill
- external-agent-pack-auditSkill
- fastSkill
- figma-to-codeSkill
- fix-security-findingSkill
- goSkill
- homeassistantSkill
- mcp-tool-routerSkill
- migration-plannerSkill
- mobile-qaSkill
- multi-agent-pr-reviewSkill
- performanceSkill
- playwright-visual-qaSkill
- pythonSkill
- quality-gatesSkill
- refactoringSkill
- responsive-breakpoint-checkSkill
- review-routerSkill
- rustSkill
- secrets-and-config-reviewSkill
- security-diff-reviewSkill
- security-routerSkill
- securitySkill
- session-memorySkill
- specialist-dispatchSkill
- subagent-result-mergeSkill
- supply-chain-reviewSkill
- tdd-guardSkill
- testing-tddSkill
- threat-modelSkill
- typescriptSkill
- ui-buildSkill
- ui-concept-firstSkill
- ui-figmaSkill
- ui-qaSkill
- ui-researchSkill
- ui-routerSkill
- The first 60 shown.
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.

