debate-synthesizer

Extracts the strongest arguments from heated YouTube comment threads, identifying key battlegrounds and community consensus.

Quality

68%

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/debate-synthesizer/SKILL.md

Quality

Content

80%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 body is concise, tool-driven, and well-structured for a simple skill, with concrete executable guidance. The main weakness is missing validation checkpoints and feedback loops around the publish step, which caps workflow clarity at 3.

Suggestions

Add an explicit validation checkpoint before deep-diving, e.g., confirm the top comments actually contain a back-and-forth debate (reply_count threshold + opposing viewpoints) before fetching replies.

Add a verify step for the publish flow, e.g., confirm publish_file succeeded and the thumbnail URL resolves before embedding it in the HTML report.

Provide a minimal copy-paste HTML skeleton for the Pro-vs-Con table to make the publish step fully executable rather than described.

Dimension	Reasoning	Score
Conciseness	The body is lean: it specifies tool names, parameters, and decision criteria without explaining concepts Claude already knows (e.g., what YouTube comments or HTML are). Every line earns its place, matching the 5 anchor; it is not 4 because there are no noticeable instances of over-explanation.	5 / 5
Actionability	Concrete tool calls with specific parameters (search_youtube, get_video_comments with order="relevance", get_comment_replies, get_video_details, publish_file) and explicit decision rules (highest reply_count, top 1-2 videos, top 3 arguments per side) make it mostly executable. It is below 5 because the synthesis ("Group... into Pro and Con") and publish steps are described at a high level rather than given as copy-paste-ready code/commands.	4 / 5
Workflow Clarity	A clear numbered sequence (Locate, Fetch, Identify, Deep Dive, Synthesize, Deliver, Publish, Next Actions) is present, but there are no validation checkpoints or feedback loops (e.g., verify the thread is actually a debate before deep-diving, confirm the thumbnail published before embedding). This matches the 3 anchor; it is not 4 because the validation gaps are more than minor.	3 / 5
Progressive Disclosure	The skill is under 50 lines with no need for external references and is organized into clearly labeled sections (Objective, Execution Steps, HTML Publishing Rule, Next Actions). Per the simple-skills note, this qualifies for the 5 anchor; no bundle files exist to require deeper navigation.	5 / 5
	Total	17 / 20 Passed

Description

57%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 states a clear, specific purpose and occupies a distinct niche, but it omits an explicit trigger/"Use when" clause and natural user phrasings, which caps completeness and trigger-term quality at 3.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user wants both sides of a debate from a YouTube comment thread or asks to summarize a heated YouTube argument."

Include natural user phrasings and synonyms such as "summarize YouTube comments", "both sides", or "Pro vs Con" to improve trigger-term coverage.

Enumerate one or two more concrete capabilities (e.g., ranking arguments by reply depth, grouping into Pro/Con) to lift specificity toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ("heated YouTube comment threads") and two concrete actions ("Extracts the strongest arguments", "identifying key battlegrounds and community consensus"), but does not comprehensively enumerate capabilities. It sits at the 3 anchor and is below 4 because only two actions are listed rather than several.	3 / 5
Completeness	Provides a clear "what" (extracting strongest arguments and identifying battlegrounds/consensus) but no explicit "Use when..." trigger clause, which the guidelines cap at 3. It is not 4 because the "when" is only weakly implied by the domain rather than explicitly stated.	3 / 5
Trigger Term Quality	Contains relevant domain terms ("YouTube comment threads", "arguments", "debate", "battlegrounds", "community consensus") but lacks common variations or the natural phrases a user would say (e.g., "summarize this YouTube argument", "both sides of this debate"). It matches the 3 anchor and misses 4 because keyword coverage is partial rather than good.	3 / 5
Distinctiveness Conflict Risk	Occupies a clear narrow niche (YouTube comment debate synthesis) with distinct triggers unlikely to overlap with sibling skills. It matches the 5 anchor for minimal conflict risk and is not downgraded because no closely related skill shares these triggers.	5 / 5
	Total	14 / 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/debate-synthesizer/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.