AutoGineer
Generated banner for Cost Estimation
Generated logo for Cost Estimation

Cost Estimation

MicrosoftOfficialCreated by Microsoft

  • Skill
  • Tool integration
  • Cloud and DevOps
  • MIT
  • No issues found
Download ZIP

From the author

Forecast Azure spend and price planned resources or workloads. WHEN: "forecast Azure spending", "project next month cost", "compare forecast to my planning target", "how much will Azure cost", "estimate VM cost", "compare storage tiers", "compare Azure regions", "retail price", "EA rate card", "negotiated pricesheet". DO NOT USE FOR: configured budget health or alerts, bill analysis, cost spikes, rightsizing, or commitments.
— the description by Microsoft

AutoGineer summary

Written by AutoGineer from the skill’s own files, not by the author

The Azure Cost Estimation skill provides a structured approach to projecting future cloud expenditures and pricing hypothetical workloads. It enables users to perform cost forecasting on existing scopes and retrieve pricing data for specific resources, including public retail rates and negotiated Enterprise Agreement (EA) or Microsoft Customer Agreement (MCA) prices. The skill emphasizes accurate scope definition and parameter handling to ensure reliable financial projections.

What it does

  • Forecasts costs for specific Azure scopes based on historical data.
  • Retrieves public retail pricing for Azure services.
  • Downloads and processes negotiated pricesheets for EA or MCA agreements.
  • Supports filtering by service name and metric types like PreTaxCost or AmortizedCost.
  • Provides structured error handling for common API and configuration issues.
  • Facilitates comparison of different storage tiers and regions.

When to use it

  • When you need to project Azure spending for the upcoming month.
  • When planning new infrastructure and requiring cost estimates for specific resources.
  • When comparing costs across different Azure regions or storage configurations.
  • When you need to access negotiated pricing via an Enterprise Agreement.
  • When you need to validate planned resource costs against a specific budget target.

Advantages

  • Direct integration with Azure pricing and forecast tools.
  • Supports both public retail and negotiated contract pricing.
  • Standardized workflow for distinguishing between forecasts and hypothetical pricing.
  • Clear error handling guidance for common API and scope-related issues.
  • Reduces manual effort in calculating complex cloud resource costs.

Usage examples

“Forecast the costs for my resource group for the next 30 days.”
The agent uses the forecast_costs tool to project spending for the specified resource group scope over the requested period.
“What is the estimated cost for a standard VM in the East US region?”
The agent utilizes pricing tools to retrieve the current retail price for the specified VM configuration in the requested region.
“Download my current EA pricesheet.”
The agent initiates the pricesheet download process and monitors the status until the data is ready for review.
“Compare the cost of storage tier A versus tier B.”
The agent retrieves pricing data for both storage tiers to provide a side-by-side cost comparison for the user.

Install

  1. Download the skill as a ZIP:

    https://mp-staging.autogineer.com/agent-skills/microsoft/cost-estimation/download

  2. Unzip it into the cross-client skills folder of your project:

    mkdir -p .agents/skills && unzip cost-estimation.zip -d .agents/skills

Documentation by Microsoft

Azure Cost Estimation

Quick Reference

IntentWorkflowPrimary tools
Forecast existing spendCost forecastforecast_costs
Price planned resourcesPricing estimatePricing tools

When to Use This Skill

Use for forecasts, pricing, and planning targets.

MCP Tools

ToolUse
forecast_costsForecast a scope.
get_retail_pricesGet public prices.
start_pricesheet_download, get_pricesheet_statusGet Enterprise Agreement (EA) or Microsoft Customer Agreement (MCA) prices.

Fallback: API mappings.

Workflow

  1. Distinguish forecasts from hypothetical pricing.

  2. Confirm scope, assumptions, period, region, OS, and currency.

  3. Load the matching workflow and label every value type.

  4. Never transform MCP results in a shell or interpreter; request tool-side filtering or bounded follow-up queries.

Error Handling

ErrorAction
Ambiguous meterAsk for OS, term, tier, or usage.
Forecast unavailableExplain the history requirement.
Pricesheet pendingHonor the returned polling interval.
Multiple currenciesNever combine currencies.
Server errorRetry once; then report the trace ID.

Files

references/cost-forecast/workflow.md

Cost Forecast Workflow

Use this workflow to project costs for an existing Azure scope.

1. Determine scope and period

forecast_costs defaults to the current month: first day through last day. For custom dates, supply from and to together in YYYY-MM-DD. from must be within the rolling 92-day lookback; to may be in the future.

2. Configure the tool call

ParameterContract
scopeAzure scope path; never a tenant ID
from, toOptional pair; defaults to current month
granularityDaily (default) or Monthly
filterDimension + filterValuesOptional pair using one exact-match dimension
metricPreTaxCost (default), Cost, or AmortizedCost

The MCP tool does not expose grouping, sorting, arbitrary aggregations, includeActualCost, or includeFreshPartialCost.

3. Execute and interpret

Call forecast_costs. If it is unavailable, use the Cost Management Forecast API through tool fallback. Preserve currency, date, scope, actual-versus-forecast status, and the 100-row response limit. Empty or unavailable forecast data is not zero.

For grouped historical data, hand off to cost-analysis. If the requested forecast cannot fit the supported contract, explain the limitation; fallback does not relax it.

Error handling

ErrorAction
Missing date or filter pairSupply both fields.
Historical start older than 92 daysMove from inside the supported window.
Unsupported metric, granularity, or dimensionUse an exposed value.
Forecast unavailableReport unavailable data and offer historical analysis.
ThrottledHonor tool retry guidance and reduce fan-out.

See examples, parameter contract, and guardrails. Use forecast errors for tool-specific remediation.

Requirements and compatibility

Works with: Claude Code, Claude apps, OpenAI Codex, GitHub Copilot, Cursor, Gemini CLI, Kiro, OpenCode, Goose, Amp, Roo Code, JetBrains Junie, Factory Droid, Devin (ex-Windsurf), Mistral Vibe, OpenHands, Letta

“Works with” means the tool reads the open Agent Skills format; a skill written for one tool may use features others lack.

Security

No issues found by our static scan· No issues found

A static scan is not a guarantee. Skills are third-party content: review a skill before you let an agent use it.

Attribution and licence

Created by
Microsoft
Publisher
Microsoft (Official)
Source
microsoft/skills · .github/plugins/azure-cost/skills/cost-estimation · commit 0696600
Licence
MIT License (redistribution allowed)
  • LICENSE (added by AutoGineer from .github/plugins/azure-cost/LICENSE)
  • ATTRIBUTION.md (written by AutoGineer)
Synced

AutoGineer is not affiliated with or endorsed by Microsoft.

Download ZIP

The ZIP holds the skill’s files, its licence files and an ATTRIBUTION.md. Download cost-estimation.zip