Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →yogsoth-ai/assumption-audit
Surface all assumptions, classify by vulnerability (load-bearing × likely-false), validate causal logic. Focus on dangerous assumptions — high load-bearing + non-explicit.
Passed 7 of 20 test cases with the skill, and 4 of 20 without it.
and 8 more in the full report
7 fixed1 passed either way11 still failing3 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 are developing a new graph neural network framework for molecular property prediction that relies on static topological conformers. I need a comprehensive audit of the unstated premises underlying this methodology. Please generate a report containing a complete inventory of implicit assumptions, a classification matrix mapping how load-bearing and vulnerable each assumption is, logical validation of the main causal arguments, and a ranked list of which assumptions we should challenge first.
| Checked | Without skill | With skill |
|---|---|---|
| Includes a HARD-GATE block containing a state ledger table with budget targets for web-search, web-research, paper-overview, paper-search, and paper-research. | Missed | Passed |
| Evaluates assumptions using Goldratt's Categories of Legitimate Reservation. | Missed | Passed |
| Ranks assumptions prioritizing those classified as both high-load-bearing and high-vulnerability. | Passed | Passed |
The instructions your model reads when the skill loads.
Systematically audit assumptions underlying a method, theory, or gap.
Need to identify which hidden assumptions are most dangerous — load-bearing yet unexamined.
| Base SOP | Target | ±10% Range |
|---|---|---|
| web-search | 30 | 27–33 |
| web-research | 10 | 9–11 |
| paper-overview | 30 | 27–33 |
| paper-search | 20 | 18–22 |
| paper-research | 10 | 9–11 |
<HARD-GATE>
| SOP | Done | Target | % |
|-----|------|--------|---|
| web-search | ? | 30 | ? |
| web-research | ? | 10 | ? |
| paper-overview | ? | 30 | ? |
| paper-search | ? | 20 | ? |
| paper-research | ? | 10 | ? |
Budget Gate: OPEN/CLOSED (>=80% required to exit)
</HARD-GATE>
Import: web-search, web-research, paper-overview, paper-search, paper-research
test cases passed, vs 4 / 20 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.