ui-library-router
Skill1 starsChanged 3 months agoMITView on GitHub
Choose among Kokonut UI, React Bits, daisyUI, Bklit UI, Anime.js, Rive, and Magic UI for frontend work. Use for pages, dashboards, landing pages, animation, data visualization, or interactive graphics; do not use when no UI/library choice is involved.
In this repository7 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- ui-orchestratorSkill
- ui-quality-auditSkill
- ui-library-routerSkill
- ui-orchestratorSkill
- ui-quality-auditSkill
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
- Very specific: line 14
Never select all seven by default.
- Distinctive: line 18
Read references/libraries.md when evaluating ecosystem-specific tradeoffs.
≈ “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
UI Library Router
Inspect the host before selecting anything: framework, package manager, installed dependency versions, React/Tailwind versions, current design system, components.json, theme tokens, chart/motion dependencies, accessibility constraints and asset rights. Classify each requested feature as base UI, product component, marketing enhancement, data visualization, creative effect, bespoke motion or interactive vector graphics.
Normalize this evidence into HostProfile and TaskProfile before formal selection. When the OrchestrUI MCP is available, call recommend_stack with those structured profiles and retain its role ownership, rejected candidates, rule IDs and evidence. Use task-text inference only when project evidence is genuinely unavailable; do not treat a legacy-text-inference result as equivalent to inspected structured routing.
Choose the smallest set with one owner per major role. Existing systems win unless migration is explicit. Review evidence-bearing candidate rankings for installed reuse, dependency/bundle cost, overlap and bounded version compatibility, but never use score to override a hard compatibility, conflict or asset-rights gate. Use Bklit for data visualization; daisyUI only as an intentional semantic Tailwind base; Kokonut for selective shadcn-compatible product polish; Magic UI for the primary marketing enhancement layer; React Bits for one or two signature creative effects; Anime.js only for bespoke timelines/SVG/scroll work; Rive only for meaningful state-machine graphics with recorded .riv rights.
Never select all seven by default. Do not add daisyUI beside a shadcn-derived base without an explicit isolation or migration strategy. Prefer CSS and component-native motion before Anime.js. Never silently use Pro material or vendor, mirror, bundle, sublicense or redistribute React Bits components from OrchestrUI.
Return: existing stack; selected libraries and role ownership; required components/effects; official retrieval method; rejected redundancies; compatibility/legal risks; and a validation plan. A valid recommendation may select no OrchestrUI library.
Read references/libraries.md when evaluating ecosystem-specific tradeoffs. Read references/selection-workflow.md when producing a formal routing plan.
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.

