sanctions-screening-legal-analysis-skill-english-gillan-saleh
Sanctions and export control analysis tool for Claude Desktop. Real-time individual screening across 30+ official lists (UN, EU, OFAC, OFSI, French DGT...), sectoral analysis, dual-use goods (EU Reg. 2021/821), US/China extraterritorial regimes (EAR, ITAR, FDPR, ECL), USD/SWIFT risk and jurisdictional mapping across 30+ countries. All results sourced and verified in real time — no memory-based answers. Responds in French, English, German, Spanish, Russian and Chinese. Updated 19 May 2026 (EU 20th package, UK SEUC, Cuba EO). Indicative guidance only — not legal advice.
npx skills add lawve-ai/awesome-legal-skills --skill sanctions-and-export-analysis-gillan-saleh --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
Real-time sanctions and export controls analysis for Claude Desktop, including individual screening, sectoral sanctions, dual-use goods, payment-system risk, and extraterritorial regimes across 30+ jurisdictions. It aims to verify results against official sources with live updates and supports multiple languages.
How it works
The skill mandates real-time sourcing for designation-related statements, requiring that any list-based conclusion be preceded by a live search of official sources. It prescribes universal A1 screening (UN, EU, and OpenSanctions baseline with fallback to official sources), then A2 geographic-based checks depending on nationality, and A3 formatting of results with explicit blocks showing match status, checked lists, and references. It also includes a structured module B for sectoral sanctions and payments, detailing regime-specific measures (e.g., Russia/Ukraine packages, Iran, DPRK) and a timeline of regulatory updates. The output must cite sources with explicit references, dates, and disclaimers, and must flag inconclusive or ambiguous results before any conclusion. It requires collecting identifiers (name, nationality, DOB, aliases) before launching screening.
When to use it
Use when evaluating individuals, entities, or transactions against sanctions and export-control regimes, particularly when multiple jurisdictions or extraterritorial regimes are involved. Activate modules A (Individual screening) and B (Sectoral sanctions) based on the data provided (name/nationality for A, sector/country for B).
What it can touch
The skill specifies interacting with lists and sources in real time; it requires the Claude Code tool. It references actions such as running searches on UN Security Council lists, EU consolidated lists, and OpenSanctions as part of the baseline checks. It mandates including source citations in every result.
Caveats
The skill enforces an absolute rule against relying on memory for sanctions designations and requires explicit real-time verification from official sources for any designation statements. It demands structured alerts for inconclusive results and prohibits extrapolating law without verified sources. It emphasizes that results are indicative and require verification against official sources before decision-making. The license is agpl-3.0, and the author is listed as Gillan Saleh.
# Sanctions Screening & Legal Analysis Skill > **Last updated: 19 May 2026** — EU 20th package · UK SEUC · Cuba EO 14404 · GL 131E Lukoil ## Scope This skill covers exclusively the field of **international economic sanctions and export controls**, in all their dimensions: - Individual designations (asset freeze, travel ban) - Sectoral sanctions (energy, finance, technology, transport...) - Dual-use goods and technologies - Payment systems (SWIFT, USD, EUR) as sanctions vectors - Extraterritorial regimes (EAR/ITAR/FDPR US, China ECL, EU no re-export clause) - Financial institutions' obligations under sanctions --- --- ## ABSOLUTE RULE — Prohibition of hallucinations and invented data **These rules apply without exception to every response produced by this skill. They take precedence over all other instructions.** ### 1. Absolute prohibition on answering from memory regarding designation lists Sanctions lists (OFAC SDN, EU FSF, UN list, French DGT, UK FCDO, etc.) are updated daily. A response based on the model's memory is by definition potentially incorrect and legally dangerous. **Rule**: any statement about the presence or absence of a person or entity on a sanctions list **must b
- Scope
- ABSOLUTE RULE — Prohibition of hallucinations and invented data
- 1. Absolute prohibition on answering from memory regarding designation lists
- 2. Mandatory source citation
- 3. Mandatory alerts — inconclusive results
- 4. Prohibition on extrapolating the state of the law without a verified source
- 5. Mandatory citation format in results
- 6. Prohibition on compensating uncertainty with a reassuring statement
- Step 0 — Language and user profile
- Supported languages — mandatory multilingual rule
- User profile
- Step 1 — Request analysis
- MODULE A — Individual screening
- A1 — Universal baseline (always run)
What does the sanctions-screening-legal-analysis-skill-english-gillan-saleh skill do?
Sanctions and export control analysis tool for Claude Desktop. Real-time individual screening across 30+ official lists (UN, EU, OFAC, OFSI, French DGT...), sectoral analysis, dual-use goods (EU Reg. 2021/821), US/China extraterritorial regimes (EAR, ITAR, FDPR, ECL), USD/SWIFT risk and jurisdictional mapping across 30+ countries. All results sourced and verified in real time — no memory-based answers. Responds in French, English, German, Spanish, Russian and Chinese. Updated 19 May 2026 (EU 20th package, UK SEUC, Cuba EO). Indicative guidance only — not legal advice.
How do I install it?
Run `npx skills add lawve-ai/awesome-legal-skills --skill sanctions-and-export-analysis-gillan-saleh --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.