analyzing-expensive-users

Analyze the most expensive users in AI observability and explain why they cost so much. Use when the user asks about top spenders, expensive users, per-user LLM cost, user-level cost drivers, or patterns behind high AI observability spend.

Quality

92%

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

Quality

Content

88%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 skill is highly actionable with executable SQL, a well-sequenced validated workflow, and disciplined cross-skill references; its main weakness is a moderately long body with a few sections that could be tightened or externalized.

Suggestions

Tighten the baseline-query HogQL alias explanation and the decision-tree interpretations in step 3 to reduce token load, since the inline SQL already makes the point.

Consider externalizing the detailed token-economics decision tree into a references/ file and summarizing it inline, to better leverage progressive disclosure for this fairly long body.

The 'Constructing UI links' section is short; fold its specifics into the workflow step that consumes them to reduce a lightly-used standalone section.

Dimension	Reasoning	Score
Conciseness	The body is dense and largely assumes Claude's competence (no basic-concept padding), but several explanatory passages (the HogQL alias caveat, the baseline-unavailable fallback, the decision-tree interpretations) are slightly longer than strictly necessary, keeping it just below the lean anchor.	4 / 5
Actionability	It provides multiple complete, copy-paste-ready SQL queries with exact property names, plus concrete tool-call JSON and URL templates covering the common cases, matching the fully-executable anchor.	5 / 5
Workflow Clarity	The six-step workflow is clearly sequenced, includes explicit validation/checkpoint guidance (baseline-unavailable fallback, 'read traces before explaining causality', 'discover properties before grouping'), and feedback loops for error recovery, matching the clear-sequence-with-explicit-validation anchor.	5 / 5
Progressive Disclosure	Structure is good with a Tools table, Core rules, numbered workflow sections, and one-level-deep cross-references to sibling skills; the cache formula is correctly deferred to exploring-llm-costs/references/cache-accounting.md, though the body itself is fairly long and could push some detail into bundle references.	4 / 5
	Total	18 / 20 Passed

Description

96%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, third-person, and clearly answers both what it does and when to use it with natural trigger terms. Its only mild weakness is some overlap with the related project-wide cost skill.

Dimension	Reasoning	Score
Specificity	The description names a concrete action set ('Analyze the most expensive users in AI observability and explain why they cost so much') which combines ranking users and explaining cost drivers, matching the 'multiple specific concrete actions' anchor.	5 / 5
Completeness	It explicitly states what it does (analyze/explain expensive users) and when to use it ('Use when the user asks about...'), matching the anchor requiring concrete trigger phrases for both what and when.	5 / 5
Trigger Term Quality	It lists natural user phrases ('top spenders, expensive users, per-user LLM cost, user-level cost drivers, or patterns behind high AI observability spend') giving comprehensive coverage of synonyms a user would actually say.	5 / 5
Distinctiveness Conflict Risk	The per-user-cost niche is fairly distinct, but the broad 'AI observability spend' phrasing has minor overlap risk with the sibling exploring-llm-costs skill; it is mostly distinct rather than a perfectly clear niche.	4 / 5
	Total	19 / 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: PostHog/posthog
Path: products/ai_observability/skills/analyzing-expensive-users/SKILL.md
Commit: 06292db

Reviewed: 20 minutes 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.