Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →lawve-ai/legal-mdl-audit-ignacio-adrian-lerer
Audits legal AI outputs and workflows for honest compression: unnecessary complexity, false simplicity, excessive caveats, hidden uncertainty and poor cost per legally acceptable output.
Passed 21 of 22 test cases with the skill, and 5 of 22 without it.
and 7 more in the full report
16 fixed5 passed either way1 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 16 test cases the skill fixed. Same model, same prompt, with and without the skill.
When auditing two competing legal AI agent chains—Chain A using 100 tokens yielding an unsafe summary, and Chain B using 500 tokens yielding a legally acceptable contract review—which cost metric does legal MDL auditing prioritize?
| Checked | Without skill | With skill |
|---|---|---|
| Selects cost per legally acceptable output as the primary cost evaluation metric. | Missed | Passed |
The instructions your model reads when the skill loads.
This skill reviews whether a legal AI answer, prompt, workflow, benchmark result, contract review, memo, compliance report, or agent chain is as simple as it can safely be.
It is inspired by Minimum Description Length: good legal reasoning should explain more with less structure, but never by hiding material uncertainty.
Classify the material as:
Review:
Return:
test cases passed, vs 5 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.