summarize

Summarize or extract text/transcripts from URLs, podcasts, and local files (great fallback for “transcribe this YouTube/video”).

Quality

86%

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

Quality

Content

100%

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

The body is a tight, well-organized, fully actionable reference for a simple CLI skill, with copy-paste commands and clear conditional guidance and no wasted tokens.

Dimension	Reasoning	Score
Conciseness	The body is lean: it lists commands, flags, and env vars directly without explaining what URLs, API keys, or models are, assuming Claude's competence and earning every token.	3 / 3
Actionability	Quick start gives copy-paste-ready `summarize` commands, and the flags/env-var/config sections are concrete and executable with no pseudocode.	3 / 3
Workflow Clarity	This is a simple single-purpose CLI skill with an unambiguous primary action, and the YouTube section adds a clear conditional flow (summarize first, then ask which section to expand), satisfying the simple-skills note.	3 / 3
Progressive Disclosure	Content is appropriately inline for a single-purpose CLI wrapper, organized into clearly labeled sections with no nested external references to manage.	3 / 3
	Total	12 / 12 Passed

Description

72%

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 uses natural trigger language with a clear niche, but it lacks an explicit 'Use when…' trigger clause, leaving the 'when' only partially addressed.

Suggestions

Add an explicit 'Use when the user asks to summarize a URL, podcast, or local file, or to transcribe a YouTube/video' clause to satisfy the completeness 'when' requirement.

Broaden the concrete action list beyond summarize/extract/transcribe (e.g., mention handling long transcripts or producing JSON output) to push specificity toward level 3.

Reframe the parenthetical fallback as primary trigger guidance rather than a secondary note so the when-to-use intent is unmistakable.

Dimension	Reasoning	Score
Specificity	It names the domains ("URLs, podcasts, and local files") and a couple of actions ("Summarize or extract text/transcripts", "transcribe this YouTube/video"), but the actions overlap and are not a comprehensive concrete list like the level-3 anchor.	2 / 3
Completeness	The "what" is clear, but there is no "Use when…" clause; the trigger is only implied via the parenthetical "(great fallback for 'transcribe this YouTube/video')", which per the guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	Phrases like "summarize", "extract text/transcripts", and the quoted "transcribe this YouTube/video" are exactly what a user would naturally say, giving good coverage of natural trigger terms.	3 / 3
Distinctiveness Conflict Risk	The podcast/YouTube-transcript niche with the explicit "transcribe this YouTube/video" trigger is a clear, distinct use case unlikely to fire for unrelated skills.	3 / 3
	Total	10 / 12 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: Bitterbot-AI/bitterbot-desktop
Path: skills/summarize/SKILL.md
Commit: e73c717

Reviewed: about 15 hours 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.