carbon.data.qa

Answers carbon accounting queries from datasets and APIs with cited sources and vintage data.

Updated Aug 9, 2025
One-click install
npx skills add https://github.com/chrislyons/carbon-acx --skill carbon-data-qa
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: carbon.data.qa
Source: https://github.com/chrislyons/carbon-acx/tree/main/.claude/skills/project/carbon-data-qa
Command: npx skills add https://github.com/chrislyons/carbon-acx --skill carbon-data-qa

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pandas, PyYAML, and includes references (resource) components.

What problem does it solve?

Manually sifting through carbon accounting datasets to answer specific analytical questions is time-consuming and error-prone. This skill allows you to query your carbon data using natural language, providing instant, accurate, and cited answers.

Core Features & Use Cases

  • Natural Language Queries: Ask questions about emissions, activities, and factors in plain English.
  • Unit-Aware Calculations: Automatically performs calculations and provides results with correct units (tCO2e, kgCO2e).
  • Source & Provenance Tracking: Every answer includes data sources and vintage, ensuring auditability.
  • Use Case: A sustainability analyst needs to quickly compare emissions from cloud storage vs. streaming. Instead of manual lookups, they ask, "Compare emissions: cloud storage vs streaming," and get a contextualized answer, saving hours of data digging and letting "AI works, you rest."

Quick Start

Example: Basic Emission Factor Query

User: "What's the emission factor for a cup of coffee?"

Output:

Coffee Emission Factor:

- Activity: FOOD.COFFEE.CUP.HOT (12 oz hot coffee cup)

- Emission Factor: 0.021 kgCO2e/cup

- Source: [SRC_FOOD_2023] Coffee supply chain LCA

- Vintage: 2023

- Scope: Includes bean production, roasting, brewing, waste

Frequently Asked Questions about carbon.data.qa

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I query emissions data using natural language questions?

Query emissions data by asking plain-English questions about activities, factors, and carbon footprints. The Skill processes your query against internal datasets, performs unit-aware calculations, and returns precise answers with cited sources, data vintage, and scope details—no manual lookups required.

Can I convert between different carbon accounting units automatically?

Yes, unit conversions are automatic. The Skill handles conversions like kWh to kgCO2e and other emissions units, ensuring results maintain correct units (tCO2e, kgCO2e) and source citations for full auditability.

What data sources and provenance information does this provide?

Every answer includes source citations, data vintage year, and scope breakdown. This ensures you can audit emissions answers, understand which datasets were queried, verify calculation layers, and confirm when data was last updated.

How do I compare emissions across different activities or sectors?

Ask comparative questions directly—for example, 'Compare emissions: cloud storage vs streaming.' The Skill queries datasets across layers and sectors, applies consistent units, and returns contextualized comparisons with provenance, saving hours of manual data digging.

What happens when a carbon accounting query is ambiguous?

The Skill surfaces clarifying questions to resolve ambiguity before returning answers. This ensures results match your intent and prevents incorrect emissions calculations or misaligned scope assumptions.

Does this work with existing pandas and YAML-based carbon datasets?

Yes, the Skill operates on pandas and PyYAML dependencies in a read-only data environment, querying from data/ directories and internal tools. It integrates with existing carbon accounting dataset structures without modifying source files.