Name: exploring-llm-costs
Rating: 74.4 (1 reviews)
Author: PostHog

exploring-llm-costs

Investigate LLM spend in PostHog — total cost over time, cost by model, provider, user, trace, or custom dimension, token and cache-hit economics, and cost regressions. Use when the user asks "how much are we spending on LLMs?", "which model / user / feature is most expensive?", "why did cost spike?", wants to build a cost dashboard or alert, or pastes a trace URL and asks about its cost.

Quality

93%

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

Quality

Content

86%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 well-structured, actionable skill body with strong progressive disclosure and executable examples. The main weakness is mild redundancy between Core rules and Tips that slightly inflates the token budget.

Suggestions

De-duplicate the 'Tips' section against 'Core rules': drop restatements of the time-range, embedding-inclusion, and cache-flag rules, keeping each guardrail in one place.

Add an explicit verify checkpoint to the query workflows (e.g. 'confirm both event types are present and the time range is set before returning totals').

Consider trimming the 'Keeping this skill current' section — its guidance largely reiterates the event-level-flag rule already stated in Core rules and the cache/source references.

Dimension	Reasoning	Score
Conciseness	Largely lean and high-signal, but several guardrails are restated across 'Core rules' and 'Tips' (e.g. 'Always set a time range', include $ai_embedding, the cache flag) — minor redundancy that could be tightened.	4 / 5
Actionability	Copy-paste-ready HogQL for total spend and JSON for trace inspection, plus a tool table and pointed recipes; common cases are covered with executable examples.	5 / 5
Workflow Clarity	Workflows are clearly sequenced with 'Core rules' as preventive guardrails, but the read-only query workflows lack explicit validate/verify checkpoints, keeping it just below the top anchor.	4 / 5
Progressive Disclosure	Clear overview in SKILL.md with well-signaled, one-level-deep references to real files in ./references/ (cost-properties, breakdown-patterns, etc.) and a consolidated References section for navigation.	5 / 5
	Total	18 / 20 Passed

Description

100%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 exemplary: third-person voice, concrete capabilities, natural trigger phrases, and an explicit 'Use when' clause. It clearly distinguishes cost analysis from adjacent skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'total cost over time, cost by model, provider, user, trace, or custom dimension, token and cache-hit economics, and cost regressions' — with comprehensive coverage of the skill's scope.	5 / 5
Completeness	Explicitly answers both 'what' (investigate LLM spend, breakdowns, token economics, regressions) and 'when' via a 'Use when the user asks...' clause with concrete trigger phrases.	5 / 5
Trigger Term Quality	Quotes natural user phrases verbatim — 'how much are we spending on LLMs?', 'which model / user / feature is most expensive?', 'why did cost spike?' — plus dashboard/alert and trace-URL triggers, covering common variations.	5 / 5
Distinctiveness Conflict Risk	Niche is PostHog LLM cost investigation with distinct cost-specific triggers; only minor overlap with sibling trace/expensive-user skills, which the body disambiguates.	5 / 5
	Total	20 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 1 suspicious	Warning

	Total	15 / 16 Passed

Repository: PostHog/posthog
Path: products/ai_observability/skills/exploring-llm-costs/SKILL.md
Commit: 6fca5f8

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.