跳到正文
cccskills
免费在 GitHub 公开

lawve-public-due-diligence-gate-ignacio-adrian-lerer

Use for due diligence, legal-financial risk review, investment or business transaction checklists, and preliminary screening where facts, documents, assumptions, legal uncertainty, debt/equity, assets/liabilities, contracts, tax, regulatory, compliance, technology/product, and financial-model issues must be separated clearly.

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.md5.3 KB
  • README.md327 B

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Lawve Public Due Diligence Gate

Use this skill for due diligence explanations, checklists, triage notes, and preliminary reports. It identifies issues and missing materials; it does not deliver a final legal opinion.

This file is self-contained for loaders that read only SKILL.md. If other skills are available, it can also be paired with legal uncertainty, truth-first reasoning, or financial glossary skills, but it must work without them.

Core Rule

Separate facts, documents, assumptions, risks, and required specialist review. Do not convert missing evidence into confident conclusions.

Reasoning Standard

  • Verify before validating a claim.
  • Distinguish fact, documented evidence, management statement, assumption, inference, and legal/financial conclusion.
  • If a material point is unknown, mark it as Missing or ESCALATE; do not fill the gap with generic caution.
  • If the requested output could be relied on externally, add a clear reliance boundary.

Public Scope

Safe public outputs may include:

  • document/request lists;
  • red flag categories;
  • generic due diligence checklists;
  • preliminary risk mapping;
  • PASS / ESCALATE / BLOCK gate notes;
  • plain-language distinctions such as debt vs equity, cash flow vs profit, asset vs liability, EBITDA vs cash.

Do not include:

  • privileged or confidential factual content unless the user explicitly provides it for the active matter;
  • client-specific negotiation tactics unless the user asks for strategy work;
  • final legal, tax, accounting, or investment conclusions beyond the reviewed materials.

Intake Contract

Before relying on an answer, identify:

  • transaction or project type;
  • jurisdiction(s);
  • parties and roles;
  • intended reliance: preliminary triage, client memo, investor presentation, negotiation, filing, or closing;
  • available documents;
  • missing documents;
  • financial model or business assumptions being relied on;
  • legal/tax/accounting topics outside ordinary certainty.

Due Diligence Buckets

Check these buckets and mark each as OK, Issue, Missing, or ESCALATE:

  • corporate existence, authority, ownership, cap table;
  • contracts, customer/vendor obligations, termination, exclusivity, change of control;
  • debt, RF, loans, repayment, interest, guarantees, liens, covenants;
  • equity, shareholder rights, dilution, founder value, governance, distributions;
  • assets, title, leases, licenses, IP, vehicles/equipment, possession vs ownership;
  • liabilities, litigation, tax, labor, regulatory, insurance, environmental where relevant;
  • accounting/finance consistency: cash flow vs profit, EBITDA vs cash, CapEx vs OpEx, book vs market value;
  • data/privacy/AI issues where technology or AI tools are part of the deal;
  • product, compliance, governance, and deployment-risk issues for legal-AI or integrity/compliance tools;
  • assumptions that require local counsel, tax advisor, accountant, auditor, or sector specialist.

Financial Concept Checks

Use these public-safe distinctions when a deal, investment, calculator, or business model is involved:

  • Cash flow is timing of cash in/out; profit is accounting result after expenses. Positive profit does not guarantee liquidity.
  • EBITDA is operating performance before interest, taxes, depreciation and amortization; it is not free cash flow or approved dividends.
  • CapEx buys long-term assets; OpEx supports current operations.
  • Debt/RF requires interest and repayment or refinancing; equity shares ownership, risk and upside.
  • Market value reflects expected/current market value; book value reflects accounting carrying value.
  • Assets may generate value; liabilities require settlement.
  • ROI evaluates return on an investment/project; ROE evaluates return on shareholder equity.

If any of these concepts are mixed in the source material, flag the issue and propose clearer labels.

Output Gate

Use this compact structure:

State: PASS | ESCALATE | BLOCK
Purpose:
Materials reviewed:
Key assumptions:
Confirmed points:
Open issues:
Missing documents:
Risks by bucket:
Required next step:
Safe for external reliance: yes/no

Decision Rules

  • PASS: documents and assumptions are sufficient for the limited stated purpose.
  • ESCALATE: material uncertainty remains, but the work can continue after targeted evidence or specialist review.
  • BLOCK: reliance, signing, filing, investment, or publication would be unsafe.

Public Wording Standard

Use cautious but concrete language:

  • "Based on the materials reviewed..." rather than "it is certain".
  • "Requires tax/accounting/local counsel review" when the issue turns on specialist advice.
  • "The model assumes..." when a financial output depends on unverified inputs.
  • "This is a preliminary due diligence screen, not a legal opinion" when external reliance is likely.

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