youtube-content

YouTube transcripts to summaries, threads, blogs.

Quality

75%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/media/youtube-content/SKILL.md

Quality

Content

85%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.

The content is highly actionable with a clear, validated workflow and executable commands, but progressive disclosure is undermined by an orphaned reference file whose content is duplicated inline. Linking the reference instead of inlining it would resolve the main weakness.

Suggestions

Replace the inlined "Example — Chapters Output" and the Output Formats list with a pointer to references/output-formats.md so the reference file is actually used and content is not duplicated.

Drop the redundant second intro sentence ("Extract transcripts from YouTube videos and convert them into useful formats.") since it restates the first.

Add a short "References" or "See also" line listing references/output-formats.md and scripts/fetch_transcript.py for discoverability.

Dimension	Reasoning	Score
Conciseness	The body is lean with executable commands and minimal concept padding, but the two redundant intro sentences and the inlined Chapters example (duplicated from the reference file) are minor instances that could be trimmed.	4 / 5
Actionability	It provides fully executable, copy-paste-ready commands (install plus four uv run invocations with real flags) backed by a real helper script, covering the common cases.	5 / 5
Workflow Clarity	The five-step workflow has explicit validation checkpoints (validate output non-empty and language; verify coherence/timestamps/completeness) plus retry feedback loops, and the Error Handling section enumerates failure modes with remediation.	5 / 5
Progressive Disclosure	Structure and the helper-script reference are clear, but references/output-formats.md is never linked from the body and its content is duplicated inline, so a provided reference is neither signaled nor used as a one-level-deep pointer.	3 / 5
	Total	17 / 20 Passed

Description

65%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.

The description is specific and distinct, targeting a clear YouTube-transcript niche, but it omits any "when to use" trigger guidance and truncates the action list. Adding an explicit Use-when clause and a fuller action list would raise completeness and specificity.

Suggestions

Append an explicit trigger clause, e.g. "Use when the user shares a YouTube URL or asks to summarize, transcribe, or reformat a video."

Expand the action list to cover the full output range (chapters, chapter summaries, threads, blog posts, quotes) instead of just "summaries, threads, blogs."

Add natural synonyms such as "video," "captions," or "subtitles" to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the YouTube-transcript domain and three concrete outputs ("summaries, threads, blogs") but the list is terse and omits other actions the skill performs (chapters, quotes), leaving minor coverage gaps closer to anchor 3 than 4.	3 / 5
Completeness	It clearly states what the skill does but provides no "Use when..." trigger clause; per the rubric, missing explicit trigger guidance caps completeness at 3.	3 / 5
Trigger Term Quality	"YouTube transcripts to summaries, threads, blogs" includes strong natural keywords users would say, but misses common synonyms like "video," "captions," or "subtitles," placing it at anchor 4.	4 / 5
Distinctiveness Conflict Risk	"YouTube transcripts" is a narrow, clearly defined niche with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	15 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: NousResearch/hermes-agent
Path: skills/media/youtube-content/SKILL.md
Commit: 6327930

Reviewed: 2 days 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.