youtube-transcript
Extract transcripts from YouTube videos. Use when the user asks for a transcript, subtitles, or captions of a YouTube video and provides a YouTube URL (youtube.com/watch?v=, youtu.be/, or similar). Supports output with or without timestamps.
95
93%
Does it follow best practices?
Impact
96%
2.13xAverage score across 3 eval scenarios
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 follows best practices. It clearly specifies the capability (transcript extraction), includes comprehensive trigger terms users would naturally use (transcript, subtitles, captions, YouTube URL formats), and explicitly states when to use it. The description is concise yet complete, using proper third-person voice throughout.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists specific concrete actions: 'Extract transcripts from YouTube videos' and 'Supports output with or without timestamps' - describes exactly what the skill does with clear functionality details. | 3 / 3 |
Completeness | Clearly answers both what ('Extract transcripts from YouTube videos', 'output with or without timestamps') AND when ('Use when the user asks for a transcript, subtitles, or captions of a YouTube video and provides a YouTube URL'). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'transcript', 'subtitles', 'captions', 'YouTube video', 'YouTube URL', plus specific URL patterns (youtube.com/watch?v=, youtu.be/) that users would naturally share. | 3 / 3 |
Distinctiveness Conflict Risk | Very clear niche with distinct triggers - specifically targets YouTube video transcripts with explicit URL patterns. Unlikely to conflict with other skills due to the specific platform (YouTube) and content type (transcripts/subtitles/captions) focus. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
87%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-crafted, concise skill that provides clear, actionable commands for transcript extraction. The main weakness is in the Output section where contradictory instructions (NEVER MODIFY vs. clean up paragraphs) create ambiguity, and the conditional file-saving logic could be more explicitly sequenced.
Suggestions
Clarify the apparent contradiction in Output: 'NEVER MODIFY' vs 'clean it up so that it is arranged by complete paragraphs' - specify that cleaning applies only to formatting/line breaks, not content
Restructure Output section as numbered steps: 1) Save to specified file or default name, 2) If no timestamps, reformat line breaks for readability
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient, providing only necessary information without explaining what YouTube or transcripts are. Every section serves a clear purpose with no padding. | 3 / 3 |
Actionability | Provides copy-paste ready bash commands with clear flag options. The supported URL formats and output behavior are explicitly specified, making execution unambiguous. | 3 / 3 |
Workflow Clarity | For a simple single-task skill, the workflow is clear, but the Output section mixes behavioral instructions (NEVER MODIFY, clean up paragraphs) with file handling in a way that could be better sequenced. The conditional logic for output formatting lacks explicit steps. | 2 / 3 |
Progressive Disclosure | For a skill under 50 lines with a single purpose, the content is well-organized into logical sections (Usage, Defaults, URL Formats, Output, Notes) with clear headers and no need for external references. | 3 / 3 |
Total | 11 / 12 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 — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- intellectronica/agent-skills
- Commit
9f7f750
- 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.