Fähigkeiten next-dev-loop
📦

next-dev-loop

Inhaltsrevision r1 Niedriges Risiko ⚙️ Externe Befehle🌐 Netzwerkzugriff

Verify Next.js Changes in a Running App

Successful builds do not prove that a Next.js change works in the browser. This skill cross-checks framework diagnostics, visible behavior, and React state during development.

Unterstützt: Claude Codex Code(CC)
Maintain this Skill? Claim it 📊 69 Angemessen

Mit meinem Agent installieren

Kopieren Sie diese Anfrage in Ihren Agent. Sie enthält die maßgebliche Skill-Seite und das Manifest.

Agent-Anfrage
Review the Skillstore skill "next-dev-loop" from https://skillstore.io/skills/vercel-next-dev-loop.md and its manifest at https://skillstore.io/api/skills/vercel-next-dev-loop/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.

Ihr Agent sollte weiterhin seinen Plan anzeigen und alle von der Sicherheitsrichtlinie verlangten Bestätigungen anfordern.

Agent-lesbare Ressourcen

Verwenden Sie diese Links, wenn ein KI-Agent, Crawler oder Skript sauberen Kontext benötigt, statt die vollständige Seite zu lesen.

Testen

„next-dev-loop“ wird verwendet. Verify a successful save after changing the profile page.

Erwartetes Ergebnis:

  • Compilation: no issues reported.
  • Runtime: no framework-reported errors after navigation.
  • Browser: saving displayed the updated profile value.
  • React: component state matched the visible value.

„next-dev-loop“ wird verwendet. Check why a route appears blank after an edit.

Erwartetes Ergebnis:

  • Framework diagnostics reported no compilation issues.
  • The browser session returned an empty snapshot.
  • Reopening the same session restored the expected page.
  • The observed failure came from stale browser state, not the edited route.

„next-dev-loop“ wird verwendet. Verify the app when the required browser CLI is missing.

Erwartetes Ergebnis:

  • Verification stopped because agent-browser was unavailable.
  • The workflow requires agent-browser 0.31.1 or later.
  • Runtime behavior remains unverified until the required browser tooling is available.

Sicherheitsaudit

Niedriges Risiko
v1 • 6.11.2026 Versionsbericht öffnen

Of 74 static findings, 72 are false positives involving Markdown, ordinary diagnostics, documentation links, or local development access. Two findings confirm instructions to install an unpinned global package without an explicit approval step; a separate concern is retained authentication state without cleanup guidance. No evidence found of credential exfiltration, malicious reconnaissance, or audit-directed prompt injection.

1
Gescannte Dateien
213
Analysierte Zeilen
2
Prüfelemente
0
Falschmeldungen ignoriert

Bestätigte Sicherheitsbedenken (1)

Niedrig
Persistent Login State Lacks Cleanup Guidance
The skill says restoration loads saved cookies/localStorage and that close saves cookies and storage for later loops. No consent, retention limit, or deletion guidance accompanies authentication persistence, increasing exposure on shared or compromised development machines.
The instructions explicitly require restoring and saving authentication state. The file provides no cleanup safeguards, although actual exposure depends on local storage protection.
Elemente der Fähigkeitsprüfung (2)

Dies sind echte lokale Fähigkeiten, die für diese Fähigkeit erwartet werden können; daher müssen sie überprüft werden, werden jedoch nicht als bestätigtes bösartiges Verhalten gezählt.

Mittel
Ruby/shell backtick execution
- Install or upgrade `agent-browser`: `npm i -g agent-browser@latest`.
The installation command selects an unpinned latest package for global installation. The next line directs installation without approval, risking lifecycle-script execution and unexpected global changes.
Mittel
Ruby/shell backtick execution
If the CLI isn't on `PATH`, install it before continuing — preflight
The instruction says to install the CLI before continuing when it is absent from PATH. It authorizes the preceding unpinned global installation without an explicit approval step.
Geprüft von: codex
Diesen Bericht teilen & zitieren

Teile den versionierten Bewertungsbericht, das neutrale Badge, die Einbettungskarte und Zitate. Skillstore berichtet Nachweise, ohne zu entscheiden, ob dieser Skill sicher ist.

Versionsbericht öffnen
Sicherheitsbewertung

Berichtslink kopieren

https://skillstore.io/skills/vercel-next-dev-loop/audits/1?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown-Badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/vercel-next-dev-loop/security.svg)](https://skillstore.io/skills/vercel-next-dev-loop?utm_source=security_passport_badge)

HTML-Badge

<a href="https://skillstore.io/skills/vercel-next-dev-loop?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/vercel-next-dev-loop/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Einbettungskarte

<iframe src="https://skillstore.io/embed/skills/vercel-next-dev-loop.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>
Wissenschaftliche Zitate (APA · BibTeX · CFF)

APA-Zitat

vercel. (2026). next-dev-loop security audit report (audit version 1) [Author version unspecified]. Skillstore. https://skillstore.io/skills/vercel-next-dev-loop/audits/1

BibTeX-Zitat

@techreport{vercel-vercel-next-dev-loop-2026, author = {vercel}, title = {next-dev-loop security audit report (audit version 1)}, institution = {Skillstore}, year = {2026}, number = {1}, url = {https://skillstore.io/skills/vercel-next-dev-loop/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: "next-dev-loop security audit report (audit version 1)" version: "unspecified" type: report authors: - name: "vercel" date-released: "2026-11-06" url: "https://skillstore.io/skills/vercel-next-dev-loop/audits/1" identifiers: - type: other value: "skillstore:vercel-next-dev-loop:audit:1" description: "Skillstore immutable audit report identifier"

Skillstore-Score

Warum dieser Score Evidenzvertrauen: Mittel
55
Architektur
65
Wartbarkeit
87
Inhalt
65
Gemeinschaft
65
Spezifikationskonformität

Was Sie erstellen können

Validate Interface Changes

Check that a changed page compiles, renders without errors, and responds correctly to user interaction.

Investigate React Regressions

Compare visible behavior with component state and render counts to investigate unexpected updates or suspense behavior.

Verify Reported Browser Failures

Reproduce a reported navigation problem and distinguish application errors from stale or misdirected browser sessions.

Diese Prompts ausprobieren

Check Development Prerequisites
Check whether my running Next.js app meets this skill's prerequisites. Report missing requirements and ask before installing or upgrading anything.
Verify a Page Edit
Verify my latest edit to [route]. Check compilation, runtime errors, and visible behavior in the running app.
Test an Authenticated Flow
Verify [interaction] on [route] using a dedicated test account. Keep the browser session worktree-scoped and confirm authentication-state retention with me.
Diagnose a React Regression
Investigate [regression] on [route] using framework diagnostics and React introspection. Reconcile browser state, inspect render behavior, and verify the fix.

Bewährte Praktiken

  • Confirm the actual development port and required tool versions before testing.
  • Use a dedicated test account and explicitly agree on authentication-state retention.
  • Preserve active development output and use separate ports for production tests.

Vermeiden

  • Treating a successful build or type check as proof of correct browser behavior.
  • Deleting active development output or running production tests against the development server's port.
  • Installing unpinned global tooling without review or keeping sensitive login state on shared machines.

Häufig gestellte Fragen

Which tools can use this skill?
The skill lists Claude, Codex, and Claude Code as supported tools.
Which Next.js setup is required?
The instructions require Next.js 16.3 or later, Turbopack, and a running development server.
Does the skill start the development server?
A running development server is a prerequisite. The instructions leave it running after verification.
Why does it use both MCP and a browser?
Framework diagnostics expose compilation and runtime context. The browser verifies visible behavior, interactions, and React state.
Does it preserve login state?
Yes. Worktree-scoped sessions restore saved cookies and local storage, then save state when closed.
Does this replace production testing?
No. The workflow checks development behavior and recommends separate output and ports when running production tests.

Entwicklerdetails

Autor

vercel

Lizenz

Unbekannt

Skillstore-Revision

r1

Versionshinweis

Der Autor hat keine Version angegeben.

Ref.

c993c6abcbffafea2683d7748b53b3dfaf438415

Aktualität der Wartung

9.11.2026

Nutzung

0 Downloads · 0 Aufrufe

Dateistruktur

📄 SKILL.md

Mehr von vercel

Alle anzeigen
Alle anzeigen