CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

assistant-ui-setup

Installs and configures assistant-ui with the `assistant-ui` CLI (`create`, `init`, `add`, `update`, `upgrade`, `codemod`, `doctor`, `info`, `mcp`, `agent`) and picks the runtime adapter for a backend. Use for first-time install (`npx assistant-ui@latest create`, templates, `--example` scaffolds), adding to an existing Next.js app (`init`), or keeping an install current. Covers the runtime hook per backend: `useChatRuntime` (AI SDK v7), `useLangGraphRuntime`, `useStreamRuntime` (LangChain), `useAdkRuntime`, `useA2ARuntime`, `useAgUiRuntime`, `useEveAgentRuntime`, `useOpenCodeRuntime`, `useLocalRuntime`, `useExternalStoreRuntime`, `useDataStreamRuntime`, and `useAssistantTransportRuntime`, plus wiring guides for Mastra, Cloudflare Agents, Claude Managed Agents, LLM gateways, and Electron, the Expo (`--native`) and React Ink (`--ink`) scaffolds, and the hosted MCP docs server. Once a runtime exists, use elements for the styled Thread, runtime for hooks and adapters, and update for a deep migration.

76

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

93%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-engineered overview body: purely actionable commands, situation-keyed decision tables, and a gotchas section that doubles as error-recovery guidance, with per-backend detail correctly pushed to existing one-level-deep references. The only gap is the absence of an explicit post-install verification checkpoint in the create/init workflow.

Suggestions

Add an explicit post-install verification step to the create/init flow (e.g., run `npx assistant-ui@latest doctor` to confirm no version drift or misconfiguration) to close the workflow's only validation gap.

In the 'Pick a runtime' section, note that `assistant-ui doctor` output (installed `@assistant-ui/*` versions) can confirm the chosen adapter's package installed correctly, tying the workflow's endpoint to an existing checkpoint command.

DimensionReasoningScore

Conciseness

Dense command tables and gotchas with zero explanations of concepts Claude already knows; every row carries a decision-relevant fact (e.g., 'There is no `langgraph` template; the LangGraph-backed starter is `langchain`'), and version-specific notes are confined to deprecation/gotcha guidance where they belong.

5 / 5

Actionability

Copy-paste-ready commands throughout ('npx assistant-ui@latest create my-app -t cloud-clerk', 'create my-app --native'), full flag documentation ('-y, --yes` skips the confirmation prompt (use it in CI or an agent shell)'), and error-message-keyed fixes like 'Pass `-o, --overwrite` deliberately... a plain `add` skips a file that already exists.'

5 / 5

Workflow Clarity

The 'CLI decision flow' section sequences situation → command and 'Pick a runtime' maps backend → hook → reference, while the gotchas act as feedback loops (e.g., 'Registry install fails mid-`create`... rerun the printed retry command'). However, there is no explicit post-install validation step (e.g., run `doctor` after `create`/`init` to confirm the install), a minor checkpoint gap that fits the 'most checkpoints present' anchor rather than the explicit-validation anchor.

4 / 5

Progressive Disclosure

All 16 references listed with one-line descriptions exist in ./references/, are one level deep, and the body stays a decision hub — per-backend detail is delegated (e.g., langgraph.md covers 'streaming, interrupts, message editing, threads, agent state') rather than inlined; the backend→hook→reference tables make navigation trivial.

5 / 5

Total

19

/

20

Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

An exemplary description: it names the tool, enumerates its concrete subcommands, states explicit 'Use for' triggers covering new installs, existing-app integration, and maintenance, and cleanly routes adjacent needs to sibling skills. Every clause carries decision-relevant information with no padding.

DimensionReasoningScore

Specificity

Lists many concrete actions in third person — 'Installs and configures assistant-ui with the `assistant-ui` CLI (`create`, `init`, `add`, `update`, `upgrade`, `codemod`, `doctor`, `info`, `mcp`, `agent`)' plus 'picks the runtime adapter for a backend' — comprehensively covering the skill's scope with no vague filler.

5 / 5

Completeness

Explicitly answers what ('Installs and configures assistant-ui with the `assistant-ui` CLI... and picks the runtime adapter for a backend') and when ('Use for first-time install..., adding to an existing Next.js app (`init`), or keeping an install current') with concrete trigger phrases.

5 / 5

Trigger Term Quality

'Use for first-time install', 'adding to an existing Next.js app (`init`)', 'keeping an install current' plus the command names (create, add, update, upgrade) are exactly what a user would say, with synonym coverage (install/create/scaffold, update/upgrade/migrate).

5 / 5

Distinctiveness Conflict Risk

Clear niche (assistant-ui CLI setup and runtime-adapter choice) with explicit de-confliction against sibling skills: 'Once a runtime exists, use elements for the styled Thread, runtime for hooks and adapters, and update for a deep migration.'

5 / 5

Total

20

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 19 suspicious

Warning

Total

15

/

16

Passed

Repository

stevenknowswhy/ProfessionalBuyer

Path

.claude/skills/assistant-ui-setup/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.