CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

video-download

Download video and audio from YouTube and 1000+ sites using yt-dlp. No API keys needed. Use when: (1) Downloading a video from YouTube or other sites, (2) Extracting audio from a video URL, (3) Downloading subtitles/captions from a video, (4) Getting video metadata without downloading.

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

88%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.

A highly actionable, well-organized reference: every command is executable and the common use cases are covered, with clear prerequisites and troubleshooting. The weaknesses are minor — some duplication between the Commands and Quality Presets sections and a length that slightly exceeds what should live directly in SKILL.md.

Suggestions

Deduplicate the resolution format flags: keep the Quality Presets table and remove the repeated 720p/1080p command examples (or vice versa).

Merge the repeated 'update yt-dlp' guidance so it appears once, either in Tips or Troubleshooting.

Consider moving the Output Template Variables table (and possibly the preset details) into a one-level reference file to keep SKILL.md under ~50 lines.

DimensionReasoningScore

Conciseness

The body is command- and table-driven with almost no padding, but there is duplication: 720p/1080p format flags appear both in the Commands section and again in the Quality Presets table, and the 'update yt-dlp' advice is repeated in both Tips ("If a download fails with HTTP errors, update yt-dlp first") and Troubleshooting ("Run `yt-dlp -U` to update"). This fits 'efficient; minor instances that could be trimmed' rather than the every-token-earns-its-place anchor.

4 / 5

Actionability

Every example is a fully executable, copy-paste-ready command (e.g. `yt-dlp "URL" -x --audio-format mp3 --audio-quality 0`) and together they cover the common cases: best quality, specific resolutions, audio-only, subtitles, metadata, format listing, and output directory. Not the 4-anchor, since there are no gaps in the covered cases.

5 / 5

Workflow Clarity

This is a simple, single-command-per-task skill where the single action is unambiguous, prerequisites (yt-dlp, ffmpeg) are stated up front, and the Troubleshooting section provides error-recovery feedback ("yt-dlp: command not found" → install; failures → `yt-dlp -U`). Downloads are not destructive or batch operations, so no validation cap applies.

5 / 5

Progressive Disclosure

Sections are well-organized (Commands, Quality Presets, Output Template Variables, Tips, Troubleshooting) and easy to navigate, but the file runs ~104 lines — beyond the under-50-line simple-skill exception — with the preset table and output-template reference being natural candidates for a one-level reference file. Fits 'good structure; most content appropriately placed; minor organization gaps' rather than a fully optimized split.

4 / 5

Total

18

/

20

Passed

Description

92%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: concrete actions, explicit what-and-when structure with four enumerated triggers, and a clearly distinct niche. The only gap is modest — a few missing natural synonyms and file extensions like .mp3/.mp4.

Suggestions

Add common synonyms and file extensions to the trigger terms, e.g. mentioning .mp3/.mp4 output or 'save video from' phrasing.

Optionally name the metadata use case more distinctly (e.g. 'video metadata lookup') to fully eliminate overlap with generic metadata skills.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — "Download video and audio", "Extracting audio", "Downloading subtitles/captions", "Getting video metadata" — and names the tool (yt-dlp) and scope ("YouTube and 1000+ sites"), comprehensively covering the skill's tasks rather than stopping at 'several specific actions with minor gaps'.

5 / 5

Completeness

It explicitly answers both: a clear "what" ("Download video and audio from YouTube and 1000+ sites using yt-dlp. No API keys needed.") and an explicit "Use when:" clause enumerating four concrete trigger scenarios, matching the top anchor's structure exactly. Not the 4-anchor, since the 'when' is already fully explicit and specific.

5 / 5

Trigger Term Quality

Good natural keyword coverage — "Downloading a video from YouTube", "Extracting audio", "subtitles/captions", "video metadata" — phrases users would actually say. Falls short of comprehensive because synonyms (e.g. "save/rip video") and file extensions (.mp3, .mp4) are missing.

4 / 5

Distinctiveness Conflict Risk

The yt-dlp video-download niche is clear with distinct triggers (YouTube/video URL download, audio extraction, subtitles, metadata), giving minimal conflict risk; only the generic "metadata" phrasing creates slight theoretical overlap, which is not enough to drop to the 4-anchor's 'minor overlap risk'.

5 / 5

Total

19

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

calesthio/OpenMontage

Path

.agents/skills/video-download/SKILL.md

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.