decision-ownership-audit-ignacio-adrian-lerer
Audits AI-assisted legal, compliance, governance, and institutional decisions before reliance to determine whether the responsible human or institution has…
Skill by Ignacio Adrián Lerer
Chalk Labs
Need help deploying decision-ownership-audit-ignacio-adrian-lerer?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/lawve-ai-decision-ownership-audit-ignacio-adrian-lerer
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: security, legal
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/decision-ownership-audit-ignacio-adrian-lerer
What's inside
- Skill name
decision-ownership-audit-ignacio-adrian-lerer- Description
- Audits AI-assisted legal, compliance, governance, and institutional decisions before reliance to determine whether the responsible human or institution has enough access to the evidence, reasoning basis, uncertainty, authority, and review path to genuinely own the decision rather than merely approve, sign, or transmit it.
- License
- AGPL-3.0
- Metadata
- author: Ignacio Adrián Lerer · license: agpl-3.0 · version: 2026-06-03
- Instructions
- 170 lines in SKILL.md · view on GitHub
Agent Skills spec issues
- name: "decision-ownership-audit-ignacio-adrian-lerer" does not match folder "decision-ownership-audit-adrian-lerer"
Files (2)
- README.md
- SKILL.md
SKILL.md (first lines)
# Decision Ownership Audit ## What This Skill Does This skill audits whether a person or institution can responsibly rely on an AI-assisted legal or governance output before approving, signing, filing, sending, enforcing, or otherwise acting on it. It does not ask only whether the output is correct, plausible, well written, or formally reviewed. It asks whether the responsible actor has enough access to the basis of the decision to stand behind it as a professional or institutional judgment. Use it for legal memos, litigation strategy, contract review, compliance decisions, regulatory responses, board materials, risk approvals, due diligence conclusions, policy determinations, and other outputs that may move from analysis into reliance. ## Core Question Can the responsible human or institution genuinely own this decision, or are they merely ratifying an output whose basis they cannot inspect, contest, or correct? ## Audit Protocol ### 1. Responsible Actor Identification Identify who is expected to own the decision. Classify the actor as: - lawyer or legal team; - client or business decision-maker; - compliance officer; - board, committee, or management body; - public authority or institutional officer; - automated or semi-automated workflow with a named human sponsor. If no responsible actor is identifiable, the output is not ready for reliance. ### 2. Decision Surface State what the actor is being asked to do with the output: - read only; - use as background; - rely on for professional analysis; - recommend a course of action; - approve, sign, file, send, or enforce; - execute through an automated system; - affect third-party rights, duties, assets, deadlines, or legal position. Higher-consequence uses require stronger ownership conditions. ### 3. Evidence Access Check whether the actor can inspect the evidence supporting each material conclusion. The output should expose: - source documents or legal authorities; - relevant clauses, facts, sections, pages, or records; - missing evidence; - conflicting evidence; - source reliability or currency concerns; - whether a conclusion is based on the document, external law, inference, professional judgment, or policy. If the evidence cannot be inspected, mark the decision as ownership-deficient. ### 4. Reasoning Access Check whether the actor can reconstruct the reasoning path at the level required for the decision. The output should show: - the legal or operational issue; - the rule, standard, mandate, or criterion applied; - the material facts used; - the inference from facts to conclusion; - alternatives considered; - why rejected alternatives were rejected; - the limits of the analysis. Do not treat a post-hoc explanation, summary, confidence score, or fluent conclusion as sufficient by itself. ### 5. Uncertainty Visibility Identify uncertainty that affects ownership: - contested legal interpretation; - missing facts; - stale or unverified legal authority; - ambiguous document language; - dependency on assumptions; - jurisdictional mismatch; - unresolved factual or evidentiary conflict; - model, retrieval, or tool limitations. Uncertainty must be visible enough to influence the decision before reliance occurs. ### 6. Authority and Competence Check whether the actor has authority and competence for the specific decision. Ask: - Does the actor have mandate, role, or delegation to make this decision? - Does the mandate cover this matter, jurisdiction, client, entity, or transaction? - Has the mandate expired, been limited, or been superseded? - Does the actor need specialist review? - Does the decision require client, board, court, regulator, partner, or supervisor approval? Formal responsibility is not enough if the actor lacks authority or practical competence. ### 7. Contestability and Correction Check whether the actor can challenge and correct the output before action. The workflow should allow: - requesting source support; - correcting facts; - changing assumptions; - escalating uncertain issues; - rejecting unsupported conclusions; - preserving an audit trail of material changes. If the workflow allows only accept/send/execute, ownership is weak.
From lawve-ai/awesome-legal-skills, AGPL-3.0.
More from lawve-ai/awesome-legal-skills
- 0.817score
uk-citation-verification-matei-clej
Matei Clej
Verifies UK case-law citations, pinpoint references and quotations against the official public register — The National Archives' Find Case Law — and statutory…
SkillAFreshness: A★ 895Claude Code +9 - 0.817score
extradition-case-law-search-matei-clej
Matei Clej
Searches the domestic courts of 122 jurisdictions — 153 databases, 49 automated — for extradition and arrest-warrant surrender decisions, each in its own…
SkillAFreshness: A★ 895Claude Code +9 - 0.813score
regulatory-threat-model
Ansvar Systems AB
Use when an application or system — including one built quickly with AI coding agents — needs a security review with regulatory grounding: a STRIDE threat…
SkillAFreshness: A★ 895Claude Code +9 - 0.813score
incident-reporting-navigator
Ansvar Systems AB
Use when a security incident, data breach, or actively exploited vulnerability raises the question "who must we notify, where, and by when?" Screens one…
SkillAFreshness: A★ 895Claude Code +9 - 0.813score
cra-vulnerability-obligations
Ansvar Systems AB
Use when a user asks what the EU Cyber Resilience Act (CRA) means for their product, whether and when they must report a vulnerability or incident, or what a…
SkillAFreshness: A★ 895Claude Code +9 - 0.813score
scotus-argument-analyzer
Seth J. Chandler
Analyze a U.S.
SkillAFreshness: A★ 895Claude Code +9 - 0.807score
jev-question-translator
Seth J. Chandler
Turns a legal question, a set of draft questions, or source material such as a statute, jury instruction, rubric, contract checklist, or coding manual into a…
SkillAFreshness: A★ 895Claude Code +9 - 0.807score
reader-first-technical-edit
Seth J. Chandler
Edit mathematically, empirically, or technically dense papers for readers outside the author’s specialty, including empirical legal scholarship…
SkillAFreshness: A★ 895Claude Code +9 - 0.777score
privacy-policy-stephane-boghossian
Stephane Boghossian
A zero-hallucination privacy-policy generator that takes anyone — non-lawyer founder to lawyer — from a guided intake to a publishable, jurisdiction-aware…
SkillBFreshness: B★ 895Claude Code +9 - 0.772score
client-instruction-schedule
Serhan Handani
Build a client instruction schedule — a plain-English, Scott Schedule-style Word table that gathers a struggling client's evidence and instructions issue by…
SkillBFreshness: B★ 895Claude Code +9 - 0.771score
cross-regulatory-impact-analyzer-patrick-munro
Patrick Munro
Analyzes how multiple regulations interact for a specific product, service, or business model.
SkillBFreshness: B★ 895Claude Code +9 - 0.771score
notification-licenciement-selim-brihi
Sélim Brihi
Guide pour la rédaction de notifications de licenciement conformes au droit du travail français.
SkillBFreshness: B★ 895Claude Code +9
Compare and alternatives
Featured in
Signals
- Stars
- 895
- Forks
- 119
- Open issues
- 7
- Last commit (this folder)
- Jul 30, 2026 (3 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- Version
- 2026-06-03
- License
- AGPL-3.0
- Repository
- github.com/lawve-ai/awesome-legal-skills
- Website
- lawve.ai
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from Ignacio Adrián Lerer
- 0.767score
legal-transition-audit-ignacio-adrian-lerer
Ignacio Adrián Lerer
Audits the transition from legal AI output to reliance, recommendation, execution, or real-world commitment.
SkillBFreshness: B★ 895Claude Code +9 - 0.763score
epistemic-fault-line-audit-ignacio-adrian-lerer
Ignacio Adrián Lerer
Audits legal AI outputs, prompts, skills, workflows and MCP/tool instructions for fluent but unsupported reasoning, missing evidence, overconfidence, hidden…
SkillBFreshness: B★ 895Claude Code +9 - 0.763score
legal-mdl-audit-ignacio-adrian-lerer
Ignacio Adrián Lerer
Audits legal AI outputs and workflows for honest compression: unnecessary complexity, false simplicity, excessive caveats, hidden uncertainty and poor cost…
SkillBFreshness: B★ 895Claude Code +9 - 0.761score
law-expertise-to-skill-ignacio-adrian-lerer
Ignacio Adrián Lerer
Turn a lawyer's bounded expertise, workflow, review standard, or legal judgment pattern into a safe, inspectable legal AI skill.
SkillBFreshness: B★ 895Claude Code +9 - 0.761score
lawve-public-due-diligence-gate-ignacio-adrian-lerer
Ignacio Adrián Lerer
Use for due diligence, legal-financial risk review, investment or business transaction checklists, and preliminary screening where facts, documents…
SkillBFreshness: B★ 895Claude Code +9 - 0.761score
lawve-agentic-delegation-audit-ignacio-adrian-lerer
Ignacio Adrián Lerer
Use when a lawyer, legal team, or client needs to assess AI agents that can act on someone's behalf: send messages, search, draft, file, pay, delete, connect…
SkillBFreshness: B★ 895Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get decision-ownership-audit-ignacio-adrian-lerer running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
decision-ownership-audit-ignacio-adrian-lerer skill. Agent Mart. https://agentmart.dev/skills/lawve-ai-decision-ownership-audit-ignacio-adrian-lerer (last updated 2026-10-24)