Skip to content

/hallucination-red-team

Use when stress-testing draft legal work product for hallucination risk by separating factual claims, legal claims, cited authorities, user-provided information, model-generated information, unsupported claims, uncertainty, and safer revisions.

shell
$ npx -y skills add zgbrenner/agentcounsel --skill hallucination-red-team --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.
  • You can call itInvoke it directly when you want it.
  • Slash command/hallucination-red-team
How auto-invocation works

Context preview

The summary Claude sees to decide when to auto-load this skill.

Use when stress-testing draft legal work product for hallucination risk by separating factual claims, legal claims, cited authorities, user-provided information, model-generated information, unsupported claims, uncertainty, and safer revisions.
Ships withagentcounsel

An open, Markdown-native library of legal skills for AI agents — and the legal professionals who supervise them. AgentCounsel is a collection of standalone legal skills.

Get the whole plugin, auto-invoked
Stats
17
Stars
0
Views
3
Forks
Active
Maintenance
Python
Language
MIT
License
57m ago
Last commit
2mo ago
Created

Repo: zgbrenner/agentcounsel