jep-jeanne-sulzer
Verification-first methodology for the Jurisdicción Especial para la Paz (JEP), Colombia's transitional justice court under the 2016 Acuerdo Final with FARC-EP. Citations are verified against jep.gov.co before use. Covers the 11 macrocasos (from Caso 01 secuestro through Caso 11 violencia sexual, including Caso 03 falsos positivos), the three sanction tiers (propias, alternativas, ordinarias), TOAR, and the SIVJRNR sister bodies (CEV, UBPD). Guards the key structural distinctions (Sala de Reconocimiento vs Tribunal para la Paz; comparecientes FARC-EP vs Fuerza Pública vs terceros civiles; Acto
npx skills add lawve-ai/awesome-legal-skills --skill special-jurisdiction-for-peace-jeanne-sulzer --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Governs every output touching the Jurisdicción Especial para la Paz (JEP), outlining how to verify citations against jep.gov.co and apply a restoration-focused, multi-tier framework (macrocasos, sanction types, TOAR, and SIVJRNR bodies) in line with JEP structure.
How it works
- Requires that for any case-specific document (auto, providencia, resolución, sentencia, lineamiento), you verify before citing, using web_fetch to jep.gov.co in the current conversation.
- Establishes a three-level verification ladder: Existence verified, Content verified, Paragraph verified, with explicit guidance to verify by section and page when paragraph numbers are not available.
- Defines a Standard workflow: identify macrocaso, organ, document type; plan citations; perform fallback verification (jep.gov.co → colombia.unmissions.org → Tier 2 sources) when fetch fails; then draft using the approved citation format and perform a self-audit.
- Specifies foundational texts and institutional architecture (Acuerdo Final, Acto Legislativo 01 of 2017, Ley Estatutaria 1957 of 2019, Ley 1922, Reglamento General) as reference points, while noting they may be cited directly.
- Emphasizes the restorative-justice model: sanciones propias, sanciones alternativas, sanciones ordinarias, and the TOAR framework, with conditionality and broad victim-participation concepts.
When to use it
- Use whenever producing or validating content related to JEP outputs (autos, sentencias, providencias, lineamientos) and when citations are required to support factual propositions about macrocasos, organ structures, or sanction regimes.
What it can touch
- References to JEP documents and macrocasos, the three sanction tiers, TOAR, and SIVJRNR bodies as described in the workflow. Requires access to jep.gov.co and the specified verification workflow as described in the tool’s steps.
Caveats
- Verifications depend on live access to jep.gov.co; HTTP 403, timeouts, or non-renderable PDFs are treated as potential failures that trigger the fallback ladder rather than a dead end. The workflow explicitly instructs to use the fallback path in such cases.
- The guidance notes that first sentences were issued in September 2025; ensure dates and macrocaso references align with published items and current conversation context.
# JEP — Jurisdicción Especial para la Paz (Colombia) This skill governs every output that touches the Jurisdicción Especial para la Paz (JEP) — the Special Jurisdiction for Peace, the judicial component of Colombia's transitional justice system established by the **24 November 2016 Final Peace Agreement** between the Government of Colombia and the FARC-EP. The discipline is simple and the reason for it is concrete: the JEP applies a distinctive restorative-justice model — it issued its **first sentences in September 2025** applying *sanciones propias* (restorative non-custodial sanctions) for the gravest crimes of an internal armed conflict that lasted more than fifty years. Its procedure mixes Colombian civil-law structure, international criminal law standards, and a uniquely restorative-justice approach. Citation discipline matters acutely. ## The discipline in one paragraph For any case-specific document — auto, providencia, resolución, sentencia, lineamiento — verify before citing. "Verify" means `web_fetch` (or equivalent retrieval) to **jep.gov.co** (the official JEP website) in the current conversation. Foundational texts in project knowledge (Acuerdo Final, Acto Legislativo
- The discipline in one paragraph
- Verification is gradient, not binary
- Standard workflow
- Foundational texts (cite from project knowledge when present)
- The institutional architecture (get this right)
- Source hierarchy
- Citation format
- Audit mode depends on document type
- Substantive doctrine — pointers
- Sensitive contexts
- What this skill is not
- Reference files
What does the jep-jeanne-sulzer skill do?
Verification-first methodology for the Jurisdicción Especial para la Paz (JEP), Colombia's transitional justice court under the 2016 Acuerdo Final with FARC-EP. Citations are verified against jep.gov.co before use. Covers the 11 macrocasos (from Caso 01 secuestro through Caso 11 violencia sexual, including Caso 03 falsos positivos), the three sanction tiers (propias, alternativas, ordinarias), TOAR, and the SIVJRNR sister bodies (CEV, UBPD). Guards the key structural distinctions (Sala de Reconocimiento vs Tribunal para la Paz; comparecientes FARC-EP vs Fuerza Pública vs terceros civiles; Acto
How do I install it?
Run `npx skills add lawve-ai/awesome-legal-skills --skill special-jurisdiction-for-peace-jeanne-sulzer --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From lawve-ai/awesome-legal-skills, a repository with 618 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.