Skills agent-ui
📦

agent-ui

Content revision r1 Safe ⚙️ External commands🌐 Network access🔑 Env variables

Build React Agent Interfaces

Agent interfaces require streaming chat, tool states, approvals, and runtime wiring. This skill helps add a React or Next.js agent component with proxy setup, scoped tools, and UI patterns.

Supports: Claude Codex Code(CC)
🥉 78 Bronze

Install with my Agent

Copy this request to your Agent. It includes the canonical Skill page and manifest.

Agent request
Review the Skillstore skill "agent-ui" from https://skillstore.io/skills/inference-sh-agent-ui.md and its manifest at https://skillstore.io/api/skills/inference-sh-agent-ui/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.

Your Agent should still show its plan and request any confirmation required by the security policy.

Agent-readable resources

Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.

Markdown detail GET /skills/inference-sh-agent-ui.md Signed manifest GET /api/skills/inference-sh-agent-ui/manifest Signed lockfile GET /api/skills/inference-sh-agent-ui/lockfile

Test it

Using "agent-ui". Create a basic agent UI for a Next.js dashboard.

Expected outcome:

  • A proxy route setup plan using the inference.sh SDK.
  • A page structure that places the Agent component in the dashboard.
  • A checklist for the API key, model reference, and runtime configuration.

Using "agent-ui". Design an agent that fills a support intake form.

Expected outcome:

  • A scoped tool plan that can inspect fields and propose values.
  • Approval steps before any form value is changed.
  • Interface notes for progress, errors, and final review.

Using "agent-ui". Review my agent UI before production.

Expected outcome:

  • A readiness review for proxy routing, secret handling, uploads, and streaming behavior.
  • A list of missing guardrails and user approval requirements.
  • Suggested documentation updates for operators and developers.

Security Audit

Safe
v6 • 7/9/2026 Open versioned report

Most static findings are false positives caused by Markdown code fences, inline property names, and documentation links. One low-severity supply-chain concern remains because the quick start asks users to fetch a component from a remote registry URL. No prompt injection, secret exfiltration, or malicious intent was found in SKILL.md.

1
Files scanned
124
Lines analyzed
1
Review items
0
False positives ignored
Capability review items (1)

These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.

Low
SKILL.md:20
Hardcoded URL
npx shadcn@latest add https://ui.inference.sh/r/agent.json
The quick-start command asks users to fetch a component from a remote registry URL with npx. It is user-visible, but it creates supply-chain exposure if the remote source changes or is compromised.

Risk Factors

⚙️ External commands (16)
SKILL.md:18-24 SKILL.md:24-30 SKILL.md:30-34 SKILL.md:34-38 SKILL.md:38-41 SKILL.md:41-45 SKILL.md:45-60 SKILL.md:60-75 SKILL.md:75-90 SKILL.md:90-96 SKILL.md:96-97 SKILL.md:97-98 SKILL.md:98-99 SKILL.md:99-100 SKILL.md:100-104 SKILL.md:104-113
🌐 Network access (8)
SKILL.md:14 SKILL.md:20 SKILL.md:117 SKILL.md:118 SKILL.md:119 SKILL.md:120 SKILL.md:121 SKILL.md:123
🔑 Env variables (1)
SKILL.md:40
Audited by: codex View Audit History →
Share & cite this report

Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.

Open versioned report
Security Assessment

Copy report link

https://skillstore.io/skills/inference-sh-agent-ui/audits/6?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/inference-sh-agent-ui/security.svg)](https://skillstore.io/skills/inference-sh-agent-ui?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/inference-sh-agent-ui?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/inference-sh-agent-ui/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/inference-sh-agent-ui.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>
Academic citations (APA · BibTeX · CFF)

APA citation

inference-sh. (2026). agent-ui security audit report (audit version 6) [Author version unspecified]. Skillstore. https://skillstore.io/skills/inference-sh-agent-ui/audits/6

BibTeX citation

@techreport{inference-sh-inference-sh-agent-ui-2026, author = {inference-sh}, title = {agent-ui security audit report (audit version 6)}, institution = {Skillstore}, year = {2026}, number = {6}, url = {https://skillstore.io/skills/inference-sh-agent-ui/audits/6}, note = {Author version unspecified} }

CITATION.cff

cff-version: 1.2.0 message: "If you use this Skill, cite its author and this versioned security audit report." title: "agent-ui security audit report (audit version 6)" version: "unspecified" type: report authors: - name: "inference-sh" date-released: "2026-07-09" url: "https://skillstore.io/skills/inference-sh-agent-ui/audits/6" identifiers: - type: other value: "skillstore:inference-sh-agent-ui:audit:6" description: "Skillstore immutable audit report identifier"

Compare variants

3 installable variants

Each author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.

Why this variant is first

Higher Skillstore usage
inference-sh-9 Recommended

inference-sh-9-agent-ui

Skillstore Score 78
Evidence Confidence High
Skillstore usage 14
Updated

2026-08-21

inference-sh Current

inference-sh-agent-ui

Skillstore Score 78
Evidence Confidence High
Skillstore usage 12
Updated

2026-08-21

inferen-sh

inferen-sh-agent-ui

Skillstore Score 69
Evidence Confidence High
Skillstore usage 6
Updated

2026-08-21

Skillstore Score

Why this score Evidence Confidence: High
55
Architecture
85
Maintainability
87
Content
69
Community
83
Spec Compliance

What You Can Build

Launch a SaaS Copilot

Add a streaming assistant interface with tool progress and approval states inside a product dashboard.

Prototype Agent Workflows

Create a working agent page that connects a proxy route, model configuration, and runtime UI.

Design Form Automation

Plan browser tools that scan form fields, request user approval, and fill values through the agent interface.

Try These Prompts

Add an Agent Screen 
Use the agent-ui skill to add a basic Next.js agent page with a proxy route and environment variable checklist.
Configure Human Review 
Use agent-ui to design an agent interface with approval states for tool actions and clear user controls.
Connect Scoped Browser Tools 
Use agent-ui to plan a form-filling assistant that can scan fields, request approval, and update values safely.
Audit Production Readiness 
Use agent-ui to review my existing agent UI plan for proxy security, API key handling, uploads, and streaming failures.

Best Practices

  • Keep API keys only in server-side environment files and never expose them to browser code.
  • Use explicit approval states before tools change user data or submit forms.
  • Review remote component changes before installing them into a production repository.

Avoid

  • Do not place API keys in client components or public environment variables.
  • Do not enable file or image uploads without size, type, and retention rules.
  • Do not let browser tools update forms without visible user approval.

Frequently Asked Questions

What does this skill help build?
It helps build React and Next.js agent interfaces with streaming, approvals, widgets, and browser tool patterns.
Does it include backend logic?
It points to an inference.sh SDK proxy route, but application teams still own deployment and security.
Does it require an API key?
Yes. The setup example shows INFERENCE_API_KEY as a required server-side environment value.
Can it support human approval flows?
Yes. The documented features include pending states, progress states, approval flows, and tool results.
Can it fill forms in the browser?
The skill shows scoped client-side tools for scanning form fields and filling values through the agent.
Is it specific to inference.sh?
Yes. The examples use inference.sh registry assets, SDK routes, services, and documentation.

Developer Details

License

MIT

Skillstore revision

r1

Version notice

The author did not declare a version.

Repository

https://github.com/inference-sh/skills/tree/main/skills/agent-ui/

Ref

0519034dad657fb1f7706e0550e962beeda73fdf

Maintenance freshness

7/18/2026

Usage

7 downloads · 158 views

File structure

📄 SKILL.md