Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →lawve-ai/epistemic-fault-line-audit-ignacio-adrian-lerer
Audits legal AI outputs, prompts, skills, workflows and MCP/tool instructions for fluent but unsupported reasoning, missing evidence, overconfidence, hidden assumptions, weak causal links and absent human-review gates.
Passed 16 of 22 test cases with the skill, and 5 of 22 without it.
and 20 more in the full report
14 fixed2 passed either way3 still failing3 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 14 test cases the skill fixed. Same model, same prompt, with and without the skill.
Audit an AI-drafted motion to dismiss claiming the court lacks personal jurisdiction over an out-of-state parent company under the long-arm statute. The draft mentions general corporate fairness principles but fails to cite specific state long-arm statutory subsections or minimum contacts test cases.
| Checked | Without skill | With skill |
|---|---|---|
| Flags grounding as a failed audit fault line. | Missed | Passed |
| Assigns an authority boundary status of ESCALATE. | Missed | Passed |
The instructions your model reads when the skill loads.
This skill reviews legal AI material before it is trusted, installed, published, cited, or used with a client. It does not decide the legal issue. It checks whether the output is grounded enough to rely on, or whether it is merely fluent.
Use it for legal memos, contract reviews, litigation drafts, compliance reports, prompts, third-party skills, MCP/tool instructions, agent workflows, or benchmark answers.
Assess seven fault lines:
Then check the authority boundary: even if the output is well-grounded, does the AI system or user have authority to act on it, or must the matter be escalated to a lawyer, court, regulator, board, compliance officer, client decision-maker, or other competent authority?
Return:
test cases passed, vs 5 / 22 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.