sentiment-analysis

Extracts the true audience mood and key feedback by analyzing comment sentiment and keyword frequency.

Quality

67%

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/sentiment-analysis/SKILL.md

Quality

Content

85%

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

The body is concise, well-organized, and gives a clear sequenced workflow with named tools, but the central analysis step leans on subjective judgment rather than a fully specified, reproducible method, which is the main actionability gap.

Suggestions

Tighten the Analyze step with a concrete, reproducible procedure — e.g. how to combine the heuristic's output with semantic judgment and a defined keyword-frequency threshold — rather than 'gauge the overall mood'.

Optionally show the expected shape of the `analyze_sentiment_heuristic` call and its return values so the step is executable rather than descriptive.

Add a brief verification cue for the synthesis (e.g. confirm top keywords map to the sentiment summary before presenting) to make the workflow self-checking.

Dimension	Reasoning	Score
Conciseness	The body is lean with no padding and no explanation of concepts Claude already knows; directives like 'Do not just list the comments. Write a cohesive executive summary' earn their place and assume Claude's competence.	3 / 3
Actionability	Names concrete tools (`get_video_comments`, `analyze_sentiment_heuristic`) and a specific range (20-50 comments), but the core analysis step is partly abstract ('gauge the overall mood', 'extract the most frequently mentioned keywords') without a fully pinned-down, executable method, falling short of copy-paste-ready guidance.	2 / 3
Workflow Clarity	Presents a clear three-step sequence (Fetch → Analyze → Synthesize) for a simple, read-only analysis task with no destructive or batch operations requiring validation checkpoints, matching the simple-skill allowance for a score of 3.	3 / 3
Progressive Disclosure	The skill is under 50 lines, needs no external references, and is organized into clear labeled sections, satisfying the simple-skill criterion for a top progressive-disclosure score with no bundle files present.	3 / 3
	Total	11 / 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 clearly conveys what the skill does with concrete, domain-specific language, but it omits any explicit trigger guidance for when Claude should invoke it and lacks the breadth of natural trigger terms that would make it maximally discoverable and distinct.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when the user asks about audience reaction to a video, wants to gauge comment sentiment, or needs a summary of viewer feedback.'

Broaden trigger terms to include phrasings users naturally say, such as 'YouTube comments', 'video comments', 'viewer reaction', or 'audience feedback'.

List a few more discrete concrete actions (e.g. 'summarize recurring complaints and praises, rank frequent keywords') to reach the score-3 specificity anchor.

Dimension	Reasoning	Score
Specificity	Names the domain and a couple of concrete actions ('Extracts the true audience mood and key feedback', 'analyzing comment sentiment and keyword frequency') but does not list multiple discrete specific actions like the score-3 anchor.	2 / 3
Completeness	Clearly states what the skill does but provides no explicit 'Use when...' trigger guidance, which caps completeness at 2 per the judging guidelines.	2 / 3
Trigger Term Quality	Contains natural terms ('comment sentiment', 'keyword frequency', 'audience mood') but misses common variations users would actually say such as 'YouTube comments', 'video comments', or 'viewer reaction'.	2 / 3
Distinctiveness Conflict Risk	The sentiment-analysis niche is reasonably distinct from broad skills but 'audience mood / sentiment' is generic enough that it could overlap with other analysis skills; it lacks the maximally distinct narrow triggers of a score-3 example.	2 / 3
	Total	8 / 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/sentiment-analysis/SKILL.md
Commit: a862ebc

Reviewed: about 11 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.