summarize

Summarize or transcribe URLs, YouTube/videos, podcasts, articles, transcripts, PDFs, and local files.

Quality

65%

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

Quality

Content

73%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 body is action-packed with executable commands and tight organization, scoring well on actionability and progressive disclosure. It loses points on workflow clarity for lacking explicit validation checkpoints in batch/transcription flows, and slightly on conciseness due to the migration note.

Suggestions

Add an explicit validation/verification checkpoint for the transcript flow (e.g., 'verify transcript length before returning; if >N tokens, summarize first') to lift workflow clarity above 3.

Remove or relocate the 'PilotDeck Migration Note' section — it is review metadata not relevant to using the skill, adding tokens without user value.

Tighten the 'best-effort transcript extraction; no yt-dlp needed' aside into a single concise note to improve token efficiency.

Dimension	Reasoning	Score
Conciseness	The body is largely lean — short flag lists, tight code blocks, minimal preamble — with only minor over-explanation like the 'best-effort transcript extraction; no yt-dlp needed' aside and the migration note that could be trimmed.	4 / 5
Actionability	It provides copy-paste-ready, executable CLI commands covering the common cases (URL, PDF, YouTube summary, YouTube transcript) plus concrete flag syntax and env-var names, matching 'fully executable; copy-paste ready'.	5 / 5
Workflow Clarity	For the transcript case it gives a short feedback loop ('return a tight summary first, then ask which section to expand'), but most flows lack explicit validation/checkpoints and the skill performs batch/transcription work, so a score of 3 fits.	3 / 5
Progressive Disclosure	Content is well organized into clearly signaled sections (Quick start, YouTube, Model+keys, flags, Config) with one-level inline reference to a config file; no bundle files exist so it relies on self-contained sections, with only minor gaps.	4 / 5
	Total	16 / 20 Passed

Description

57%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 names a broad domain and two concrete actions with good natural-term coverage, but lacks an explicit 'Use when...' trigger clause, which the rubric caps at completeness 3. Voice is correctly third person.

Suggestions

Add an explicit 'Use when...' clause naming trigger phrases users would say (e.g., 'Use when the user asks to summarize an article, transcribe a video, or digest a URL/PDF').

Add one or two more concrete actions beyond summarize/transcribe (e.g., 'extract content', 'digest') to broaden capability specificity.

Include file extensions and synonyms (e.g., .pdf, .mp3, audio) to push trigger-term coverage to comprehensive.

Dimension	Reasoning	Score
Specificity	It names the domain (URLs, videos, PDFs, etc.) and two concrete actions ('Summarize' and 'transcribe'), but no additional distinct actions like extracting or clipping, matching 'names domain and 1-2 concrete actions'.	3 / 5
Completeness	It clearly states 'what' the skill does but has no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the rubric guidelines.	3 / 5
Trigger Term Quality	It covers many natural terms users say (URLs, YouTube/videos, podcasts, articles, transcripts, PDFs, local files) with synonyms and file types, though it omits some extensions like .pdf/.mp3 and explicit trigger phrasing.	4 / 5
Distinctiveness Conflict Risk	The mix of summarize/transcribe across many input types is somewhat specific but could overlap with general summarization or transcription skills, fitting 'somewhat specific but could still overlap'.	3 / 5
	Total	13 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: OpenBMB/PilotDeck
Path: skills/summarize/SKILL.md
Commit: 9a33f4d

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.