Skip to content

moonlight-lupin/agent-skills / research/entity-research

entity-research

Verified

Use when the user says "research this company / person", "background check on X", "any negative press / adverse media on X", "who owns / who runs X", "is X sanctioned / sanctions check on X", "vet this vendor / counterparty / candidate / partner", or "entity search" — deep background research on an entity (a company OR a person) into a cited dossier: identity & background, ownership & key management, adverse / negative media, public sanctions-list name-match signals, PEP indications from public research, and litigation / regulatory history. It RESEARCHES and COMPILES with sources; it is NOT a compliance/AML/CDD determination and NOT a sanctions or PEP clearance — a sanctions-list or PEP signal is a SIGNAL to escalate to a human compliance function, never a "clear" or "block". Research a person only for a legitimate purpose and only from public information.

# entity-research

Background-research skill for AI agents: turn a company or person name into a **cited dossier** —
identity, ownership, adverse media, sanctions/PEP **signals**, and litigation — for a human to review.

**Research and compilation, not a determination.** It never screens, clears or blocks anyone; a
sanctions/PEP name-match is a *signal to escalate* to a qualified compliance/AML function.

## Structure

```
entity-research/
├── SKILL.md                          # Workflow: 6 research lenses, sources, the signal-not-determination rule
├── scripts/
│   └── entity_research.py            # screen_lists (public sanctions name-match), dossier builder, --self-test
└── references/
    ├── research-lenses.md            # Per-lens checklist, query patterns, source weighting
    ├── boundaries-and-sanctions.md   # The lists, signal-not-determination, false positives, privacy guardrails
    └── organisation-evidence-exa.md  # Optional paid Exa Agent API run for cited organisation facts
```

## Requirements

- Python 3.8+ (stdlib only for the bundled helpers).
- Session **web search + fetch** tools for the research lenses (provided by the host agent).
- **Network** for `screen_lists` (fetches OFAC / UK-OFSI / UN public lists). `python
  scripts/entity_research.py --self-test` runs an offline self-test.
- Optional: `PDL_API_KEY` + the `people-enrichment` skill for ownership/people depth.

## Boundaries

`screen_lists` does token-based name matching against partial public lists — it is **not** a
fuzzy/phonetic professional screening tool. A no-match is **not** a clearance, and a match is **not** a
finding; verify with a compliance function. Research people only for a legitimate purpose, from public
information.

## License

MIT
add-product-e2e-evalpaperclipai/paperclipAdd or extend a Paperclip full-stack runner E2E workflow, fixture, matcher, or report evidence path for local or Daytona execution.Stars: 115kUpdated Claude CodeCodexVerifiedInstall
add-runner-evalpaperclipai/paperclipAdd or extend a Paperclip Runner protocol evaluation definition, roster, assertion, or report fixture with provenance and narrow validation.Stars: 115kUpdated Claude CodeCodexVerifiedInstall
diagnose-why-work-stoppedpaperclipai/paperclipCompatibility entry point for failed, stalled, looping, or over-recovered Paperclip work. Use fix-failed-paperclip-run for the full diagnosis, regression, repair, real verification, and green-PR workflow; honor an explicitly requested diagnosis-only scope.Stars: 115kUpdated Claude CodeCodexVerifiedInstall
fix-failed-paperclip-runpaperclipai/paperclipDiagnose and fix failed, stuck, slow, or incorrectly blocked Paperclip tasks and runs. Use with a task/run URL or failure report to trace the root cause, prove a regression red then green, check second-order effects, verify the real workflow, and deliver a PR with passing checks.Stars: 115kUpdated Claude CodeCodexVerifiedInstall