跳到正文
cccskills
免费在 GitHub 公开

legal-transition-audit-ignacio-adrian-lerer

Audits the transition from legal AI output to reliance, recommendation, execution, or real-world commitment. Use it before an AI-generated analysis, memo, contract review, compliance finding, or workflow output is acted upon to check whether authority, evidence, mandate, uncertainty, procedure, and review conditions remain sufficient.

中文简介正在准备中。当前显示原文说明。

实测评分 未实测

查看安装方法

包含的文件(2)

  • SKILL.md5.9 KB
  • README.md336 B

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Legal Transition Audit

What This Skill Does

This skill audits the step between legal AI output and real-world consequence.

It is designed for the moment when an analysis may become reliance, a recommendation may become action, or an automated workflow may affect rights, duties, deadlines, assets, filings, communications, or institutional decisions.

It does not replace legal analysis. It governs the transition from analysis to action.

Core Question

Should this output be allowed to move into reliance, recommendation, execution, or commitment now?

Transition States

Use one of these states:

  • PROCEED: the transition is supported and may move forward.
  • QUALIFY: the output may be used only with visible limits, caveats, or assumptions.
  • ESCALATE: the transition requires human, specialist, client, institutional, or procedural review.
  • REFUSE: the transition must not occur because material conditions are missing or invalid.

Audit Protocol

1. Identify the Proposed Transition

State what movement is being proposed:

  • draft to final;
  • analysis to recommendation;
  • recommendation to client advice;
  • review to approval;
  • approval to signature;
  • finding to filing;
  • output to automated execution;
  • internal assessment to external communication;
  • legal conclusion to operational or financial consequence.

If no transition is specified, classify the output as analysis only.

2. Consequence Mapping

Identify what changes if the transition occurs:

  • rights, duties, liabilities, deadlines, payments, assets, or records;
  • court, regulator, client, counterparty, employee, consumer, shareholder, or public-facing effect;
  • irreversible or difficult-to-reverse consequence;
  • reputational, compliance, privilege, confidentiality, or procedural impact.

The stronger the consequence, the stronger the transition controls must be.

3. Evidence Sufficiency

Check whether the output has enough evidentiary support for the proposed transition.

Ask:

  • Are source documents, legal authorities, and factual premises identified?
  • Are material citations current and verifiable?
  • Are missing facts visible?
  • Are assumptions separated from verified facts?
  • Are conflicts or contrary authorities disclosed?
  • Is the conclusion stronger than the evidence permits?

If evidence is insufficient, the output may not proceed without qualification, escalation, or refusal.

4. Authority and Mandate

Check whether the system, user, or institution has authority to make the transition.

Ask:

  • Who authorized the transition?
  • What is the source and scope of the mandate?
  • Does the mandate cover this jurisdiction, matter, client, entity, risk, or action?
  • Has authority expired, been revoked, exceeded, or become contested?
  • Does the transition require approval by a lawyer, client, board, supervisor, court, regulator, or other institutional actor?

Do not allow an output to create authority for itself.

5. Procedure and Timing

Check whether procedural conditions remain satisfied at the moment of transition.

Ask:

  • Are deadlines, limitation periods, procedural steps, notices, approvals, or waiting periods still valid?
  • Has the legal or factual context changed since the output was generated?
  • Has a new document, instruction, evidence item, policy, or authority superseded the basis of the output?
  • Is the transition occurring after interruption, handoff, delegation, restoration, or reentry?

If conditions have changed, re-test before action.

6. Uncertainty and Contestability

Check whether uncertainty remains visible and contestable before reliance.

Material uncertainty includes:

  • unresolved factual disputes;
  • ambiguous legal standards;
  • conflicting authorities;
  • stale or unverified sources;
  • jurisdictional mismatch;
  • unclear client objectives;
  • unresolved privilege or confidentiality issue;
  • model/tool limitations that affect the conclusion.

If uncertainty is hidden by fluent prose, do not proceed.

7. Transition Decision

Assign a transition state:

  • PROCEED only if evidence, authority, procedure, timing, and uncertainty controls are sufficient.
  • QUALIFY if the output may be used with explicit limits.
  • ESCALATE if a responsible person or institution must decide.
  • REFUSE if the transition would be unsupported, unauthorized, procedurally defective, or materially misleading.

Output Format

## Legal Transition Audit

Transition State: PROCEED | QUALIFY | ESCALATE | REFUSE

### Proposed Transition
| From | To | Consequence | Status |
|---|---|---|---|

### Transition Conditions
| Condition | Finding | State |
|---|---|---|
| Evidence sufficiency |  |  |
| Authority and mandate |  |  |
| Procedure and timing |  |  |
| Uncertainty visibility |  |  |
| Contestability |  |  |

### Blocks or Qualifications
| Issue | Effect on transition | Required action |
|---|---|---|

### Permitted Use
- May be used for:
- Must not be used for:
- Required before further action:

Non-Negotiable Rules

  • Do not move from output to action merely because the output is plausible or well written.
  • Do not allow uncertainty to disappear at the point of reliance.
  • Do not treat authority, mandate, evidence, or procedure as historical facts only; they must remain valid when the transition occurs.
  • Do not execute, file, sign, send, approve, or advise on the basis of an output whose transition state is ESCALATE or REFUSE.
  • The transition itself is the object of review.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Public-safe preliminary screen for challenges to the impartiality of an AI evaluator, LLM-as-a-judge, decision-support agent, or adjudicative system based on prior outputs, suspected bias, unstable reasoning, or self-reinforcing memory. Use when asked whether an AI should be recused, disqualified, replaced, audited, or escalated. Does not decide real cases or claim that human judicial-recusal doctrine automatically applies.

中文简介正在准备中。当前显示原文说明。

lawve-ai/awesome-legal-skills8952026年10月20日 更新

Creates an Agent Authority Charter for enterprise or regulated AI agents before deployment. Use this Skill when a user needs to define what an AI agent is allowed to do, who delegated authority to it, what actions are permitted or prohibited, when human approval is required, what evidence must be preserved, and how the agent can be suspended, revoked, or escalated.

中文简介正在准备中。当前显示原文说明。

lawve-ai/awesome-legal-skills8952026年10月20日 更新

EU AI Act Knowledge Engine — authoritative regulatory Q&A grounded in 70 official EU source documents (including the 2026 Commission draft guidelines on Art. 6 high-risk classification — general principles, Annex I, Annex III). Answers any question about the AI Act with article-level citations from the full regulation text, Commission guidelines, EDPB/EDPS opinions, codes of practice, harmonised standards, FRIA guides, incident templates, and sector-specific guidance. This skill should be used when the user asks about the "EU AI Act", "AI Act regulation", "Regulation 2024/1689", "KI-Verordnung", asks to "explain an AI Act article", "what does Article X say", "AI Act requirements", "AI Act penalties", "AI Act timeline", "GPAI obligations", "high-risk AI", "prohibited AI practices", "AI Act and GDPR", "fundamental rights impact assessment", "AI Act standards", "AI Act national implementation", "AI literacy", "serious incident reporting", "Digital Omnibus", "AI regulatory sandbox", or any question about EU artificial intelligence regulation. Also triggers on German terms: "KI-Gesetz", "KI-Verordnung", "Hochrisiko-KI", "KI-Kompetenz", "Grundrechte-Folgenabschaetzung", "GPAI-Verhaltenskodex". For assessment workflows that produce a classification decision rather than a knowledge answer, offer to run a structured risk-tier classification in-session.

中文简介正在准备中。当前显示原文说明。

lawve-ai/awesome-legal-skills8952026年10月20日 更新

This skill builds a structured audit trail of an AI-assisted task: what the tool was asked to do, what materials it was given, what it produced, how the output was verified, and what was ultimately relied upon. It documents the workflow for supervision and later review without ruling on privilege or disclosure, so the record stays accurate rather than self-serving.

中文简介正在准备中。当前显示原文说明。

lawve-ai/awesome-legal-skills8952026年10月20日 更新

Use this skill when the user wants an AI governance, legal-risk, privacy, compliance, procurement, or vendor-risk review of an internal AI use case, an AI product feature, an LLM workflow, or a third-party AI vendor. The skill asks intake and clarifying questions first when facts or evidence are missing, identifies required documentation and missing evidence, maps the use case to AI governance frameworks and applicable legal domains, and produces a preliminary or final governance review with scorecards, findings, owners, remediation actions, and follow-up questions.

中文简介正在准备中。当前显示原文说明。

lawve-ai/awesome-legal-skills8952026年10月20日 更新

Turn an interpretive-ambiguity audit of a legal text — contract, statute, regulation, or judicial opinion — into a polished deliverable. Produces a multi-page website (default), a single-page interactive site, a Microsoft Word document, a PowerPoint deck, or a LaTeX/PDF. Use whenever a user has a stress-test result, ambiguity audit, or "where will this be litigated" scenarios and wants to publish, present, or share them. Triggers on "publish the audit," "make a report from this," "turn this into a website / deck / brief / Word doc," "make a Netlify site," "build slides of these ambiguities," "render the scenarios," "package this stress test," "produce a LaTeX version," and similar. Pairs with the ambiguity-stress-test skill (the underlying analysis) but works on any structured or semi-structured ambiguity analysis. Visual design is opinionated but the user can override colors, fonts, and brand label. Most formats need Python and a writable filesystem; single-file HTML works where the host has neither.

中文简介正在准备中。当前显示原文说明。

lawve-ai/awesome-legal-skills8952026年10月20日 更新

查看 lawve-ai 的全部技能

报告此技能的问题