Analyzes LLM token spend and unit-economics to track margin health and report usage costs weekly.

Install

mkdir -p .claude/skills/llm-cost-report && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/16472" && unzip -o skill.zip -d .claude/skills/llm-cost-report && rm skill.zip

Installs to .claude/skills/llm-cost-report

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Weekly LLM spend + unit-economics report — cost by stage (Haiku classifier vs Sonnet reply), by product (Solo 1:1 vs Family group), and per household, plotted against the price. Surfaces margin creep before it becomes a loss. Use to report spend, check the margin, or size the cost impact of a feature. Triggers - cost report, spend, margin, unit economics, how much per household.
381 charsno explicit “when” triggerlonger than Claude Code's old 250-char listing cap (fine on current versions)
Intermediate

Key capabilities

  • Produce weekly LLM spend reports by processing stage
  • Report LLM costs by product (Solo 1:1 vs Family group)
  • Calculate per-household LLM cost
  • Compare per-household cost against premium pricing to determine margin
  • Flag margin creep when per-call tokens grow

How it works

This skill queries AI usage data to calculate LLM spend by processing stage, product type, and per household. It then compares these costs against baselines and premium pricing to identify margin creep.

Inputs & outputs

You give it
AI usage data from `ai_usage` table and PostHog LLM-analytics
You get back
A one-page weekly summary report detailing LLM spend, per-household cost, and margin

When to use llm-cost-report

  • Generate weekly LLM cost report
  • Track per-household LLM spend
  • Calculate the margin impact of a new feature

About llm-cost-report

Produces cost reports based on AI usage metrics, splitting spend by processing stage (classifier vs. reply) and product tier. It flags margin creep and provides baselines for cost analysis.

Weekly LLM spend + unit-economics report — cost by stage (Haiku classifier vs Sonnet reply), by product (Solo 1:1 vs Family group), and per household, plotted against the price. Surfaces margin creep before it becomes a loss. Use to report spend, check the margin, or size the cost impact of a featur

When not to use it

  • When the task is not related to LLM cost reporting
  • When the task does not involve analyzing AI usage data
  • When the task is not focused on unit economics or margin analysis

Limitations

  • `ai_usage` table only stores `household_id / usage_date / message_count`, not tokens/$ directly.
  • Individual-tier orgs cannot create admin keys for `anthropic_usage_report.py`.
  • The skill relies on specific data sources like `ai_usage` table and PostHog LLM-analytics.

How it compares

This skill provides a structured, weekly unit-economics report for LLM spend, focusing on margin and cost per correctly-resolved-first-try message, which is more specific than general cost tracking.

Compared to similar skills

llm-cost-report side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
llm-cost-report (this skill)02moNo flagsIntermediate
quant-analyst1033moNo flagsAdvanced
stock-analyzer712moReviewBeginner
creating-financial-models368moReviewAdvanced

Try saying

Example prompts that trigger this skill in your AI assistant.

You might also like

quant-analyst

zenobi-us

Expert quantitative analyst specializing in financial modeling, algorithmic trading, and risk analytics. Masters statistical methods, derivatives pricing, and high-frequency trading with focus on mathematical rigor, performance optimization, and profitable strategy development.

103355

stock-analyzer

FrancyJGLisboa

Provides comprehensive technical analysis for stocks and ETFs using RSI, MACD, Bollinger Bands, and other indicators. Activates when user requests stock analysis, technical indicators, trading signals, or market data for specific ticker symbols.

71214

creating-financial-models

anthropics

This skill provides an advanced financial modeling suite with DCF analysis, sensitivity testing, Monte Carlo simulations, and scenario planning for investment decisions

36161

reconciliation

anthropics

Reconcile accounts by comparing GL balances to subledgers, bank statements, or third-party data. Use when performing bank reconciliations, GL-to-subledger recs, intercompany reconciliations, or identifying and categorizing reconciling items.

30139

analyzing-financial-statements

anthropics

This skill calculates key financial ratios and metrics from financial statement data for investment analysis

32134

us-stock-analysis

tradermonty

Comprehensive US stock analysis including fundamental analysis (financial metrics, business quality, valuation), technical analysis (indicators, chart patterns, support/resistance), stock comparisons, and investment report generation. Use when user requests analysis of US stock tickers (e.g., "analyze AAPL", "compare TSLA vs NVDA", "give me a report on Microsoft"), evaluation of financial metrics, technical chart analysis, or investment recommendations for American stocks.

24137

Search skills

Search the agent skills registry