CtrlK
BlogDocsLog inGet started
Tessl Logo

summarize

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

86

3.44x
Quality

82%

Does it follow best practices?

Impact

100%

3.44x

Average score across 3 eval scenarios

SecuritybySnyk

Advisory

Suggest reviewing before use

SKILL.md
Quality
Evals
Security

Quality

Content

100%

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

This is a strong, well-crafted skill that efficiently teaches Claude how to use the `summarize` CLI tool. It's concise, actionable with real executable commands, and well-structured with clear sections. The YouTube transcript handling guidance (summarize first if huge, then ask about expansion) shows thoughtful workflow design for the most complex use case.

DimensionReasoningScore

Conciseness

The content is lean and efficient. It doesn't explain what summarization is or how CLI tools work. Every section serves a purpose—trigger phrases, quick start examples, flags, and config. No wasted tokens.

3 / 3

Actionability

Provides fully executable, copy-paste ready bash commands for all major use cases (URLs, local files, YouTube). Flags are listed concisely with their options. API key environment variable names are specific and concrete.

3 / 3

Workflow Clarity

This is a simple, single-purpose skill (invoke a CLI tool). The workflow is unambiguous: run the command with appropriate flags. The YouTube section adds a useful decision point (huge transcript → summarize first, then ask about expansion), which is a lightweight but appropriate validation/feedback step.

3 / 3

Progressive Disclosure

For a skill under 50 lines with no need for external references, the content is well-organized into clearly labeled sections (trigger phrases, quick start, YouTube specifics, model/keys, flags, config). No monolithic walls of text or unnecessary nesting.

3 / 3

Total

12

/

12

Passed

Description

64%

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 has good trigger term coverage with natural keywords like 'transcribe', 'YouTube', 'podcasts', and 'summarize' that users would commonly use. However, it lacks an explicit 'Use when...' clause which limits completeness, and the scope of 'local files' and 'URLs' is broad enough to risk overlap with other skills. The parenthetical fallback note is a nice touch for disambiguation but doesn't substitute for formal trigger guidance.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user asks to transcribe, summarize, or extract text from a URL, podcast, YouTube video, or local media file.'

Narrow the scope of 'local files' to be more specific (e.g., 'audio files', 'video files', 'media files') to reduce conflict risk with general file-processing skills.

DimensionReasoningScore

Specificity

Names the domain (URLs, podcasts, local files) and some actions (summarize, extract text/transcripts), but doesn't list comprehensive specific actions beyond summarize/extract.

2 / 3

Completeness

The 'what' is reasonably clear (summarize/extract text from URLs, podcasts, files), but there is no explicit 'Use when...' clause. The parenthetical hint about YouTube/video fallback partially serves as trigger guidance but is not a formal 'when' statement, capping this at 2.

2 / 3

Trigger Term Quality

Includes strong natural trigger terms users would say: 'summarize', 'extract text', 'transcripts', 'URLs', 'podcasts', 'YouTube', 'video', 'transcribe'. Good coverage of common variations including the parenthetical fallback note.

3 / 3

Distinctiveness Conflict Risk

The combination of URLs, podcasts, and transcripts gives it some distinctiveness, but 'extract text from local files' and 'summarize URLs' are broad enough to potentially overlap with general file processing or web scraping skills.

2 / 3

Total

9

/

12

Passed

Validation

72%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation8 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

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

8

/

11

Passed

Repository
deepgram/dglabs-deepclaw
Reviewed

Table of Contents

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.