Publisher: Anthropic · Editorial profile by AI Tools Ratings · Review method
Not runtime tested; source-document review only. Referenced scripts were not executed or comprehensively audited. No security certification.
What task is this skill designed for?
Prepare an inventory-dashboard demo using synthetic records and a portable HTML handoff.
What input and output should you expect?
Input: A workflow brief, synthetic fixture, required views and explicit exclusions for real credentials and production data.
Output: Frontend source and a bundled HTML artifact; expected, not independently tested. Backend services are not established by a working frontend.
What does it need to run?
The source names Node 18+, shell scripts, React, TypeScript, Vite, Tailwind, shadcn/ui and Parcel. Referenced setup and bundle scripts install dependencies and require separate inspection.
Publisher README describes Claude Skills use; independent Codex or Cursor runtime compatibility is not established.
How should you approach installation?
- Inspect the pinned source, license and task-specific reference files before installing anything.
- Follow the publisher README guidance for your actual client; no installation command or cross-client compatibility was independently tested here.
- Try the illustrative prompt with synthetic input in a separate folder, inspect the output against the checklist and approve external actions separately.
Installation guide: discovery, dependencies and runtime checks
What files, accounts or data can it access?
Writes project files and may invoke package installations contacting registries. Bundled HTML is executable JavaScript; inspect network calls and embedded content before sharing.
What does the skill cost?
The inspected source license is Apache-2.0. Agent subscriptions, model usage, dependencies and external services have separate costs and terms. No paid runtime was tested.
What are its limits and alternatives?
Bundling can increase size and obscure dependencies. A mock action can appear to provide authentication or persistence when it only changes local state; label mocked behavior.
Use Frontend Design for visual direction or plain HTML for a small interaction. Choose this workflow for stateful components and a portable artifact.
What could you ask in a small trial?
Try this with a small sample:
Build an inventory demo with ten invented records, a filter and empty states. Keep all state local, label synthetic data and explain what resets on reload.
How would you verify the result?
- Open a clean browser session and exercise every control.
- Check for secrets, real records and unexpected endpoints.
- Verify keyboard access, narrow screens and bundle loading.
Use a baseline and record acceptance evidence before treating a successful task as a reliable workflow.
Which source and license were checked?
Read the reviewed SKILL.md at its pinned commit · Complete reviewed folder
Repository and current publisher guidance
Checked:
Apache-2.0 — identified in skills/web-artifacts-builder/LICENSE.txt at the reviewed commit. Dependencies and third-party assets may have separate terms. License evidence
Version details and review scope
Source: anthropics/skills/skills/web-artifacts-builder
Reviewed commit: dbd4588f9e1033efb41dad4bef2f7947c8993d44
SKILL.md SHA-256: 81c5002c6643b0de7b8710b00e7a9038daa6fb9b68d59870ee6adb12da8d10f8
Source-document review. Source text and stated dependencies were inspected for this profile. Referenced code was not comprehensively audited, no runtime test was performed, and source files are not mirrored here.