product-launch-audit

Provides an executive dashboard comparing Creator vs Audience verdicts for a recent client product launch.

Quality

63%

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/product-launch-audit/SKILL.md

Quality

Content

72%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 content is a tight, actionable 5-step workflow with specific tool calls and good structure, scoring well on conciseness, actionability, and progressive disclosure. Its main weakness is the absence of validation/feedback steps around the batch comment-aggregation step, which caps workflow clarity at 3.

Suggestions

Add an explicit validation checkpoint after aggregate_comment_sentiment (e.g. confirm sentiment data was returned and that found videos are actually about the launch before synthesizing).

Specify how 'top 3 review videos' are ranked (by view count, relevance, or recency) to close the actionability gap.

Insert a retry/fallback note for steps that can fail (missing transcript, no comments) so the workflow has a feedback loop.

Dimension	Reasoning	Score
Conciseness	The body is efficiently organized into bold numbered steps with concrete tool names; only minor padding (e.g. 'Are they praising the graphics?', 'This tool pulls comments across all the videos at once') could be trimmed, so it sits above a 3 but short of a 5.	4 / 5
Actionability	It names specific tools and parameters (search_youtube with get_date_range/published_after, get_video_transcript on top 3 videos, aggregate_comment_sentiment, generate_timestamp_url, publish_file) giving mostly executable guidance, with a minor gap in how 'top 3' videos are selected.	4 / 5
Workflow Clarity	The five steps (Locate, Creator Verdict, Audience Verdict, Synthesize, Deliver) are clearly sequenced, but the batch aggregate_comment_sentiment step has no validation checkpoint, and the rubric caps workflow clarity at 3 for batch operations missing feedback loops.	3 / 5
Progressive Disclosure	This is a single-purpose, under-50-line skill with no external bundle files and clearly organized sections (Objective, Execution Steps, Next Actions), matching the simple-skill exception that allows a 5 with just well-organized sections.	5 / 5
	Total	16 / 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 produces but omits any explicit 'when to use it' trigger guidance and relies on somewhat jargon-heavy terms, which keeps it mid-range across most dimensions. Distinctiveness is its strongest dimension thanks to the niche Creator-vs-Audience framing.

Suggestions

Add a 'Use when...' clause naming concrete triggers, e.g. 'Use when auditing a client product launch to compare creator reviews against audience sentiment.'

Swap jargon ('verdicts', 'executive dashboard') for natural user terms like 'reviews', 'feedback', 'reception' to improve trigger-term coverage.

List 1-2 more concrete actions (e.g. 'synthesizes a pitch angle from creator and audience feedback') to lift specificity toward a 4.

Dimension	Reasoning	Score
Specificity	Names the domain and 1-2 concrete actions ('comparing Creator vs Audience verdicts', 'executive dashboard') but does not enumerate multiple specific actions, so it is not comprehensive enough for a 4.	3 / 5
Completeness	It gives a clear 'what' (an executive dashboard comparing Creator vs Audience verdicts) but has no 'Use when...' trigger clause, and the guideline caps completeness at 3 when explicit trigger guidance is missing.	3 / 5
Trigger Term Quality	'client product launch' is a natural term, but the description leans on jargon ('verdicts', 'executive dashboard') and misses common variations/synonyms like 'review', 'feedback', or 'reception'.	3 / 5
Distinctiveness Conflict Risk	The Creator-vs-Audience product-launch comparison is a fairly distinct niche with low overlap risk; it stops short of 5 only because the trigger phrasing is not sharply differentiated.	4 / 5
	Total	13 / 20 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/product-launch-audit/SKILL.md
Commit: 2d0c272

Reviewed: 3 days 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.