Download YouTube video transcripts as readable text files. Use when extracting transcripts from videos for analysis, documentation, or content review.
41
Quality
27%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/content-tools/skills/fetch-youtube-transcript/SKILL.mdQuality
Discovery
N/ABased on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
Something went wrong
Implementation
27%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is significantly over-engineered for a simple transcript download task. It explains concepts Claude already knows (error handling patterns, path handling, user communication tips), includes unnecessary sections (Future Enhancements, Technical Details), and buries the core actionable content in verbose prose. The skill would be far more effective at 1/8th the length.
Suggestions
Reduce to ~50 lines: Quick start with the command, one example, brief error handling notes, and link to a separate REFERENCE.md for language codes and URL formats
Remove 'Implementation Tips for Claude Code' section entirely - Claude knows how to parse arguments, handle errors, and communicate with users
Remove 'Future Enhancements' and 'Limitations' sections - these don't help Claude execute the skill
Clarify the actual execution command - the current uvx + local script path combination appears incorrect and confusing
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~400 lines for a simple transcript download task. Includes excessive explanation of error handling, implementation tips Claude doesn't need, future enhancements, and repetitive examples. The core functionality could be conveyed in under 50 lines. | 1 / 3 |
Actionability | Provides concrete command examples and code snippets, but the actual execution command is unclear - references a script at 'scripts/fetch-youtube-transcript.py' but the uvx command construction seems incorrect (mixing uvx with a local script path). The core action is buried in verbose instructions. | 2 / 3 |
Workflow Clarity | Steps are listed (parse, construct, execute, handle output/errors) but the workflow is overly complex for a single-command operation. Validation is mentioned but the testing verification section at the end feels disconnected from the main workflow. | 2 / 3 |
Progressive Disclosure | Monolithic wall of text with no references to external files. Content that could be separate (language codes, URL formats, error messages) is all inline. The document is overwhelming rather than progressively revealing information. | 1 / 3 |
Total | 6 / 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 |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
0ebe7ae
Table of Contents
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.