buriedsignals/anomaly/opensanctions
Claude Code and agent skill by buriedsignals/anomaly
- community
Checking that the SKILL.md file is still in the repository.
Use this skill to screen a described person, company, vessel, or other FollowTheMoney entity through OpenSanctions query-by-example matching, conduct investigative full-text discovery, or retrieve one exact entity with nested relationships and source-lineage identifiers. Apply it to sanctions, PEP, debarment, and watchlist research; do not equate search relevance or match scores with identity, target status, or grounds for an adverse decision.
Install
npx vskill@latest install buriedsignals/anomaly/opensanctionsSKILL.md
Query OpenSanctions
meta.yaml is the executable contract. Use only released operations.
<!-- BEGIN GENERATED OPERATION STATUS -->
Current catalogue release status
meta.yaml is authoritative. Execute only operations listed as Released below; other sections in this playbook may document provider or unreleased adapter scope.
Released
global/opensanctions:match-entity— Rank candidates for a structured query-by-example using explicit dataset, topic, algorithm, and threshold controls.global/opensanctions:search-entities— Search the OpenSanctions sanctions, PEP, and watchlist entity index with bounded pagination, facets, filters, and explicit search syntax controls.global/opensanctions:get-entity— Retrieve one exact entity ID, optionally including nested adjacent entities and canonical referents.
<!-- END GENERATED OPERATION STATUS -->
Choose the correct operation
- Use
match-entityto screen a known subject with structured attributes. - Use
search-entitiesfor investigator-facing discovery and facets. Its
ranking is search relevance, not match quality.
- Use
get-entityonly after obtaining an exact provider ID.
Inspect the contract before sending identity data upstream:
Screening example
Use all reliable attributes, an explicit scope, and a reviewed threshold:
Review every candidate, score, match flag, topics, datasets, identifiers, and source evidence. A score above threshold is not a final identity decision.
Discovery and exact retrieval
Read the API reference for current filters, matching algorithms, search/privacy semantics, canonical-ID redirects, and licensing. Read the query guide for screening review, false-positive handling, and evidence reporting.
Identity and risk discipline
- Search rankings and match scores solve different tasks; neither proves
identity.
- Dataset membership does not necessarily mean the entity is itself targeted.
Inspect topics, target, nested sanctions, and the original designation.
- PEP, relative/associate, debarment, and sanctions classifications have
different meanings. Report the precise topic and source.
- A no-match result is not proof that a subject is clear. Coverage, spelling,
scope, attributes, source freshness, and threshold all matter.
- Never automate an adverse decision from this output. Use human review and
independent primary-source verification.
Privacy, authentication, and reuse
Provide the key through the execution context. Match sends structured identity attributes in a POST body; search uses a GET query string that the provider warns can enter access logs. Do not send confidential lead names without considering that disclosure.
OpenSanctions documents free keys for qualifying public-interest work and a CC BY-NC data licence for non-commercial use; commercial use requires the applicable licence. This skill conservatively does not pre-authorize caching or redistribution.
Bundled resources
references/api-reference.md— Firecrawl-preserved official OpenAPI and
documentation for matching, search, entities, authentication, and licence.
references/query-guide.md— structured screening, discovery, candidate
review, canonical IDs, and reporting.
scripts/verify.pywithassets/verification-cases.json— credential-aware
match, search, and exact-entity checks.
evals/evals.json— search/match, target, no-match, privacy, and human-review
behavior cases.
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingdata-skills/global/opensanctions/SKILL.md
Popularity
- 7-day trend score
- 0
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/buriedsignals/anomaly/opensanctions)