Name: abcd-framework-audit
Rating: 52 (1 reviews)
Author: google

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.

Quality

57%

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

Fix and improve this skill with Tessl

tessl review fix ./python/agents/youtube-analyst/youtube_analyst/skills/abcd-framework-audit/SKILL.md

Quality

Content

57%

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

The content is well-organized and gives concrete guidance for a short, single-purpose skill, but it is padded with marketing filler, has a step-numbering error, and lacks validation checkpoints. Actionability is good but weakened by unverified tool references.

Suggestions

Remove the marketing filler ("highly valuable for B2B marketers, advertisers, and gaming publishers...") and tighten the disclaimer to respect the token budget.

Fix the duplicate "3." step numbering so the sequence reads cleanly 1–5, and add a checkpoint for when the transcript fetch fails or returns nothing.

Clarify how get_video_transcript / get_video_details are invoked (confirm they are available tools) or specify fallback behavior, so the guidance is fully actionable.

Dimension	Reasoning	Score
Conciseness	The body is structured and actionable, but includes unnecessary filler ("This is highly valuable for B2B marketers, advertisers, and gaming publishers...") and a verbose disclaimer block that could be tightened.	2 / 3
Actionability	It provides concrete tool calls, a verbatim analysis prompt, and a precise output schema, but the referenced tools (get_video_transcript, get_video_details) are unverified and invoked with a placeholder, with no handling of missing/failing tools.	2 / 3
Workflow Clarity	Steps are listed and sequenced, but two steps share the same "3." label (duplicate numbering) and there are no validation checkpoints for edge cases such as a failed or empty transcript fetch.	2 / 3
Progressive Disclosure	The skill is under 50 lines, needs no external references, and is organized into clear sections (Objective, Execution Steps, Next Actions), meeting the simple-skill bar for progressive disclosure.	3 / 3
	Total	9 / 12 Passed

Description

57%

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 conveys what the skill does and occupies a distinctive niche, but it lacks an explicit "Use when..." trigger clause and misses common natural trigger terms. Specificity is adequate but not comprehensive.

Suggestions

Add an explicit "Use when..." trigger clause (e.g., "Use when evaluating YouTube ad creatives, trailers, or sponsored content against the ABCD framework") to satisfy completeness.

Include natural trigger terms users would actually say — "YouTube ad", "creative audit", "video ad review" — alongside "ABCD framework" to broaden trigger coverage.

Name concrete output actions in the description (e.g., "scores each ABCD dimension out of 10 and recommends optimizations") to lift specificity toward multiple concrete actions.

Dimension	Reasoning	Score
Specificity	Names the domain and a concrete action ("strict evaluation of a video asset") with the ABCD sub-dimensions, but it is a single evaluation task rather than a list of multiple distinct concrete actions like extract/fill/merge.	2 / 3
Completeness	The "what" is clearly stated, but there is no "Use when..." clause or equivalent explicit trigger guidance, which per the guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	"ABCD framework" and "Attract, Brand, Connect, Direct" plus "transcript" and "metadata" are relevant keywords, but common natural variations a user would say (e.g. "YouTube ad", "creative audit", "video ad review") are missing.	2 / 3
Distinctiveness Conflict Risk	The named ABCD framework tied to video-asset evaluation is a clear, distinctive niche unlikely to trigger for unrelated skills.	3 / 3
	Total	9 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: google/adk-samples
Path: python/agents/youtube-analyst/youtube_analyst/skills/abcd-framework-audit/SKILL.md
Commit: a862ebc

Reviewed: about 10 hours 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.