summarize

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

Quality

80%

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

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

Quality

Content

100%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 lean, fully actionable single-purpose CLI skill with clear sections and copy-paste commands; it avoids padding and needs no external references. It scores at the top of every content dimension.

Dimension	Reasoning	Score
Conciseness	Lean and efficient with no concept-padding: every section (trigger phrases, quick start, flags, keys, config) earns its place and assumes Claude's competence, matching the anchor-5 example.	5 / 5
Actionability	Copy-paste-ready `summarize` commands cover the common cases (URL, local file, YouTube) plus a concrete flag list and env vars, matching anchor 5's "fully executable; specific examples cover the common cases".	5 / 5
Workflow Clarity	Single-purpose simple skill whose single action (run `summarize`) is unambiguous, with a useful conditional for large transcripts; the simple-skill note permits a 5 here, and there are no destructive/batch operations requiring validation.	5 / 5
Progressive Disclosure	No bundle files exist and the single-file body is well-organized into clear sections; per the rubric's simple-skill note, a sub-50-line skill with no need for external references scores 5 with just well-organized sections.	5 / 5
	Total	20 / 20 Passed

Description

61%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 concise and names concrete capabilities with strong natural trigger terms, but it lacks an explicit "Use when..." clause, capping completeness at 3. Adding explicit activation guidance would lift it into the 4-5 range.

Suggestions

Append an explicit "Use when..." clause naming activation scenarios (e.g., "Use when the user asks to summarize a URL, article, podcast, or video, or to transcribe a YouTube link") to raise completeness above 3.

Add a few more natural synonyms ("article", "transcript", "video") to trigger_term_quality for fuller coverage.

List one more concrete action (e.g., "transcribe", "extract transcript") to push specificity from 3 toward 4-5.

Dimension	Reasoning	Score
Specificity	Names the domain ("URLs, podcasts, and local files") and 1-2 concrete actions ("Summarize or extract text/transcripts"), matching anchor 3; it does not list several distinct actions that would reach anchor 4.	3 / 5
Completeness	Has a clear "what" but only a weakly implied "when" ("great fallback for 'transcribe this YouTube/video'"); per the rubric, a missing explicit "Use when..." clause caps completeness at 3 rather than 4.	3 / 5
Trigger Term Quality	Includes natural terms users say ("summarize", "transcribe this YouTube/video", "podcasts") with good coverage, but a few synonyms (e.g. "article", "transcript") are absent, fitting anchor 4 rather than the comprehensive anchor 5.	4 / 5
Distinctiveness Conflict Risk	Targets a distinct niche (the summarize CLI / transcript extraction) with minimal overlap risk, matching "mostly distinct; minor overlap risk"; it lacks the fully explicit trigger phrasing that would reach anchor 5.	4 / 5
	Total	14 / 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: volcengine/OpenViking
Path: bot/workspace/skills/summarize/SKILL.md
Commit: dbf3fcc

Reviewed: 3 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.