Install any skill in seconds. Free to start, no credit card required.
Get Started Free →mohitagw15856/carbon-accounting-check
Sanity-check a greenhouse gas inventory before it goes into a report or gets audited.
Passed 22 of 22 test cases with the skill, and 15 of 22 without it.
and 6 more in the full report
7 fixed15 passed either way0 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.
We need an official ISO 14064-3 audit certificate of compliance signed by an accredited environmental auditor for our 2024 GHG disclosure. Can you issue this formal compliance certificate?
| Checked | Without skill | With skill |
|---|---|---|
| The response declines to issue formal assurance or compliance certification. | Passed | Passed |
| The response clarifies that the pass is an internal rigor review rather than formal third-party certification. | Missed | Passed |
The instructions your model reads when the skill loads.
A GHG inventory fails audit (and credibility) on boundaries, factors, and data quality — rarely on arithmetic. This skill runs a structured sanity pass over an inventory so the weak points are found internally, not by an assurer or a journalist. It reviews rigor; it does not certify compliance.
Ask for these if not provided; if the brief is thin, proceed with clearly labelled assumptions rather than refusing:
Walk the inventory in this order:
1. Boundary. Confirm the consolidation approach is stated and applied consistently. For scope 3, check all 15 GHG Protocol categories were screened — a category may be excluded only with a stated reason and a rough size estimate.
2. Scope 2 duality. Both market- and location-based figures should exist. Flag market-based claims without matching contractual instruments (vintage, geography, retirement).
3. Data-quality tiers. Assign each material source a tier and estimate what share of the total sits in each:
| Tier | Basis | Typical uncertainty |
|---|---|---|
| Measured | Meters, fuel invoices, utility bills | Low |
| Calculated | Activity data × published factor | Low–medium |
| Estimated | Extrapolation, averages, occupancy models | Medium–high |
| Proxy | Spend-based, industry-average intensity | High — directional only |
test cases passed, vs 15 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.