core
Build Typed UI Specifications with json-render
AI-generated interfaces need consistent schemas, state bindings, and validation. This skill guides assistants through json-render core APIs for catalogs, prompts, streaming, and specification repair.
Installer avec mon Agent
Copiez cette demande dans votre Agent. Elle contient la page Skill de référence et le manifeste.
Review the Skillstore skill "core" from https://skillstore.io/skills/vercel-labs-core.md and its manifest at https://skillstore.io/api/skills/vercel-labs-core/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.Votre Agent doit toujours présenter son plan et demander toute confirmation exigée par la politique de sécurité.
Ressources lisibles par les agents
Utilisez ces liens lorsqu’un Agent IA, un crawler ou un script a besoin d’un contexte propre au lieu de lire toute la page.
Tester
Utilisation de « core ». Explain how to connect an email field to nested form state.
RĂ©sultat attendu:
- Bind the input value to the nested email path using a two-way state binding.
- Read that same nested path in the submit action binding.
- A bare email field name does not search nested form state.
- Validate and authorize the action in the application handler.
Utilisation de « core ». Describe a cautious repair workflow for a generated specification.
RĂ©sultat attendu:
- Run structural validation and inspect each reported issue.
- Apply lossless fixes first and retry generation when required.
- Review lossy fixes before pruning dangling child references.
- Validate the repaired specification again before rendering.
Utilisation de « core ». Explain what information the experimental evaluator receives.
RĂ©sultat attendu:
- The evaluator receives candidate descriptions, prompts, instructions, topology, and explicit context.
- Initial state and raw property or binding values are not sent automatically.
- Keep Gateway credentials on the server and exclude sensitive information from descriptions and context.
Audit de sécurité
SûrAll 88 static findings are false positives: Markdown delimiters, documented server-side authentication, and application-state terminology do not establish the reported threats. No evidence found of prompt injection, unauthorized credential disclosure, or shell execution in SKILL.md. Evaluator requests intentionally transmit described composition inputs; downstream package implementations were not included in this review.
Facteurs de risque
⚙️ Commandes externes (50)
🔑 Variables d’environnement (3)
Partager et citer ce rapport
Partagez le rapport d’évaluation versionné, le badge neutre, la carte intégrable et les citations. Skillstore présente les preuves sans décider si ce Skill est sûr.
Copier le lien du rapport
https://skillstore.io/skills/vercel-labs-core/audits/1?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportBadge Markdown
[](https://skillstore.io/skills/vercel-labs-core?utm_source=security_passport_badge)Badge HTML
<a href="https://skillstore.io/skills/vercel-labs-core?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/vercel-labs-core/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Carte intégrable
<iframe src="https://skillstore.io/embed/skills/vercel-labs-core.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>Citations académiques (APA · BibTeX · CFF)
Citation APA
vercel-labs. (2026). core security audit report (audit version 1) [Author version unspecified]. Skillstore. https://skillstore.io/skills/vercel-labs-core/audits/1Citation BibTeX
@techreport{vercel-labs-vercel-labs-core-2026,
author = {vercel-labs},
title = {core security audit report (audit version 1)},
institution = {Skillstore},
year = {2026},
number = {1},
url = {https://skillstore.io/skills/vercel-labs-core/audits/1},
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: "core security audit report (audit version 1)"
version: "unspecified"
type: report
authors:
- name: "vercel-labs"
date-released: "2026-09-29"
url: "https://skillstore.io/skills/vercel-labs-core/audits/1"
identifiers:
- type: other
value: "skillstore:vercel-labs-core:audit:1"
description: "Skillstore immutable audit report identifier"
Score Skillstore
Pourquoi ce score Niveau de confiance des preuves: MoyenCe que vous pouvez créer
Define a reusable component catalog
Frontend developers can structure component properties and catalog prompts for consistent AI-generated interfaces.
Integrate progressive specification generation
AI application engineers can plan JSONL streaming, refinement prompts, and validation before rendering generated specifications.
Connect forms to shared state
Design system maintainers can standardize form bindings, visibility rules, validation checks, and external state store adapters.
Essayez ces prompts
Explain schemas, catalogs, specifications, and SpecStream in json-render. Use a small contact form as the example and identify the packages I need.
Define a json-render schema and catalog for Button and TextInput components. Include Zod property constraints and show how catalog.prompt generates instructions.
Review my supplied form specification for state binding, visibility, and cross-field validation issues. Propose lossless repairs first and explain any changes requiring lossy fixes.
Design server-side experimental composition using my supplied catalog and atomic candidates. Include batch creation, sequential edits, evaluation budgets, cancellation, and partial snapshot handling. Identify evaluator data exposure and runtime action authorization requirements.
Bonnes pratiques
- Validate generated specifications and review lossy repairs before rendering; separately validate and authorize runtime actions.
- Keep evaluator credentials server-side and minimize sensitive data in descriptions, prompts, and explicit context.
- Pin experimental package versions when published, set evaluation limits, and supply an overall abort signal.
Éviter
- Treating schema validation as proof of semantic completeness or permission to execute actions.
- Using repeat, watch, computed, template, or conditional properties in the experimental composition subset.
- Assuming a catalog alone supplies configured candidate values, bindings, and rendering implementations.
Foire aux questions
Which assistants can use this skill?
Does this skill install json-render or render an interface?
Are the experimental composition APIs stable?
What information leaves the application during Gateway evaluation?
What should I check when form values do not resolve?
Does specification validation secure action execution?
Détails du développeur
Auteur
vercel-labsLicence
MIT
RĂ©vision Skillstore
r1
Avis de version
L’auteur n’a déclaré aucune version.
DĂ©pĂ´t
https://github.com/vercel-labs/json-render/tree/c2600d73908ed505e6d726f5b6f969ba8f597ce7/skills/coreRĂ©f
bad9dafc37d1638cd29cb9bab06d5f8dbcd0f6c2
RĂ©cence de maintenance
30/09/2026
Utilisation
0 téléchargements · 0 vues
Structure de fichiers
đź“„ SKILL.md