CF 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.
Sanctions and export control analysis tool for Claude Desktop.
As a process F 32/100 · No process to follow — References files that are not bundled: references/regimes.md, references/qualification-juridique.md, references/sources-officielles.md
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- The text references files that are not there: add them or drop the references.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 1
✓ No critical or high findings
Medium and low: 1
-
low Risky intent
intent-offensive-securitySKILL.md:219Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- **Managed security services** (cybersecurity risk management, penetration testing, security audits) prohibited to Russian government and Russia-established entities (effective 25 May 2026)
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 10392 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: references/regimes.md - warning
missing-refreference to a missing file: references/qualification-juridique.md - warning
missing-refreference to a missing file: references/sources-officielles.md
Process rating: all ten parameters 32/100
- 0Tools and files. 3 referenced file(s) missing: references/regimes.md, references/qualification-juridique.md, references/sources-officielles.md
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 6 mutating operations with no state check
- 40Consistency. Frontmatter name (sanctions-screening-legal-analysis-skill-english-gillan-saleh) differs from the folder (sanctions-and-export-analysis-gillan-saleh)
- 40Execution cost. Instruction body is 10392 tokens: crowds the task out of the window
- 85Steps. 155 steps, 3 vague phrases
- 100Failures and branches. 1 branches, has a failure section
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 14 top-level sections: this looks like several domains in one skill
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- -215 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +3Description length 574: enough signal without eating the budget
- +4Structure: 46 headings
- +3Step-by-step instructions: 155 items
- +4Has examples (6 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 60.