CtrlK
BlogDocsLog inGet started
Tessl Logo

abcd-framework-audit

Performs a strict evaluation of a video asset using Google's official 'ABCD' framework (Attract, Brand, Connect, Direct) based on transcript and metadata.

60

Quality

68%

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/abcd-framework-audit/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

71%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 well-structured, actionable instruction skill with concrete tool calls, an exact prompt, and a clear deliverable format. Its weak spots are some marketing verbosity in the Objective and a step-numbering bug.

Suggestions

Remove the audience-marketing sentence ('highly valuable for B2B marketers, advertisers, and gaming publishers...') since it adds tokens without guiding Claude's execution.

Fix the duplicate step numbering (two steps are both labeled '3.') so the sequence is unambiguous.

Move the verbatim Open-Source disclaimer to a short, explicitly fenced block and trim redundant framing to reduce token weight.

DimensionReasoningScore

Conciseness

Mostly efficient, but the Objective includes marketing padding ('highly valuable for B2B marketers, advertisers, and gaming publishers...') and the long verbatim disclaimer that Claude does not need explained, so it could be tightened.

3 / 5

Actionability

Gives concrete tool calls (get_video_transcript, get_video_details, publish_file), an exact analysis prompt, an exact disclaimer string, and a specific output schema with 0-10 scores and 2-3 recommendations; minor gaps keep it just below fully copy-paste ready.

4 / 5

Workflow Clarity

Execution Steps are clearly sequenced with a CRITICAL disclaimer checkpoint and a defined deliverable, though the numbering error (two steps labeled '3.') and absence of any verify step are minor gaps.

4 / 5

Progressive Disclosure

This is a short single-purpose skill under 50 lines with no external references needed; it is organized into clear sections (Objective, Execution Steps, Next Actions), satisfying the simple-skill exception.

5 / 5

Total

16

/

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.

The description is specific and reasonably distinctive, naming the ABCD framework and its four dimensions with concrete inputs. Its main weakness is the absence of any explicit 'Use when...' trigger guidance, which caps completeness.

Suggestions

Append a 'Use when...' clause naming natural triggers, e.g. 'Use when auditing YouTube ad creatives, trailers, or sponsored content against the ABCD framework.'

Add common user-facing synonyms to the description such as 'YouTube ad', 'creative audit', or 'ad performance review' to improve trigger-term coverage.

Tighten 'strict evaluation of a video asset' to 'audits YouTube/YouTube ad creatives' to sharpen the niche and reduce overlap with generic video analysis.

DimensionReasoningScore

Specificity

Names the domain (video asset evaluation) and several concrete actions tied to the four ABCD dimensions (Attract, Brand, Connect, Direct) using transcript and metadata; minor coverage gaps keep it below a 5.

4 / 5

Completeness

It clearly states what the skill does but provides no 'Use when...' clause or equivalent explicit trigger guidance, which per the rubric caps completeness at 3.

3 / 5

Trigger Term Quality

Includes natural terms like 'video asset', 'transcript', 'metadata', and 'ABCD framework' that users would plausibly say, though common variants like 'YouTube ad' or 'ad creative' are absent from the description.

4 / 5

Distinctiveness Conflict Risk

The ABCD framework niche is fairly distinct and unlikely to collide with unrelated skills, with only minor overlap risk against general video-analysis skills.

4 / 5

Total

15

/

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.