yt-dlp
Download videos, audio, and transcripts from YouTube and 1000+ sites with yt-dlp. Use when the user mentions "yt-dlp", "youtube-dl", wants to download a video, rip audio from a video, or extract a transcript from a URL.
72
88%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an excellent skill description that hits all the marks. It provides specific capabilities, includes a comprehensive 'Use when...' clause with natural trigger terms covering both tool names and user intent phrases, and occupies a clear, distinct niche. It follows the third-person voice convention and is concise without being vague.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Download videos, audio, and transcripts' and names the tool 'yt-dlp' and scope '1000+ sites'. These are clear, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (download videos, audio, and transcripts from YouTube and 1000+ sites) and 'when' (explicit 'Use when...' clause with multiple trigger scenarios). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'yt-dlp', 'youtube-dl', 'download a video', 'rip audio', 'extract a transcript', 'URL'. These cover both tool-specific and action-based queries users would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with specific tool names (yt-dlp, youtube-dl) and a clear niche around video/audio downloading and transcript extraction from URLs. Unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, highly actionable skill with excellent executable commands and a well-structured transcript workflow. The content is mostly concise but could trim some explanatory commentary that Claude already knows. The single-file structure works reasonably well given the skill's scope, though the transcript section is quite detailed and could potentially be split out.
Suggestions
Trim explanatory asides like 'strips the video stream', 'means best VBR', and the yt-dlp site count mention — Claude knows these concepts.
Consider extracting the detailed transcript workflow into a separate TRANSCRIPT.md to keep the main skill file as a quick-reference overview.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient with good use of concrete commands, but includes some explanatory text that Claude wouldn't need (e.g., explaining what --audio-quality 0 means, what --restrict-filenames does). The tips section adds useful but somewhat verbose context. Could be tightened in places. | 2 / 3 |
Actionability | Excellent actionability — every action has fully executable, copy-paste-ready bash commands with specific flags. Variants are concrete with exact flag combinations. The transcript workflow includes precise find commands and script invocations with clear variable handling. | 3 / 3 |
Workflow Clarity | The transcript action is a well-sequenced multi-step workflow with numbered steps, clear dependencies between steps (download subs → find file → strip → show path). Video and audio are single-command actions that are unambiguous. Edge cases and fallback behaviors are explicitly noted (e.g., zsh glob errors, stdin format detection). | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear sections (Actions, Tips & Gotchas) and references the strip-transcript.mjs script. However, all content is inline in a single file — the common variants under Video and the detailed transcript workflow could benefit from separation. The reference to supportedsites.md is appropriate. No bundle files are provided to evaluate against. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- shillem/cc-marketplace
- Commit
2384118
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.