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.

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

81%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

Highly actionable with strong sequenced workflows and validation loops, plus well-signaled references and a real bundled script. The main weakness is conciseness: the body re-states SOP/checklist material already in the references and over-explains familiar concepts.

Suggestions

Remove the 'Reliable Download SOP (Internal)' and 'Agent Execution Checklist (Internal)' sections from the body since the same content exists in references/internal-sop.md; replace with a one-line pointer.

Cut the 'Parameters explained' block under WebM-to-MP4 conversion and the 'What are PO Tokens' framing — Claude already knows ffmpeg flags and PO-token concepts; keep only values that differ from defaults.

Collapse the duplicated PO-token troubleshooting guidance that appears in both the body and references/po-token-setup.md into the reference file to reduce token cost.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with executable commands, but pads with explanations Claude already knows (e.g., 'Parameters explained' for ffmpeg flags, 'What are PO Tokens') and duplicates the SOP/checklist content that also appears verbatim in references/internal-sop.md and references/po-token-setup.md.	3 / 5
Actionability	Copy-paste-ready yt-dlp and ffmpeg commands with concrete flags cover YouTube, audio extraction, subtitles, playlists, WebM conversion, and HLS auth-header streams; the bundled download_video.py wrapper is fully documented with arguments.	5 / 5
Workflow Clarity	Clear sequenced workflows with explicit validation/retry checkpoints — the SOP, Agent Execution Checklist, and Troubleshooting sections encode fail-fast, retry, and fallback loops for 403/nsig/PO-token/SSL failures.	5 / 5
Progressive Disclosure	Good one-level-deep references to references/po-token-setup.md and references/internal-sop.md (both real files) and a bundled script, but significant SOP content is inlined in the body that already lives in those reference files, so some content that should be separate remains inline.	4 / 5
	Total	17 / 20 Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description: third-person, concrete actions, comprehensive trigger terms, explicit 'what' and 'when', and a clear distinct niche. All four dimensions land at the top anchor.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Download YouTube videos', 'extracting audio', 'handling protected streams with authentication headers', 'troubleshooting download issues' — giving comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Clearly states what ('Download YouTube videos and HLS streams... using yt-dlp and ffmpeg') and when ('Use this skill when users request... or troubleshooting download issues like...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural user phrases and concrete failure terms — 'downloading videos', 'extracting audio', '403 errors', 'nsig extraction failures', 'cookie extraction problems', 'HLS streams (m3u8)' — covering synonyms and specific technical triggers.	5 / 5
Distinctiveness Conflict Risk	The YouTube/HLS-download niche with yt-dlp/ffmpeg and specific failure signatures (nsig, 403, cookies) is distinct and unlikely to trigger competing skills.	5 / 5
	Total	20 / 20 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (510 lines); consider splitting into references/ and linking	Warning
relative_links	Relative link issues: 2 missing	Warning

	Total	14 / 16 Passed

Repository: daymade/claude-code-skills
Path: youtube-downloader/SKILL.md
Commit: a0af111

Reviewed: 22 minutes ago

Table of Contents

Discovery Implementation Validation

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.