CtrlK
BlogDocsLog inGet started
Tessl Logo

creative-insight-analyzer

Deconstructs high-performing or viral videos to extract actionable creative insights from metadata and transcript.

58

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./python/agents/youtube-analyst/youtube_analyst/skills/creative-insight-analyzer/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

78%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 concise, actionable, and well-structured with named tools and a clear numbered workflow, scoring well across all dimensions. The main weaknesses are a duplicate step-numbering error and the lack of an explicit validation/retry loop, plus a partly descriptive analysis step.

Suggestions

Fix the duplicate numbering (two '3.' steps in Execution Steps) so the sequence is unambiguous.

Make step 2's analysis more concrete by specifying the exact hook/narrative signals to look for rather than 'analyze as a senior creative director'.

Consider adding a light validation checkpoint (e.g. confirm transcript was retrieved before synthesizing the blueprint) to push workflow_clarity toward 5.

DimensionReasoningScore

Conciseness

The body is lean with numbered steps and no conceptual padding Claude already knows; only minor trimmable bits remain (the verbatim disclaimer block and 'analyze the script as a senior creative director' framing), fitting the score-4 'efficient; minor instances of over-explanation' anchor.

4 / 5

Actionability

Concrete tool calls are named with arguments (search_youtube, get_video_details, get_video_transcript(video_id), publish_file) and a mandated exact output message; per the code-vs-instruction note absence of code is acceptable, but step 2's analysis remains descriptive, so it is 'mostly executable guidance with minor gaps' (score-4), not a 5.

4 / 5

Workflow Clarity

Execution steps are clearly sequenced with a length-check branch and a mandatory pre-analysis disclaimer checkpoint; the operation is non-destructive so the destructive-cap does not apply, but a duplicated '3.' numbering and absence of an explicit validate→fix→retry loop keep it at score-4 rather than 5.

4 / 5

Progressive Disclosure

A single under-50-line SKILL.md with no bundle files and clearly organized sections (Objective, Execution Steps, Next Actions) qualifies for score-5 under the guideline that simple skills with no external-reference need score 5 on well-organized sections alone.

5 / 5

Total

17

/

20

Passed

Description

53%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 clear and domain-specific with concrete actions, but it omits any explicit 'when to use' trigger guidance, which caps its completeness and limits trigger-term coverage. Adding a 'Use when...' clause with natural user phrasings would lift the weakest dimensions.

Suggestions

Add an explicit trigger clause such as 'Use when the user wants to analyze a viral or high-performing video, deconstruct a YouTube video's creative strategy, or extract creative insights from a video transcript.'

Include natural user phrasings and synonyms (e.g. 'YouTube video', 'analyze my video', 'video performance', 'creative breakdown') to improve trigger-term coverage.

Optionally list the distinct concrete actions (metadata audit, transcript/hook analysis, viral blueprint synthesis) to raise specificity from 3 to 4-5.

DimensionReasoningScore

Specificity

Quotes 'Deconstructs high-performing or viral videos to extract actionable creative insights from metadata and transcript' — names the domain plus 1-2 concrete actions (deconstruct, extract insights), matching the score-3 anchor; not a 4 because it does not list several specific actions.

3 / 5

Completeness

The description gives a clear 'what' but lacks any 'Use when...' / trigger clause, which per the guidelines caps completeness at 3 and matches the score-3 anchor 'Has a clear what but when is missing or only weakly implied'.

3 / 5

Trigger Term Quality

Terms like 'viral videos', 'creative insights', 'metadata', and 'transcript' are relevant but miss common natural variations users would say (e.g. 'analyze my video', 'YouTube', 'video performance'), fitting the score-3 'some relevant keywords but missing common variations' anchor.

3 / 5

Distinctiveness Conflict Risk

The viral-video creative-analysis niche is mostly distinct with only minor overlap risk against general video skills, matching the score-4 anchor; not a 5 because the trigger phrasing is not crisply differentiated.

4 / 5

Total

13

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
google/adk-samples
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.