kol-discovery

Identifies and ranks Key Opinion Leaders (KOLs) based on engagement metrics, active rate, and sentiment rather than just views.

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./python/agents/youtube-analyst/youtube_analyst/skills/kol-discovery/SKILL.md

Quality

Content

85%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, well-structured, and actionable, naming the specific tools and metrics to use across a clear four-step workflow. Its main gap is the absence of explicit validation checkpoints and an undefined match_score formula, which keep actionability and workflow clarity just below the top anchor.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence: it states the objective, four numbered execution steps, and next actions with no padding or explanation of concepts Claude already knows, matching the 'lean and efficient; every token earns its place' anchor.	5 / 5
Actionability	It names concrete tools to call (search_youtube, get_video_details, calculate_engagement_metrics, analyze_sentiment_heuristic) and specific outputs (engagement_rate, active_rate, match_score, a table), which is mostly executable guidance; it falls short of 5 because formula details and exact match_score computation are not specified.	4 / 5
Workflow Clarity	The four-step Search → Data Gathering → Evaluation → Reporting sequence is clear with a conditional branching hint (use get_date_range first for a time frame), but it lacks explicit validation/checkpoint feedback loops, so it sits just below the 5 anchor.	4 / 5
Progressive Disclosure	For a sub-50-line skill with no bundle files and no need for external references, the body is well organized into Objective, Execution Steps, and Next Actions sections, qualifying for the simple-skill exception that lets progressive disclosure score 5 with just well-organized sections.	5 / 5
	Total	18 / 20 Passed

Description

51%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 is specific and mostly distinct but lacks an explicit 'Use when...' trigger clause, which caps completeness at 3 and weakens trigger-term coverage. It reads as third person and avoids fluff, but is not comprehensive enough for top scores.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks to find, evaluate, or rank influencers/KOLs for a topic.'

Broaden natural keyword coverage to include synonyms users actually say: 'influencers', 'creators', 'influencer marketing', 'YouTube channels'.

List a couple more concrete actions (e.g. 'filters out clickbait, presents a ranked table') to lift specificity toward a 4-5.

Dimension	Reasoning	Score
Specificity	The description names the domain ('Identifies and ranks KOLs') and one concrete action ('ranks ... based on engagement metrics, active rate, and sentiment'), but it lists metric categories rather than multiple distinct concrete actions, matching the 'names domain and 1-2 concrete actions' anchor.	3 / 5
Completeness	It clearly states what the skill does but provides no 'Use when...' clause or equivalent trigger guidance, so per the judging guidelines completeness is capped at 3 (clear 'what', missing 'when').	3 / 5
Trigger Term Quality	It surfaces relevant terms ('KOLs', 'engagement metrics', 'active rate', 'sentiment', 'views') but misses the natural phrases a user would actually say (e.g. 'find influencers', 'influencer marketing', 'YouTube creators'), fitting 'some relevant keywords but missing common variations'.	3 / 5
Distinctiveness Conflict Risk	The KOL/influencer-ranking niche with specific metrics is reasonably distinct and unlikely to trigger for unrelated skills, with only minor overlap risk against general analytics skills, matching 'mostly distinct; minor overlap risk'.	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/kol-discovery/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.