kol-discovery

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

Quality

63%

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

72%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.

A tight, well-structured instructional workflow that relies on concrete tool names and clear sequencing rather than padding. Its weak points are the undefined match_score calculation and the absence of any validation or sanity-check step before the ranked list is reported.

Suggestions

Define the match_score explicitly (its components and rough weighting) so the ranking step is reproducible rather than left to judgment.

Add a lightweight validation checkpoint before reporting, e.g. re-verify engagement figures for the top candidates or flag candidates whose sample size is too small to trust.

Trim minor padding such as 'to save their time' and the objective line that duplicates the frontmatter description.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes competence — concrete tool names with no explanation of known concepts — but contains minor trimmable padding such as 'to save their time' and an objective line that repeats the frontmatter's 'rather than just view counts' framing.	4 / 5
Actionability	Every step names concrete tools ('search_youtube', 'get_video_details', 'calculate_engagement_metrics') and includes a concrete output example ('High Engagement of 12%, despite lower subscriber count'), but 'Calculate the match_score' gives no formula or weights, leaving a key executable detail undefined.	4 / 5
Workflow Clarity	The four-step sequence (Search → Data Gathering → Evaluation → Reporting) is clear with conditional branching ('If the user specifies a time frame'), but there are no validation checkpoints — nothing sanity-checks computed metrics or the ranked list before presenting it, and the undefined match_score ranking step is implicit.	3 / 5
Progressive Disclosure	This is a short (under 50 lines) single-purpose skill with no need for external reference files; its content is appropriately self-contained and organized into clear sections (Objective, Execution Steps, Next Actions) with no bundled files to disclose.	5 / 5
	Total	16 / 20 Passed

Description

53%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 concise, specific, and clearly third-person, with a well-defined niche and distinguishing metric focus. Its main weaknesses are the complete absence of a 'when to use' trigger clause and limited keyword coverage (no 'influencer' or platform synonyms).

Suggestions

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

Include natural trigger synonyms such as 'influencer', 'creator', or platform terms (e.g., 'YouTube') so the description matches how users actually phrase the request.

Briefly surface one or two more of the workflow's concrete actions (e.g., filtering out clickbait/low-engagement channels) to raise specificity and distinctiveness.

Dimension	Reasoning	Score
Specificity	Names the domain ('Key Opinion Leaders (KOLs)') and two concrete actions ('Identifies and ranks'), anchored to specific metrics ('engagement metrics, active rate, and sentiment'), but coverage is not comprehensive — the underlying workflow (searching video platforms, gathering stats, filtering, reporting) is not mentioned.	3 / 5
Completeness	Has a clear 'what' (identifies and ranks KOLs by engagement/active rate/sentiment) but no 'Use when...' clause or equivalent trigger guidance, capping completeness at 3.	3 / 5
Trigger Term Quality	Includes relevant natural keywords such as 'Key Opinion Leaders (KOLs)', 'engagement metrics', and 'sentiment', but misses common variations users would say, like 'influencer', 'find creators', or platform names like 'YouTube'.	3 / 5
Distinctiveness Conflict Risk	The KOL-discovery framing with specific metrics ('engagement metrics, active rate, and sentiment') carves a fairly distinct niche, though it could minorly overlap with general social-analytics or sentiment-analysis skills.	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: 2f902cb

Reviewed: 5 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.