buriedsignals/anomaly/courtlistener-opinion
Claude Code and agent skill by buriedsignals/anomaly
- community
Checking that the SKILL.md file is still in the repository.
Use this skill to search CourtListener case-law opinion clusters by text, cluster ID, or docket ID and inspect citations, status, snippets, and nested lead, concurrence, or dissent records. Apply it to legal-source discovery; do not treat relevance ranking or an indexed snippet as legal authority, and explicitly opt into unpublished or other non-default statuses.
Install
npx vskill@latest install buriedsignals/anomaly/courtlistener-opinionSKILL.md
Query CourtListener opinions
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/opinion:search-opinions— Search type=o by text or one exact indexed identifier and optionally include explicitly selected non-published statuses.
<!-- END GENERATED OPERATION STATUS -->
Search case law
Provide exactly one of q, cluster_id, or docket_id:
Published opinions are the provider default. To broaden status scope, name it:
Semantic GET search is available only with q and sends that query to CourtListener. It does not conceal a sensitive research term.
Evidence discipline
- Use relevance to find candidates, never to decide controlling authority.
- Open the linked opinion, identify the court and status, and verify the cited
passage in context before quoting or relying on it.
- Preserve cluster, docket, and nested opinion IDs; a cluster can contain
multiple opinion documents with different roles.
- State whether non-published statuses were included.
- A no-result query is a coverage statement, not a conclusion about the law.
Read the API reference for current type o semantics, status flags, snippets, semantic search, and limits. Read the query guide for a defensible research loop.
Bundled resources
references/api-reference.md— primary API evidence and contract details.references/query-guide.md— search, status, source-reading, and reporting practice.scripts/verify.pyandassets/verification-cases.json— live keyword and ID checks.evals/evals.json— authority, status, snippet, and no-result cases.
Security
- Security scanPassed, 95 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/us/courtlistener-opinion/SKILL.md
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
[](https://verified-skill.com/skills/buriedsignals/anomaly/courtlistener-opinion)