Skip to content
Agentmart
Submit a tool

design-artifact-evaluator

Independently evaluate a rendered product or UI artifact by collecting browser/device evidence, checking real structure and interactions, applying the…

Skill by Poom5741

IndexedLicense unknown★ 2
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/poom5741-design-artifact-evaluator

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Independently evaluate a rendered product or UI artifact by collecting browser/device evidence, checking real structure and interactions, applying the project's EVAL.md subchecks and blockers, producing a deterministic verdict and prioritized return plan, and comparing iteration rounds. Use this skill whenever a user asks to review, QA, score, validate, approve, release-gate, or iteratively improve a real screen, flow, prototype, website, app, or generated interface. Do not use it to author the evaluation standard or silently fix the artifact while judging it.

Use cases: design, testing

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found
Runs as
Node.js package

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/design-artifact-evaluator

What's inside

Skill name
design-artifact-evaluator
Description
Independently evaluate a rendered product or UI artifact by collecting browser/device evidence, checking real structure and interactions, applying the project's EVAL.md subchecks and blockers, producing a deterministic verdict and prioritized return plan, and comparing iteration rounds. Use this skill whenever a user asks to review, QA, score, validate, approve, release-gate, or iteratively improve a real screen, flow, prototype, website, app, or generated interface. Do not use it to author the evaluation standard or silently fix the artifact while judging it.
License
unknown
Instructions
206 lines in SKILL.md · view on GitHub

Before installing

  • Ships executable scripts

Files (8)

  • SKILL.md
  • openai.yaml · agents/
  • EVALUATION-REPORT.template.md · assets/
  • evaluation-output.schema.json · assets/
  • evals.json · evals/
  • evidence-protocol.md · references/
  • scoring-runtime.md · references/
  • recompute-scores.mjs · scripts/

The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub

More from Poom5741/super-speckit

Signals

Stars
2
Forks
0
Open issues
0
Last commit (this folder)
Sep 17, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

License
License unknown
Repository
github.com/Poom5741/super-speckit
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

More from Poom5741

Cite this page

design-artifact-evaluator skill. Agent Mart. https://agentmart.dev/skills/poom5741-design-artifact-evaluator (last updated 2026-10-24)