CtrlK
BlogDocsLog inGet started
Tessl Logo

multi-video-synthesis

Performs high-density targeted extraction across 10+ videos to map semantic landscapes, consensus, and controversies.

44

Quality

46%

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/multi-video-synthesis/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, sequenced pipeline with specific tool references, but it lacks executable code, a concrete synthesis mechanism, and validation checkpoints for its batch operation. Grandiose framing adds modest unnecessary bulk.

Suggestions

Add a verification checkpoint after ingestion to confirm how many of the top-10 transcripts were retrieved before synthesis.

Make the synthesis step concrete with a defined method (e.g. clustering arguments by topic) instead of 'cross-reference all transcripts simultaneously'.

Trim marketing language ('ATTENTION GUARDIAN', 'absolute truth', 'knowledge artifact that does not exist elsewhere') to tighten token efficiency.

DimensionReasoningScore

Conciseness

The workflow is mostly lean with specific tool calls and no padding about what videos/transcripts are, but marketing-flavored lines ('ATTENTION GUARDIAN', 'extract the absolute truth', 'knowledge artifact that does not exist elsewhere') keep it from being fully tight, matching anchor 2.

2 / 3

Actionability

Concrete tool names with parameters and defined output formats are given, but there is no executable code and the core synthesis step ('Map the Semantic Vectors', 'Cross-reference all transcripts simultaneously') is abstract without a concrete mechanism, matching anchor 2.

2 / 3

Workflow Clarity

Six clearly sequenced steps with a mandatory gate and a transcript fallback exist, but this batch operation across 10+ videos has no validation/verification checkpoint confirming retrieval or synthesis quality, which per the rubric caps workflow clarity at 2.

2 / 3

Progressive Disclosure

The skill is under 50 lines, has no bundle files, and is organized into clear sections (Objective, Execution Steps, Key Design Principle), so per the scoring notes progressive disclosure can score 3 with well-organized sections alone.

3 / 3

Total

9

/

12

Passed

Description

35%

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 names a clear domain and outcome but leans on invented jargon and lacks any explicit 'when to use' trigger guidance. It is moderately specific but not trigger-friendly or fully concrete.

Suggestions

Replace jargon ('high-density targeted extraction', 'semantic landscapes') with natural user terms like 'summarize and compare multiple YouTube videos'.

Add an explicit trigger clause, e.g. 'Use when the user wants to research, compare, or synthesize findings across 10+ videos.'

State concrete actions (search, fetch transcripts, cross-reference, generate timestamp links) instead of abstract framing.

DimensionReasoningScore

Specificity

Names a domain (videos) and some actions ('targeted extraction', 'map semantic landscapes, consensus, and controversies'), but the actions are abstract and buzzword-laden rather than a list of multiple concrete actions, so it sits at anchor 2 and not 3.

2 / 3

Completeness

It states what the skill does but provides no 'Use when...' trigger clause or equivalent, so per the rubric guideline completeness is capped at 2 rather than 3.

2 / 3

Trigger Term Quality

The terms used ('high-density targeted extraction', 'semantic landscapes', 'consensus and controversies') are invented jargon, not the natural phrases a user would say (e.g. 'summarize videos', 'compare YouTube videos'), matching anchor 1.

1 / 3

Distinctiveness Conflict Risk

The '10+ videos' niche offers some specificity, but the generic research/analysis jargon ('targeted extraction', 'semantic landscapes') could overlap with other analysis skills, matching anchor 2 rather than a clear distinct niche at 3.

2 / 3

Total

7

/

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.