youtube-downloader
Download YouTube videos and HLS streams (m3u8) from platforms like Mux, Vimeo, etc. using yt-dlp and ffmpeg. Use this skill when users request downloading videos, extracting audio, handling protected streams with authentication headers, or troubleshooting download issues like nsig extraction failures, 403 errors, or cookie extraction problems.
67
81%
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 clearly defines its scope, lists concrete actions and tools, includes a well-structured 'Use this skill when...' clause with specific trigger scenarios, and uses natural keywords users would employ. The description is concise yet comprehensive, covering both common use cases and troubleshooting scenarios, making it highly distinguishable from other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: downloading YouTube videos, HLS streams (m3u8), extracting audio, handling protected streams with authentication headers, and troubleshooting specific issues like nsig extraction failures, 403 errors, and cookie extraction problems. | 3 / 3 |
Completeness | Clearly answers both 'what' (download YouTube videos and HLS streams using yt-dlp and ffmpeg) and 'when' (explicit 'Use this skill when...' clause covering downloading videos, extracting audio, handling protected streams, and troubleshooting specific download issues). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'YouTube', 'download videos', 'HLS streams', 'm3u8', 'yt-dlp', 'ffmpeg', 'Mux', 'Vimeo', 'extracting audio', '403 errors', 'cookie extraction', 'authentication headers'. These are terms users would naturally use when seeking help with video downloading. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche around video downloading via yt-dlp/ffmpeg, specific platforms (YouTube, Mux, Vimeo), and specific error types (nsig extraction, 403 errors, cookie extraction). Unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a comprehensive and highly actionable skill with excellent workflow clarity, clear error recovery paths, and executable commands throughout. However, it is significantly over-length with substantial redundancy (troubleshooting items repeated across SOP, checklist, and troubleshooting sections), unnecessary explanations of basic concepts (ffmpeg flags, what HLS is), and content that should be split into reference files rather than inlined in the main SKILL.md.
Suggestions
Reduce redundancy by consolidating the 'Reliable Download SOP', 'Agent Execution Checklist', and 'Troubleshooting Quick Reference' into a single concise section — currently the same failure modes (403, PO token, bot detection) are described three times.
Remove explanations of concepts Claude already knows: ffmpeg parameter descriptions, what HLS/m3u8 is, what AAC codec is, and the 'When to Use This Skill' section (this duplicates frontmatter).
Move the HLS stream download section and the detailed troubleshooting reference into separate files (e.g., `references/hls-downloads.md` and `references/troubleshooting.md`) and link from the main SKILL.md.
Remove the 'Parameters explained' block for the ffmpeg WebM-to-MP4 conversion — Claude knows what `-crf`, `-preset`, and `-c:v libx264` do.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~350+ lines. It explains concepts Claude already knows (what HLS is, what ffmpeg parameters do, what AAC is), includes a lengthy 'Parameters explained' section for basic ffmpeg flags, repeats information across multiple sections (e.g., PO token troubleshooting appears in both the SOP, checklist, and troubleshooting sections), and includes a 'When to Use This Skill' section that restates the frontmatter description. | 1 / 3 |
Actionability | The skill provides fully executable, copy-paste-ready commands throughout — yt-dlp format checks, download commands, ffmpeg conversions, HLS downloads with headers, and verification via ffprobe. The bundled script arguments are thoroughly documented with concrete usage examples. | 3 / 3 |
Workflow Clarity | Multi-step workflows are clearly sequenced with explicit validation checkpoints: the high-quality download workflow has numbered steps with verification (check formats after PO token install), the HLS workflow has clear step-by-step with DevTools identification, and the internal SOP/checklist provides error recovery loops (retry with cookies, fall back to WPC provider, retry with progressive formats). | 3 / 3 |
Progressive Disclosure | The skill references `references/po-token-setup.md` and `scripts/download_video.py` appropriately, but the main file itself is monolithic — the HLS section, troubleshooting, and the extensive non-technical user experience section could be split into separate reference files. Significant inline content bloat reduces the effectiveness of the overview structure. | 2 / 3 |
Total | 9 / 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 |
|---|---|---|
skill_md_line_count | SKILL.md is long (509 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
- Repository
- daymade/claude-code-skills
- Commit
bbf87f3
- 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.