본문으로 건너뛰기
cccskills
무료GitHub에 공개

icc-jeanne-sulzer

Research, drafting, and analysis involving the International Criminal Court (Rome Statute system). Enforces a verification-first methodology — every case-law, decision, filing, warrant, and statement citation is verified against an authoritative primary source (icc-cpi.int, legal-tools.org) in the current conversation before it appears in an output. Foundational texts (Rome Statute, Elements of Crimes, RPE, Regulations of the Court) may be cited from project knowledge when present. Use whenever the user is working with ICC case law, OTP statements, ASP documents, or ICC procedure.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

실행 점수 미검증

설치 방법 보기

포함된 파일(9)

  • SKILL.md6.4 KB
  • CHANGELOG.md2.4 KB
  • examples/example-audit.md9.1 KB
  • examples/example-verification.md6.6 KB
  • README.md589 B
  • references/authoritative-sources.md5.1 KB
  • references/citation-format.md8.9 KB
  • references/foundational-texts.md2.9 KB
  • references/verification-workflow.md7.7 KB

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

ICC skill

Core discipline

For any case-specific document — judgment, decision, warrant, filing, OTP statement — verify before citing. Verification means retrieving the document from a Tier 1 source (icc-cpi.int, legal-tools.org, asp.icc-cpi.int) in the current conversation. The four foundational texts (Rome Statute, Elements of Crimes, Rules of Procedure and Evidence, Regulations of the Court) are the only exception, and only when they are present in project knowledge.

Nothing else may be cited from memory. Inventing a document number, a date, or a paragraph reference is the single failure mode this skill exists to prevent.

When to use this skill

  • The user asks a question that requires citing ICC case law, decisions, warrants, OTP statements, ASP resolutions, or ICC procedural texts.
  • The user supplies an ICC filing or judgment for analysis or audit.
  • The user is drafting something — a memo, a brief section, a research note — that will reference ICC instruments or case law.
  • The user asks about Rome Statute interpretation, command responsibility, modes of liability, war crimes / crimes against humanity / genocide / aggression elements, victim participation, reparations, or other Statute-grounded questions.

If the question is about another tribunal (ICTY, ICTR, MICT, SCSL, STL, ECCC, KSC, or hybrid mechanisms), this skill does not apply — use the relevant tribunal's skill or, if none exists, surface that to the user.

Workflow

The full procedure is in references/verification-workflow.md. The short form:

  1. Identify the document. Read what is actually in front of you; if the user names a case or document, disambiguate against the document's own header before proceeding. (Bemba TJ vs. Bemba AJ; Ntaganda 2017 interlocutory vs. 2021 final appeal — identity errors propagate.)
  2. List every citation that will appear in the planned output, with the proposition each supports.
  3. Verify each citation. Work the fallback ladder: icc-cpi.int → legal-tools.org → search-result snippet from a Tier 1 domain → ICC press release → authoritative secondary database (e.g. OUP ORIL) → ask the user. Stop at the first level that satisfies what the claim needs.
  4. Match verification level to claim. Three levels: Existence (document, number, date, chamber), Content (the document holds, in substance, what the output says it holds), Paragraph (the cited paragraph contains the cited proposition). Pinpoint quotations require paragraph-level verification. If verification stops short, soften the claim or flag it explicitly.
  5. Draft using verified material. Use the citation formats in references/citation-format.md.
  6. Self-audit. Walk every citation in the draft: from project knowledge or from this conversation's retrieval? Does the proposition match? Is the verification level appropriate to the claim?

Reference materials

Read these as needed; they are the operational detail behind the workflow above.

  • references/authoritative-sources.md — Tier 1 / Tier 2 / do-not-cite source hierarchy; the icc-cpi.int 403 fallback ladder.
  • references/citation-format.md — exact formats for the Rome Statute, Elements of Crimes, RPE, Regulations, decisions, warrants, OTP statements, ASP documents. Includes the Article 28 numbering discipline — the Rome Statute uses 28(a) (military commanders) and 28(b) (other superiors), with no numbered paragraphs; the non-statutory 28(1)/(2) form is the trap to avoid.
  • references/verification-workflow.md — the full operational procedure, the three-level verification gradient, a worked Bemba example.
  • references/foundational-texts.md — the four foundational texts and what is not foundational (case law, OTP policy papers, most ASP resolutions, Regulations of the Registry/OTP, professional codes).

Worked examples

  • examples/example-verification.md — two end-to-end examples: full paragraph-level verification (Bemba effective control) and partial verification when icc-cpi.int blocks (Ntaganda 2017 jurisdiction).
  • examples/example-audit.md — two audit modes: working draft (the user wrote it; citations are claims to be checked) vs. finalised Court record (the Court issued it; citations are part of the record, and the audit is about how downstream work uses them).

What this skill is not

  • Not legal advice. Outputs are research and drafting aids for users who understand international criminal law.
  • Not a substitute for primary documents. A skill that follows this workflow can produce accurate citations and disciplined drafts; only the user can decide what to do with them.
  • Not endorsed by the Court. Independent open-source project.

Hard rules

These are non-negotiable. Edits or workarounds that weaken them defeat the skill.

  1. No case-specific citation from memory. Verify in-conversation.
  2. Public-redacted (-Red) versions only in public outputs. Confidential filings (-Conf, -Conf-Exp) are not citable from a public output, ever — even when the user has lawful access to the confidential version, cite the -Red counterpart.
  3. The Statute's own numbering governs. For Article 28, that means Article 28(a) (military commanders) and Article 28(b) (other superiors) — not the non-statutory 28(1)/(2) form — in anything that will be filed, read by judges or counsel, or quote the Statute.
  4. Secondary sources (HRW, Amnesty, UN bodies, academic commentary, news) are clearly separable in the output and never used to establish what the Court has said or held.
  5. icc-cpi.int 403s are structural, not failures. Work the fallback ladder; do not abandon a real citation because the direct fetch was blocked.

리뷰

아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.

댓글

로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.

아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.

보내면 바로 공개됩니다. 이메일 주소나 전화번호 같은 개인 정보는 쓰지 마세요. URL은 2개까지입니다.

0 / 1,000자

이 양식은 reCAPTCHA로 보호되며 Google 개인정보처리방침 및 서비스 약관이 적용됩니다.

같은 저장소의 스킬

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.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

lawve-ai/awesome-legal-skills8952026년 10월 20일 업데이트

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.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

lawve-ai/awesome-legal-skills8952026년 10월 20일 업데이트

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.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

lawve-ai/awesome-legal-skills8952026년 10월 20일 업데이트

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.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

lawve-ai/awesome-legal-skills8952026년 10월 20일 업데이트

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.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

lawve-ai/awesome-legal-skills8952026년 10월 20일 업데이트

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.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

lawve-ai/awesome-legal-skills8952026년 10월 20일 업데이트

lawve-ai의 스킬 모두 보기

이 스킬의 문제 신고