summarize

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

Quality

79%

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/summarize/SKILL.md

The canonical home for this skill is summarize in Hung-Reo/hungreo-openclaw

Quality

Content

92%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 a model of lean, actionable CLI skill writing: executable examples for every common case, concrete flags and keys, and a clear decision rule for transcript requests. Its only blemish is the redundant, time-sensitive model pin repeated in the Quick start.

Dimension	Reasoning	Score
Conciseness	The body is lean — commands, flags, env vars, and one decision rule — with no explanations of concepts Claude already knows. Minor trimmable instances: the Quick start repeats `--model google/gemini-3-flash-preview` on two lines even though it is stated as the default, and the version-pinned model name is time-sensitive, keeping it just below anchor 5.	4 / 5
Actionability	Fully executable, copy-paste-ready commands cover the common cases: URL summary, local PDF, YouTube summary, and transcript-only extraction ("summarize \"https://youtu.be/...\" --youtube auto --extract-only"), plus concrete flags and env vars. Matches anchor 5 exactly.	5 / 5
Workflow Clarity	This is a simple, single-purpose CLI skill where the single action is unambiguous, and the YouTube section adds explicit branching guidance ("return a tight summary first, then ask which section/time range to expand"). No destructive or batch operations exist, so the validation cap does not apply; per the simple-skill exception the clarity here merits 5.	5 / 5
Progressive Disclosure	No bundle files exist and none are needed; the ~60-line body keeps all compact, appropriately-inline content under clear section headers (Quick start, YouTube, Model + keys, Useful flags, Config) with nothing that belongs in a separate file inlined. The structure is easy to navigate, matching the well-organized-simple-skill case.	5 / 5
	Total	19 / 20 Passed

Description

66%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 mostly distinctive with good natural trigger phrases, but it lacks an explicit "Use when..." clause — the trigger guidance is only a parenthetical fallback hint. Adding explicit when-to-use phrasing with a few more synonyms would lift it substantially.

Suggestions

Add an explicit trigger clause, e.g., "Use when the user asks to summarize a link/article/URL, extract a transcript, or transcribe a YouTube video."

Include common synonyms such as "article", "TL;DR", and "transcript" to broaden natural trigger coverage.

State the file types handled for local files (e.g., PDF, text) to sharpen the 'what' and reduce overlap with generic summarization skills.

Dimension	Reasoning	Score
Specificity	"Summarize or extract text/transcripts" names two concrete actions and specifies sources ("URLs, podcasts, and local files"), listing several specific actions with minor coverage gaps (e.g., no article/file-format detail). It goes beyond the 1-2 actions of anchor 3 but is not comprehensive enough for anchor 5.	4 / 5
Completeness	The "what" is clear (summarize/extract text and transcripts from URLs, podcasts, local files), but the "when" appears only as the weakly implied parenthetical "great fallback for 'transcribe this YouTube/video'" with no explicit "Use when..." clause, which caps completeness at 3 per the judging guidelines. It is above anchor 2 because a clear "what" is present, but below anchor 4 because the "when" is not explicit.	3 / 5
Trigger Term Quality	Natural user phrases like "summarize", "transcribe this YouTube/video", "podcasts", and "URL" are present, including the quoted trigger "transcribe this YouTube/video". A few natural terms are missing (e.g., "article", "TL;DR", "transcript"), matching anchor 4 rather than the comprehensive synonym coverage of anchor 5.	4 / 5
Distinctiveness Conflict Risk	The transcript-extraction/summarization niche with a distinct quoted YouTube trigger is mostly distinguishable, with only minor overlap risk against generic summarization or transcription skills. Not anchor 5 because "summarize... URLs" alone could collide with general summarization skills.	4 / 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: Bitterbot-AI/bitterbot-desktop
Path: skills/summarize/SKILL.md
Commit: 1c7dc1b

Reviewed: 20 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.