Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →mohitagw15856/climate-risk-assessment
Assess physical and transition climate risk for a site, product, or portfolio with scenario-based structure.
Passed 18 of 22 test cases with the skill, and 6 of 22 without it.
and 17 more in the full report
12 fixed6 passed either way4 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 12 test cases the skill fixed. Same model, same prompt, with and without the skill.
We operate three major freight logistics hubs across coastal and inland Northern Europe, managing a fleet of heavy transport vehicles with an annual business turnover around €180M. Please run a climate risk assessment for our operations. We need a breakdown of both physical and transition factors, evaluating hazard, exposure, and vulnerability components across multiple climate scenarios and timeframes. Include separate physical and transition risk registers, a financial impact summary with ranges and confidence ratings, practical adaptation options with target decision dates, documented assumptions, and monitoring triggers that would prompt a re-evaluation.
| Checked | Without skill | With skill |
|---|---|---|
| Evaluates climate risks across the three time horizons 2030, 2040, and 2050. | Passed | Passed |
| Assigns a confidence label of High, Medium, or Low accompanied by an explicit reason for each financial impact range. | Missed | Passed |
The instructions your model reads when the skill loads.
Climate risk work goes wrong by being either vague ("weather may worsen") or falsely precise ("flood losses of $4.7M in 2043"). This skill structures an assessment as hazard × exposure × vulnerability, across explicit time horizons and named scenarios, with impact expressed as ranges plus a confidence label. It supports decision-making; it is not an engineering or actuarial study.
Ask for these if not provided; with a thin brief, proceed using labelled assumptions (e.g. "assumed coastal location — confirm") rather than refusing:
1. Structure every risk as hazard × exposure × vulnerability. A hazard (e.g. riverine flood) only becomes a risk when exposure (asset in the floodplain) meets vulnerability (no defenses, 6-week recovery). Score each component, not just the headline.
2. Use three horizons: 2030 / 2040 / 2050. Near-term physical risk is mostly locked in regardless of scenario; scenario divergence dominates from ~2040. Say which effect drives each rating.
3. Label scenarios and use them consistently:
| Label | Character | Physical risk | Transition risk |
|---|---|---|---|
| Orderly | Early, coordinated policy (~1.5–2°C) | Lower long-term | Front-loaded but predictable |
| Disorderly | Late, abrupt policy (~<2°C, delayed) | Moderate | Sharp, repricing shocks in 2030s |
| Hothouse | Weak policy (~3°C+) | High and compounding | Low policy risk, high physical + liability |
Assess at least orderly and hothouse — they bracket the outcome space. Note that transition and physical risk peak in different scenarios; a single-scenario view always understates one of them.
4. Express impact as a range with confidence. Use order-of-magnitude bands tied to the subject's financial scale (e.g. "1–5% of site revenue per event"), and tag each estimate High / Medium / Low confidence with the reason (data quality, model dependence, deep uncertainty).
test cases passed, vs 6 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.