CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

71

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Risky

Do not use without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

77%

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

The body is highly actionable with clear, validated workflows and good reference structure. Its main weakness is token-efficiency: the internal SOP is duplicated inline rather than linked, and one bundled reference is orphaned.

Suggestions

Replace the inline 'Reliable Download SOP (Internal)' section with a one-line pointer to references/internal-sop.md to remove the near-verbatim duplication and reclaim tokens.

Link references/internal-sop.md from the body (e.g., in the SOP or Further Reading section) so every bundled reference is reachable.

Consolidate the repeated troubleshooting guidance between the Agent Execution Checklist and Troubleshooting Quick Reference into a single canonical section to reduce redundancy.

DimensionReasoningScore

Conciseness

Mostly lean executable command blocks with little concept padding, but the 'Reliable Download SOP (Internal)' section duplicates references/internal-sop.md almost verbatim and the Agent Execution Checklist repeats troubleshooting already present later, adding tokens that could be tightened.

2 / 3

Actionability

Fully executable yt-dlp/ffmpeg commands, a complete scripts/download_video.py argument reference, and copy-paste-ready examples with explained parameters.

3 / 3

Workflow Clarity

Multi-step flows (default user flow, internal SOP, execution checklist, HLS steps) are clearly sequenced with explicit validation and retry checkpoints such as fail-fast PO token startup, ffprobe quality verification, and 403/fragment retry logic.

3 / 3

Progressive Disclosure

Clear one-level references exist (references/po-token-setup.md, scripts/download_video.py), but references/internal-sop.md is never linked from the body and its content is instead duplicated inline, and the large body could offload more to references.

2 / 3

Total

10

/

12

Passed

Description

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.

The description is specific, complete, and uses natural trigger terms with a clear 'Use when' clause. It clearly stakes out a distinct video-download niche with low conflict risk.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Download YouTube videos and HLS streams (m3u8)', 'extracting audio', 'handling protected streams with authentication headers', 'troubleshooting download issues' — matching the multiple-specific-actions anchor.

3 / 3

Completeness

Explicitly answers both 'what' (download YouTube/HLS, extract audio, handle protected streams) and 'when' via a clear 'Use this skill when users request...' clause with explicit triggers.

3 / 3

Trigger Term Quality

Natural user phrasing is well covered — 'downloading videos', 'extracting audio', '403 errors', 'cookie extraction problems' — terms a user would actually say, matching the good-coverage anchor.

3 / 3

Distinctiveness Conflict Risk

A clear yt-dlp/ffmpeg video-download niche with distinct, specific triggers (m3u8, PO tokens, nsig, 403) unlikely to conflict with other skills.

3 / 3

Total

12

/

12

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (509 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
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.