Evaluation report
Warningsnotebooklm · plugin72ff5ab· 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/roomi-fields/notebooklm-mcp @ 72ff5ab — ★ 107 · TypeScript · MIT · last push 9 days ago
Manifest detected
kind=plugin slug=notebooklm · source=.claude-plugin/plugin.json
Slug is URL-safe
"notebooklm" matches /^[a-z0-9][a-z0-9-]{0,62}$/
Slug is unique within kind
No collision found for plugin/notebooklm
Version is semver
2.1.0
Documentation
5 passedDescription quality
28 words · 247 chars — "Automate Google NotebookLM at scale. Citation-backed Q&A, full Studio generation…"
README is present and substantial
18,500 chars · 8 sections · 5 code blocks
Tags / topics declared
16 total — ai, anthropic, automation, citations, claude, claude-code (+10)
README has usage / example sections
found: Quick Start
Homepage / docs URL declared
https://github.com/roomi-fields/notebooklm-mcp
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
3 passed1 warningPlugin: bundled artifacts presentwarn
Couldn't find a skills/ subdir or an MCP server config inside the plugin
A plugin is most useful when it bundles ≥ 1 skill or an MCP server.
Plugin: manifest fields complete
Plugin: bundle shape
empty bundle
Plugin: manifest location
manifest at .claude-plugin/plugin.json (modern convention)
Maintenance
3 passedRecent activity
last push 9 days ago
Tests detected
3 test directories · 45 test files
CI configuration detected
GitHub Actions (3 workflows)
Behavioral
This artifact hasn't produced behavioral results yet: the evaluation sandbox couldn't run it (it may need credentials we don't provide, or a build our environment doesn't support). That's a limitation of our environment, not a verdict on the artifact.