ui-sdk-expert-review
Skill4.8k starsChanged 18 days agoApache-2.0View on GitHub
Reviews a change with ui-sdk's framework experts (react, vue, svelte, solid, web), only the ones the change reaches, each from its last reviewed commit. Use before merging a branch that touches an adapter, core, specs, examples or framework docs, or when asked for an expert review. Pass a base ref, framework names, or nothing.
Trending
More talk lately.about the whole repository
Who's talking about vercel-labs/ui
- @druce.ai“Vercel Releases UI SDK: 50+ UI Behaviors for AI Coding Agents”Bluesky · Nov 15, 2026 · 2 likes
- @shun91.bsky.social“AIが生成するUIでアクセシビリティやインタラクション設計が欠落しやすい課題を解決するため、Vercel Labsがエージェント向けヘッドレスUIライブラリを公開。 vercel-labs/ui: A …”Bluesky · Nov 15, 2026 · 2 likes
- @yug1224.com“AIエージェントが新しいUIを構築するためのインタラクション動作を提供するライブラリっぽい 次世代のフロントエンド開発に応用できそうだから試したい yug1224 starred vercel-labs/ui …”Bluesky · Nov 13, 2026 · 2 likes
- @technews4869.bsky.social“github.com/vercel-labs/ui GitHub - vercel-labs/ui: A library of behaviors for agents to build the next …”Bluesky · Nov 13, 2026 · 1 likes
- @tech-trending.bsky.social“GitHub - vercel-labs/ui: A library of behaviors for agents to build the next generation of user interfaces.…”Bluesky · Nov 13, 2026 · 1 likes
The biggest 5 of 23 mentions linking to the repository that our crawl found. Each line is their own headline.
See all 23
Talked about on GitHub and Bluesky (23 times).
On GitHub · 17
- Nov 16, 2026U3756b, U3512d, U2580a: Move the desktop App to Solid 2 and ui-sdk — roundup-app/roundup0 reactions · 2 comments
- Nov 15, 2026Qué ofrece vercel-labs/ui y si sirve para una UI esqueuomórfica vectorial — itsmistermoon/plaid0 reactions · 1 comment
- Nov 15, 2026agent-skills.github.vercel-labs.ui: 0-unstable-2026-11-13 → 0-unstable-2026-11-15 — sudosubin/agents.nix0 reactions
- Nov 14, 2026[EPIC] UIBL — Universal Interface Behavior Layer: architecture, security, adapters, conformance — UniversalStandards/atlantis-ai-enhanced0 reactions
- Nov 14, 2026Add UI SDK (vercel-labs/ui) cheatsheet — luongnv89/awesome-cheatsheets0 reactions
12 more on GitHub
- Nov 14, 2026frontend-design, ux-ax-review: use UI SDK behaviors for interactive parts (beta) — luongnv89/skills0 reactions
- Nov 14, 2026[FEATURE] Index vercel-labs/ui (UI SDK) and its ui-sdk skill — luongnv89/asm0 reactions
- Nov 14, 2026Vercel Labs 'UI SDK' 베타 공개 — 완성 컴포넌트 대신 에이전트가 조립할 행동 50여 개를 주는 라이브러리 (11/12, Vercel 공식) — roomedia/ax-trend0 reactions
- Nov 14, 2026Resolve open design questions in order — asonas/native-ui-sdk0 reactions
- Nov 14, 2026agent-skills.github.vercel-labs.ui: 0-unstable-2026-11-12 → 0-unstable-2026-11-13 — sudosubin/agents.nix0 reactions
- Nov 13, 2026feat(ui): render json-render views in chat via app_ui tool — VinSpee/velvet-hammer0 reactions · 2 comments
- Nov 13, 2026spike(viewer): evaluate UI SDK behaviors for trace navigation and filters — open-ocpp-trace/viewer0 reactions
- Nov 13, 2026UI SDK をいれる — HayatoW/irreversible0 reactions
- Nov 13, 2026Plan documents build every component Astryx lacks on UI SDK, never by hand (owner instruction 29) — 416rehman/Guardrails0 reactions · 2 comments
- Nov 13, 2026agent-skills.github.vercel-labs.ui: init at 0-unstable-2026-11-12 — sudosubin/agents.nix0 reactions
- Nov 13, 2026Trending candidates 2026-11-13-04 — tayyabimam1/awesome-ai-agent-stack0 reactions · 1 comment
- Nov 12, 2026chore(agents): vendor ui-sdk skill as UI guidance (pinned) — tutur3u/platform0 reactions · 3 comments
On Bluesky · 6
- Nov 15, 2026Vercel Releases UI SDK: 50+ UI Behaviors for AI Coding Agents — @druce.ai2 likes and reposts
- Nov 15, 2026AIが生成するUIでアクセシビリティやインタラクション設計が欠落しやすい課題を解決するため、Vercel Labsがエージェント向けヘッドレスUIライブラリを公開。 vercel-labs/ui: A library of behaviors for agents to… — @shun91.bsky.social2 likes and reposts
- Nov 13, 2026AIエージェントが新しいUIを構築するためのインタラクション動作を提供するライブラリっぽい 次世代のフロントエンド開発に応用できそうだから試したい yug1224 starred vercel-labs/ui https://github.com/vercel-labs/ui — @yug1224.com2 likes and reposts
- Nov 13, 2026github.com/vercel-labs/ui GitHub - vercel-labs/ui: A library of behaviors for agents to build the next generation of user ... — @technews4869.bsky.social1 likes and repost
- Nov 13, 2026GitHub - vercel-labs/ui: A library of behaviors for agents to build the next generation of user interfaces.… — @tech-trending.bsky.social1 likes and repost
1 more on Bluesky
- Nov 13, 2026見てる: "vercel-labs/ui: A library of behaviors for agents to build the next generation of user interfaces." https://github.com/vercel-labs/ui — @azu.bsky.social1 likes and repost
In this repository7 other files it gives its agents.
- AGENTS.mdAGENTS.md
- apps/docs/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- ui-sdk-unslopSkill
- ui-sdk-write-codeSkill
- ui-sdk-write-docsSkill
- ui-sdkSkill
The file
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 10
Run the framework experts on what changed.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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-sdk: expert review
Run the framework experts on what changed. Each expert lives in .agents/experts/<framework>/: who it is in expert.md, what it knows in knowledge.md and what's decided in decisions.md. You orchestrate; the experts review.
1. Find the scope
node scripts/expert-scope.mjs --json # each expert from its "Last reviewed" commit
node scripts/expert-scope.mjs --base origin/main --json # a branch before mergingArguments narrow it: a ref becomes --base; framework names keep only those experts. An empty plan means no expert is needed: say so and stop.
Then run each framework's own lint rules on what changed, so the experts spend their review on what a linter can't catch:
git diff --name-only <base>...HEAD | xargs npx eslint --no-warn-ignored2. Ask the experts
Spawn one background agent per framework in the plan, all at once, as <framework>-expert (in a harness without named agents, a general-purpose agent told to read .agents/experts/<framework>/expert.md first and act as it). Prompt:
Review mode. Scope: git diff <base>...HEAD.
Your files: <own>. Shared files every adapter renders: <shared>.
Review your files, and the shared ones only for what a user of your framework would meet.
Don't report anything decisions.md lists, or these lint findings: <findings, or none>.Each expert works in its own worktree when it writes throwaway tests (git worktree add ../ui-sdk-expert-<framework> HEAD), with its own ports.
3. Collect
- One table: framework, verdict, proven findings by rank, suspected, revisit.
- Dedupe across experts: a finding in core that several experts report is one item, listed once, with every framework it reaches.
- Hand the table to the user. Don't fix anything unless asked.
4. After triage
Each finding goes one of three ways, in the same turn:
- Fix now: fix it with its proof as the test.
- Later: one line under "Known and open" in that expert's
decisions.md. - Won't do / decided otherwise: one line under "Settled" in
decisions.md, with the reason, so no expert raises it again.
Then move Last reviewed: in each expert's decisions.md to the reviewed HEAD. If an expert said its knowledge.md was wrong, fix the file and its "Last checked" date.
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.

