Analyze Cloud Costs
FreeGain insights into your Langfuse Cloud spending.
Free · Opens the source repo
What Analyze Cloud Costs does
The Analyze Cloud Costs skill is designed for users looking to perform detailed analysis of Langfuse Cloud infrastructure expenses. By leveraging data from Metabase's cost marts, this skill allows users to break down cloud spending into meaningful insights. It provides a structured approach to querying costs, enabling users to understand their expenses across different providers, services, and usage types. Whether you're a developer or a financial analyst, this skill helps clarify where your cloud budget is being allocated and identifies potential areas for optimization.
The workflow begins by clarifying the user's question and selecting the appropriate granularity for the analysis. Users can choose to view headline daily totals, examine cost structures by provider or service, or conduct driver and regression analyses. This flexibility allows for both high-level overviews and in-depth investigations into specific cost drivers. The skill emphasizes the importance of using complete UTC days for accurate reporting and encourages users to start broad before drilling down into specific details.
As users interact with the skill, they will utilize the Metabase tools to extract relevant data, ensuring that their findings are evidence-based. The skill also includes guidelines for constructing queries and interpreting results, which is particularly useful for users who may not be familiar with Metabase. The output is designed to be clear and informative, summarizing key metrics such as total costs, provider splits, and trends over time, while also highlighting any caveats related to data completeness.
In summary, Analyze Cloud Costs is an essential tool for anyone involved in managing or analyzing cloud expenditures within the Langfuse environment. It provides the necessary framework to make informed decisions based on accurate data, ultimately helping organizations optimize their cloud spending.
When to use it
Use this skill when you need to analyze and report on your Langfuse Cloud costs, especially when comparing different providers or usage types.
When not to use it
This skill is not suitable for general cloud cost management outside of the Langfuse environment or for real-time monitoring of costs.
What you can build with it
Cost Structure Analysis
Analyze the breakdown of your cloud costs by provider, service, and usage type to identify spending patterns.
Trend Analysis
Compare current costs against historical data to understand changes in your cloud spending over time.
Driver Identification
Determine the top cost drivers affecting your cloud budget, helping to inform optimization strategies.
How to install Analyze Cloud Costs
View source1. Install with the skills CLI
npx skills add langfuse/langfuse/analyze-cloud-costs --agent claude-code2. Or install it manually
Download the skill folder and drop it into ~/.claude/skills/ for all projects, or .claude/skills/ to scope it to one repo. Restart Claude Code so it picks up the new skill.
Anthropic's agentic coding CLI, and the reference implementation of Agent Skills. Drop a skill folder into ~/.claude/skills and Claude Code loads it automatically whenever a task matches the skill's description. Claude Code docs
Inside SKILL.md
Written by langfuseAnalyze Cloud Costs
Overview
Use this skill for evidence-backed Langfuse Cloud cost analysis. The primary source is the Metabase infra cost dashboard and its production cost marts; the deliverable should name the time window, query grain, top drivers, and caveats.
Workflow
- Clarify the question and choose the grain:
- Headline daily totals: total, AWS, ClickHouse, tracing events, and cost per 100k events.
- Cost structure: provider, service, usage type, operation, account, and day.
- Driver or regression analysis: compare a recent complete-day window against a prior baseline.
- Load
references/cost-marts.mdfor table IDs, field IDs, query examples, and caveats. - Use the Metabase MCP. If the Metabase tools are not visible, discover them with tool search before falling back to manual interpretation.
- Prefer complete UTC days. Avoid treating current-day AWS cost as final because AWS CUR rows can arrive late.
- Start broad, then drill down:
- Provider split.
- Service split within the dominant provider.
- Usage type, operation, and account split for the top services.
- Daily trend when explaining change over time.
- Report only what the queried data supports. If a requested slice is absent, say that no rows were found for that slice instead of inventing a driver.
Query Rules
- Use
mcp__metabase__.queryfor quick reads. Useconstruct_queryplusexecute_querywhen you need to inspect or reuse the opaque query. - Pass
filters,aggregations,group_by, andfieldsas JSON arrays. Some tool schemas may display these as strings; if that happens, serialize the same arrays without changing their shape. - Keep limits explicit and small enough for analysis. Use pagination only when the continuation token is needed.
- Include the Metabase dashboard link or query result context in the final answer when useful.
Output Expectations
Summarize:
- Time window and whether it uses complete UTC days.
- Total cost and provider split when relevant.
- Top cost drivers by service, usage type, operation, or account.
- Trend or baseline comparison when the user asks "why did this change?"
- Caveats, especially incomplete current-day AWS data and ClickHouse credit labeling in the unified mart.
Frequently asked questions about Analyze Cloud Costs
Similar skills
Power BI Semantic Modeling
Optimize your Power BI data models with best practices.
Data Context Extractor
Tailor data analysis skills to your company's needs.
Power BI Performance Troubleshooting
Systematic guidance for optimizing Power BI performance.
Power BI Model Design Review
Optimize your Power BI data models with expert reviews.
Power BI DAX Formula Optimizer
Optimize your DAX formulas for better performance and clarity.
Fabric Lakehouse
Optimize your data solutions with Lakehouse best practices.