buriedsignals/anomaly/courtlistener-financial-disclosures

Claude Code and agent skill by buriedsignals/anomaly

Trust tier 2
  • community
LLM review pending
Source check pending

Checking that the SKILL.md file is still in the repository.

Use this skill to retrieve CourtListener financial-disclosure reports for one known federal judicial person ID and inspect extracted investments, gifts, debts, agreements, positions, reimbursements, income, redactions, and source PDFs. Apply it to conflict-of-interest research; preserve value ranges and inferred flags, and verify every material finding in the original filing.

Install

npx vskill@latest install buriedsignals/anomaly/courtlistener-financial-disclosures

SKILL.md

Query judicial financial disclosures

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

  • us/courtlistener/financial-disclosures:list-financial-disclosures — Return bounded disclosure reports and selected nested extracted rows for an exact CourtListener person ID.
  • us/courtlistener/financial-disclosures:judge-interests — Flatten one person's reports into one row per investment, gift, reimbursement, position, agreement, income, spouse income or debt line.

<!-- END GENERATED OPERATION STATUS -->

Court domain rows

judge-interests flattens the same reports into the court domain contract's judge_interests table (domains/court.yaml). Nested field names follow CourtListener's cl/disclosures/models.py. The endpoint returned HTTP 401 without a token on 2026-10-27.

Disclosure fieldjudge_interests column
person id at the end of personjudge_id (joins court_cases.assigned_judge_id)
yearreport_year
filepathurl
investments[]: description; gross_value_code J..P4interest_type investment, counterparty; value_low/value_high from the code's band (P4 has no upper bound; -1 and unknown codes stay empty)
gifts[]: source, description, value ("$1,199.00")gift, counterparty, description, value_low = value_high
reimbursements[]: source; date_raw, location, purpose, items_paid_or_providedreimbursement, counterparty; description (joined with "; ")
positions[]: organization_name, positionposition, counterparty, description
agreements[]: parties_and_terms, date_rawagreement, counterparty, description
non_investment_incomes[]: source_type, income_amountincome, counterparty, value bounds when the amount parses
spouse_incomes[]: source_typespouse_income, counterparty
debts[]: creditor_name, description, value_codedebt, counterparty, description, value bounds
row redactedextra column redacted (not in the contract; check the PDF)

judge_name is left empty: the report links the person only by id. Lines without a counterparty are dropped.

Retrieve one person's reports

Resolve the subject to a CourtListener person ID first, then query:

bash
catalogue query us/courtlistener/financial-disclosures \
  --operation list-financial-disclosures \
  --input '{"person_id":2738,"limit":10}'

The provider endpoint does not accept a year filter. Filter the returned bounded reports locally only after preserving that limitation; do not send an invented provider parameter.

Extraction discipline

  • Open pdf_url before publishing a finding. Extraction can be incomplete.
  • Keep gross_value_code, transaction_value_code, and their ranges. Never

turn a band into an exact amount.

  • Treat has_inferred_values=true as an extraction inference, not a filing fact.
  • Inspect every redacted marker and avoid reconstructing protected details.
  • Separate a reported interest from evidence that it affected a case.
  • Absence from CourtListener coverage is not proof of no report or no conflict.

Read the API reference for endpoint scope, nested fields, redactions, inferred values, and provider limits. Read the query guide for conflict research and reporting.

Bundled resources

  • references/api-reference.md — Firecrawl-preserved official documentation and OPTIONS evidence.
  • references/query-guide.md — identity resolution, extraction review, and corroboration.
  • scripts/verify.py and assets/verification-cases.json — live disclosure check.
  • evals/evals.json — range, inference, redaction, and absence cases.
bash
python3 scripts/verify.py --list
python3 scripts/verify.py

Security

  • Security scanPassed, 100 of 100Pattern checks on the skill's files.
  • Model reviewNot runA model review is scheduled for the next rescan.

See the full security report

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

See evaluation results

Source

Popularity

7-day trend score
5

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
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/buriedsignals/anomaly/courtlistener-financial-disclosures/badge)](https://verified-skill.com/skills/buriedsignals/anomaly/courtlistener-financial-disclosures)

Something wrong with this skill or its page? Tell us.