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.

53

Quality

59%

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

65%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 skill body is a compact, actionable, well-structured instruction set with an exact analysis prompt and a concrete deliverable format. Its main defects are cosmetic-but-real workflow errors (duplicate step numbering), some non-instructional marketing padding, and the absence of any error-handling guidance.

Suggestions

Fix the duplicated step numbering (two steps are labeled '3') so the five-step sequence reads 1-5 unambiguously.

Trim the audience-value sentence ('This is highly valuable for B2B marketers...') — it explains why the skill matters rather than what to do.

Add a brief fallback step for when the transcript or metadata fetch fails or returns empty, to close the validation gap.

DimensionReasoningScore

Conciseness

The body is mostly efficient, but the sentence 'This is highly valuable for B2B marketers, advertisers, and gaming publishers looking to optimize trailers or sponsored influencer content' is marketing rationale with no instructional value, and the mandatory disclaimer block adds padding that could be tightened. This matches 'mostly efficient but includes some unnecessary explanation or could be tightened' rather than the leaner anchor 4.

3 / 5

Actionability

Concrete, executable guidance is present: named tool calls ('get_video_transcript(video_id)', 'get_video_details(video_id)'), a verbatim analysis prompt, and a fully specified output structure with per-pillar 0-10 scores and '2 to 3 specific changes'. Minor gaps — no example report and the duplicated step numbering (two steps labeled '3') introduce ambiguity — keep it below fully copy-paste-ready.

4 / 5

Workflow Clarity

The sequence (context, disclaimer, ingest, synthesize, deliver) is present and ordered, but the step list contains two steps both numbered '3', which breaks the sequence labels, and no validation or checkpoint step exists (e.g. what to do if the transcript is unavailable). This fits 'steps listed but... checkpoints missing or implicit' more than 'clear sequence with most checkpoints present'.

3 / 5

Progressive Disclosure

This is a short (under 50 lines), single-purpose instruction skill with no external reference material needed and no bundle files present; the body is organized into clear Objective / Execution Steps / Next Actions sections. Per the simple-skill exception, well-organized sections with no forced external references score 5.

5 / 5

Total

15

/

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 clearly states what the skill does and anchors it to a distinctive named framework, but it lacks any 'when to use' trigger guidance and omits natural vocabulary (YouTube, ad, creative, audit) that users would actually say. It is functional but below the standard of the good examples.

Suggestions

Add an explicit trigger clause, e.g. 'Use when auditing YouTube ads, video creatives, trailers, or sponsored content against Google's ABCD framework.'

Include natural synonyms users would say — 'YouTube ad', 'creative audit', 'trailer', 'video transcript' — to improve trigger-term coverage.

Enumerate the concrete outputs (per-pillar scoring of Attract/Brand/Connect/Direct plus optimization recommendations) to raise specificity.

DimensionReasoningScore

Specificity

The description names the domain ("video asset", "Google's official 'ABCD' framework (Attract, Brand, Connect, Direct)") and one concrete action ("Performs a strict evaluation") plus inputs ("transcript and metadata"), but does not list several specific actions like extracting transcripts or generating scored recommendations — matching the '1-2 concrete actions, not comprehensive' anchor. It is not a 4 because no additional specific capabilities are enumerated.

3 / 5

Completeness

The 'what' is clear (performs an ABCD-framework evaluation of a video based on transcript and metadata), but there is no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines. It is above a 2 because the 'what' is explicit rather than vague.

3 / 5

Trigger Term Quality

Relevant keywords exist ("video", "evaluation", "transcript", "metadata", "ABCD", "Google"), but common natural phrasages a user would say — "YouTube ad", "creative", "audit", "trailer" — are absent. It sits between 'one or two generic keywords' (2) and 'good keyword coverage' (4): some strong niche terms but missing common variations and synonyms.

3 / 5

Distinctiveness Conflict Risk

The named 'ABCD' framework is a clear niche with minimal conflict risk against generic skills; the residual overlap is only with broadly similar 'video analysis' skills because terms like 'YouTube ad' or 'creative audit' that would sharpen the niche are missing. Not a 5 since the trigger surface is not fully distinctive.

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.

Validation — 16 / 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.