Content
93%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.
An efficient, highly actionable command-reference body that is well-structured for a single-script skill. The only gap is the absence of an explicit post-download/post-transcript verification step.
Suggestions
Add a brief verification note after download/audio/subs commands (e.g., 'confirm the file exists and is non-empty before reporting success'), since downloads can silently fail or produce empty output.
Document the script's non-zero exit code / stderr behavior so Claude knows to surface yt-dlp/ffmpeg errors and retry rather than assuming success.
Mention how to handle playlists explicitly if batch downloads are a supported use case, including any per-item validation.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is a lean command catalog with no padding and no over-explanation of yt-dlp/ffmpeg basics; every line is an executable command or a brief useful note, matching the lean-and-efficient anchor. | 5 / 5 |
Actionability | Provides copy-paste-ready bash commands with concrete flags covering transcript, download, audio, subs, and formats, matching the fully-executable anchor for the common cases. | 5 / 5 |
Workflow Clarity | Commands are clearly grouped and the script self-reports failures via exit codes, but the body lacks an explicit verification/feedback checkpoint for confirming output success, leaving a minor validation gap short of the 5 anchor. | 4 / 5 |
Progressive Disclosure | The SKILL.md is a concise overview with well-organized sections, and implementation is appropriately split into the one-level-deep ./scripts/vtd.js (verified to exist with matching commands), satisfying the simple-skill exception for a 5. | 5 / 5 |
Total | 19 / 20 Passed |