CtrlK
BlogDocsLog inGet started
Tessl Logo

product-launch-audit

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

49

Quality

53%

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/product-launch-audit/SKILL.md
SKILL.md
Quality
Evals
Security

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 body is a well-structured, single-purpose workflow with named tools and a clear sequence, but it lacks validation checkpoints and exact tool-invocation details. Progressive disclosure is strong given the skill's simplicity.

Suggestions

Add validation checkpoints after ingestion, e.g. confirm enough launch-window videos were found and that transcripts/comments returned non-empty results before synthesizing.

Specify exact tool call details — how aggregate_comment_sentiment accepts multiple video IDs and the parameter shape for get_date_range — to make the guidance copy-paste ready.

Trim rhetorical questions and definitional asides (e.g. the KOL parenthetical, "a new game, phone, or software") that restate context Claude already knows.

DimensionReasoningScore

Conciseness

The workflow is mostly lean, but rhetorical asides like "Are they praising the graphics? Complaining about the price?" and parentheticals such as "e.g., a new game, phone, or software" and "(Key Opinion Leaders)" explain context Claude already knows and could be trimmed.

2 / 3

Actionability

It names concrete tools (search_youtube, get_video_transcript, aggregate_comment_sentiment, generate_timestamp_url) and specific counts (top 3 videos, 2-3 timestamp links, 7-14 day window), but omits exact call signatures and how multiple video IDs are passed, leaving key details missing.

2 / 3

Workflow Clarity

The five numbered steps (Locate, Creator Verdict, Audience Verdict, Synthesize, Deliver) form a clear sequence, but there are no validation checkpoints for the batch comment-aggregation step, so per the rubric workflow clarity is capped at 2.

2 / 3

Progressive Disclosure

The skill is under 50 lines, single-purpose, and has no bundle files; it is organized into clear sections (Objective, Execution Steps, Deliver, Next Actions), meeting the rubric's allowance for simple skills to score 3 without external references.

3 / 3

Total

9

/

12

Passed

Description

50%

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 conveys a clear, specific deliverable and domain but stops short of providing explicit trigger guidance and natural keyword coverage. It scores a uniform 2 across dimensions.

Suggestions

Add a "Use when..." clause, e.g. "Use when preparing for a client meeting after a product launch and you need to compare creator reviews against audience sentiment."

Include natural trigger terms a seller might actually say ("product launch", "review sentiment", "what creators and audiences are saying") to lift trigger-term quality and distinctiveness.

Enumerate concrete actions (find launch-window videos, ingest creator transcripts, aggregate comment sentiment, synthesize a pitch angle) to push specificity toward a 3.

DimensionReasoningScore

Specificity

Quotes "Provides an executive dashboard comparing Creator vs Audience verdicts" — it names the domain (product-launch sentiment comparison) and a deliverable action, but only one high-level action verb rather than the multiple concrete actions the score-3 anchor requires.

2 / 3

Completeness

It answers "what" (provides a dashboard comparing Creator vs Audience verdicts) but has no "Use when..." clause or equivalent trigger guidance, so per the rubric completeness is capped at 2.

2 / 3

Trigger Term Quality

"product launch" and "executive dashboard" are natural terms a user might say, but the description relies on domain jargon ("Creator vs Audience verdicts") and omits common variations like "reviews", "sentiment", or "what people are saying".

2 / 3

Distinctiveness Conflict Risk

The Creator-vs-Audience product-launch niche is fairly distinctive, but without explicit trigger terms it could overlap with generic YouTube-analysis or sentiment-analysis skills.

2 / 3

Total

8

/

12

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.