Content
67%Weight 40%Scale 1-5Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
A lean, well-structured CLI-harness skill with executable install and usage commands and a sensible agent workflow. Its weaknesses are repeated --json/unofficial disclaimers and the lack of concrete example invocations for most command groups or error-recovery steps.
Suggestions
Consolidate the --json guidance into a single statement and merge the duplicated experimental/unofficial disclaimers into one line.
Add one concrete example invocation per command group (e.g. `source add <url>`, `artifact generate`, `download <id>`) instead of one-line purpose descriptions.
Include a brief error-recovery path, such as running `auth login` when `auth status` fails, to close the workflow validation gap.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Mostly efficient, but the --json guidance is repeated three times ("# Prefer JSON for agent use", "Prefer --json only where the upstream notebooklm command supports it", "Use --json for machine-readable output only on commands that support it upstream") and the experimental/unofficial disclaimer appears twice, which could be tightened. | 3 / 5 |
Actionability | Install and usage commands are concrete and executable, and workflow steps carry real commands, but the command groups (chat, artifact, download, share) get only one-line purposes with no example invocations, leaving minor gaps. | 4 / 5 |
Workflow Clarity | The 4-step agent workflow is a clear, concrete sequence that opens with an explicit auth checkpoint ("cli-anything-notebooklm auth status"), but no error-recovery guidance exists for auth failure, a minor validation gap. | 4 / 5 |
Progressive Disclosure | No bundle files exist, and the single-file body is well-organized into clearly labeled sections with an explicit References list of external URLs; the ~73-line body and un-expanded per-command detail keep it just short of the clean-overview ideal. | 4 / 5 |
Total | 15 / 20 Passed |