Evaluation report
Warningsplaywright-skill · pluginbb7e920· 3 months ago
Every check MetaHub ran on this artifact, grouped by area. Static checks run on the source at publish time; behavioral checks run the artifact in a sandbox and judge what it actually does.
Structural
5 passedRepository is reachable
https://github.com/lackeyjb/playwright-skill @ bb7e920 — ★ 2,879 · JavaScript · MIT · last push 7 months ago
Manifest detected
kind=plugin slug=playwright-skill · source=.claude-plugin/plugin.json
Slug is URL-safe
"playwright-skill" matches /^[a-z0-9][a-z0-9-]{0,62}$/
Slug is unique within kind
No collision found for plugin/playwright-skill
Version is semver
4.1.0
Documentation
5 passedDescription quality
25 words · 188 chars — "Claude Code Skill for general-purpose browser automation with Playwright. Auto-d…"
README is present and substantial
8,461 chars · 14 sections · 9 code blocks
Tags / topics declared
13 total — ai-tools, automation, browser-automation, claude, claude-code, claude-plugin (+7)
README has usage / example sections
found: Installation · Quick Start · Usage
Homepage / docs URL declared
no homepage declared (registry will use the repo URL) — info-only, not blocking
Safety
2 passedLICENSE file at repo root
LICENSE
No sensitive files in the repo
scanned for .env, credentials.json, *.pem, .ssh/, AWS / GCP configs — none found
Kind-specific
4 passedPlugin: manifest fields complete
Plugin: bundled artifacts present
1 skill
Plugin: bundle shape
1 skill
Plugin: manifest location
manifest at .claude-plugin/plugin.json (modern convention)
Maintenance
3 warningsRecent activitywarn
last push 7 months ago — looks slowing down
Consumers prefer artifacts that are actively maintained (threshold: 90 days, configurable via EVAL_RECENCY_PASS_DAYS).
Tests detectedwarn
no test/tests/__tests__/spec/t/ dirs, no JVM src/test/, and no JS/TS/Python/Go/Ruby/Elixir test files
Add tests (even a smoke test). Consumers gauge maintenance quality by their presence.
CI configuration detectedwarn
no CI config found (looked for GitHub Actions, CircleCI, GitLab CI, etc.)
Add a simple workflow (lint + test on PR) — it tells consumers the artifact is built reproducibly.
Behavioral
Behavioral results aren't published for this artifact. The publisher sees the full report on their own dashboard.