summarize

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

2.63x

Quality

79%

Does it follow best practices?

Impact

87%

2.63x

Average score across 3 eval scenarios

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./apps/picooraclaw/cmd/picooraclaw/internal/onboard/workspace/skills/summarize/SKILL.md

The canonical home for this skill is summarize in HKUDS/nanobot

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 body is a tight, command-first reference with executable examples for every main use case and a sensible decision rule for oversized transcripts. The only notable deduction is the use of version-pinned model identifiers that will age poorly, which the rubric treats as time-sensitive content.

Suggestions

Move pinned model identifiers (e.g., "google/gemini-3-flash-preview", "openai/gpt-5.2") into a clearly labeled section for current defaults so they can be updated or deprecated without penalizing the skill body.

Clarify model selection precedence in one place (CLI --model vs. config file vs. built-in default) to remove the slight redundancy between Quick start and the Model + keys section.

Dimension	Reasoning	Score
Conciseness	The body is lean — quick-start commands, a flag list, env keys, and a config snippet with no concept explanations. Not 5 because time-sensitive version-pinned model IDs ("google/gemini-3-flash-preview", "openai/gpt-5.2") appear outside any 'old patterns'/deprecated section, which the guidelines penalize.	4 / 5
Actionability	Quick-start commands are copy-paste executable and cover the three main cases (URL, local file, YouTube), followed by concrete flag syntax ("--youtube auto --extract-only", "--length short\|medium\|long\|xl\|xxl\|<chars>") and named env vars. Specific examples cover the common cases fully.	5 / 5
Workflow Clarity	This is a simple, single-purpose skill whose primary action is unambiguous, which the simple-skill exception allows to score 5; additionally the transcript section includes a decision rule ("If the user asked for a transcript but it’s huge, return a tight summary first, then ask which section/time range to expand"). No destructive or batch operations require validation checkpoints.	5 / 5
Progressive Disclosure	There are no bundle files to reference, and the body is short and cleanly sectioned (When to use, Quick start, YouTube, Model + keys, Flags, Config), fitting the simple-skill exception for progressive disclosure. Not below 5 because nothing that belongs in a separate reference file is inlined.	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.

A compact, third-person description that clearly states what the tool does and includes a natural quoted trigger phrase. Its main weakness is the absence of an explicit 'Use when...' clause, leaving the triggering conditions only weakly implied.

Suggestions

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

Include more natural synonyms users would say, such as "article", "link", and file extensions like .mp3/.mp4.

Consider naming one or two distinguishing capabilities (e.g., transcript extraction without yt-dlp, JSON output) to further separate it from generic summarization skills.

Dimension	Reasoning	Score
Specificity	Quotes like "Summarize or extract text/transcripts from URLs, podcasts, and local files" list several concrete actions (summarize, extract text, extract transcripts) with concrete input types. Not 5 because coverage has minor gaps (e.g., no mention of output formats or extraction methods); not 3 because more than 1-2 actions are named with specific sources.	4 / 5
Completeness	The "what" is clear ("Summarize or extract text/transcripts from URLs, podcasts, and local files"), but the "when" is only weakly implied by the parenthetical "(great fallback for “transcribe this YouTube/video”)". Per judging guidelines, a missing explicit 'Use when...' clause caps completeness at 3; not 2 because the fallback phrase does provide a weak implied trigger.	3 / 5
Trigger Term Quality	Includes natural user phrases such as "transcribe this YouTube/video", "summarize", "URL", and "podcasts". Not 5 because common variants like "article", "link", or file extensions (.mp3, .mp4) are missing; not 3 because the natural quoted trigger phrase goes beyond bare domain keywords.	4 / 5
Distinctiveness Conflict Risk	The URL/podcast/video summarization and transcript-extraction niche is mostly distinct, anchored by the quoted trigger "transcribe this YouTube/video". Not 5 because it could still overlap with general summarization or transcription skills; not 3 because the specific input sources and fallback framing keep it largely distinguishable.	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: oracle-devrel/oracle-ai-developer-hub
Path: apps/picooraclaw/cmd/picooraclaw/internal/onboard/workspace/skills/summarize/SKILL.md
Commit: 93ecdd7

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.