authority-verification
Verifies legal citations and retrieves source material using the case.dev Legal Research API and CLI. Use when validating a citation, confirming a case exists, pulling source text, finding related authorities, extracting citations from a brief or opinion, or building a filing-ready authority check without branded citator terminology.
Best use case
authority-verification is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Verifies legal citations and retrieves source material using the case.dev Legal Research API and CLI. Use when validating a citation, confirming a case exists, pulling source text, finding related authorities, extracting citations from a brief or opinion, or building a filing-ready authority check without branded citator terminology.
Teams using authority-verification should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/authority-verification/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How authority-verification Compares
| Feature / Agent | authority-verification | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Verifies legal citations and retrieves source material using the case.dev Legal Research API and CLI. Use when validating a citation, confirming a case exists, pulling source text, finding related authorities, extracting citations from a brief or opinion, or building a filing-ready authority check without branded citator terminology.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Authority Verification with case.dev Use case.dev legal research endpoints to verify citations, retrieve source text, and expand to related authorities. Keep the language generic: "verified citation," "candidate authority," "related authority," and "manual treatment review." ## Quick Start 1. Verify the citation text with `legal.verify()` before citing it. 2. If verification is unclear, search by topic with `legal.find()` or `legal.research()`. 3. Pull the full document text with `legal.fullText()` once you have a verified source URL. 4. Expand outward with `legal.similar()` to find related authorities. 5. Format the result using [references/OUTPUT-TEMPLATE.md](references/OUTPUT-TEMPLATE.md). Reference guide: [references/CASEDEV-WORKFLOW.md](references/CASEDEV-WORKFLOW.md) Runtime and setup: [references/RUNTIME.md](references/RUNTIME.md) Concrete scenarios: [references/EXAMPLES.md](references/EXAMPLES.md) Lightweight eval set: [references/EVALS.md](references/EVALS.md) Examples: - Python: [scripts/verify_authority.py](scripts/verify_authority.py) - TypeScript: [scripts/verify_authority.ts](scripts/verify_authority.ts) - CLI: [scripts/verify_authority.sh](scripts/verify_authority.sh) ## Core Workflow ### 1. Verify the citation Use `legal.verify()` with the citation text exactly as written. - `verified` means the citation matched a real source in the database. - `not_found` means likely typo, hallucination, or unsupported citation. - `multiple_matches` means manual review is required before citation. ### 2. Retrieve the source text If verification succeeds, use the returned case URL with `legal.fullText()` to inspect the opinion and optionally highlight the issue you care about. ### 3. Expand the authority set Use `legal.similar()` on the verified source URL to find related authorities. Use `legal.research()` when you need broader issue-based research with multiple phrasings of the same question. ### 4. Audit a document If you are checking a brief, opinion, or article URL, use `legal.citationsFromUrl()` to extract cited authorities, then verify important citations individually. ### 5. Record the result Always record: - the exact citation checked - verification status - authoritative URL - jurisdiction used for search - date checked - any manual review needed before filing ## Guardrails - Do not say a case was "Shepardized," "KeyCited," or given a proprietary signal. - Do not describe case.dev results as editorial treatment analysis unless you performed separate manual review. - Say "verified citation" instead of "good law." - Say "manual treatment review required" when the workflow does not establish precedential weight by itself. - Search results are candidates, not filing-ready authorities, until verified. - Re-run verification immediately before filing. ## Output Standard Format the final work product using [references/OUTPUT-TEMPLATE.md](references/OUTPUT-TEMPLATE.md). ## Dependencies Do not assume tools are installed. Check [references/RUNTIME.md](references/RUNTIME.md) before running any script. ## Pitfalls - Verifying only the case name and not the reporter citation. - Treating `legal.find()` results as verified authorities. - Assuming related cases from `legal.similar()` are citing references or direct history. - Skipping the full-text read after verification. - Hiding uncertainty when the result is `multiple_matches` or `not_found`.
Related Skills
discovery-verification-audit
Produces an attorney-grade audit memorandum assessing whether written discovery responses are legally binding and timely. Use this skill when the user mentions verification audit, discovery verification, proof of service review, signature authority, perjury clause compliance, deadline computation, mailbox rule extensions, service defects, waiver risk, or motion-to-compel deadline analysis. Also trigger when the user references FRCP 33(b)(3) verification, CCP 2015.5, 28 U.S.C. 1746, attorney vs. party verification, or asks for help checking whether discovery responses are properly executed. Even if the user just says "check these responses for defects" or "is this verification valid," use this skill.
decision-record-verification
Cross-references a judge's decision, court opinion, or final order against one or more hearing/trial/deposition transcripts to verify whether the record supports each finding. Produces strict dual-citation blocks with document names, page/line references, and verbatim quotes from both sources. Use when preparing appellate review, post-trial motions, record discrepancy audits, or transcript-based fact checks of judicial findings.
ca-discovery-verification
Drafts California Superior Court discovery verification pages under CCP §§ 2030.250 and 2031.250 with proper CCP § 2015.5 perjury declarations. Trigger when the user needs a verification page for interrogatory or inspection/RPD responses, mentions California discovery verification, party vs. attorney signing, information-and-belief clauses, or fixing unverified responses. CA Superior Court only — not federal.
bates-citation-verification
Citation format and verification protocol for legal documents that draw on Bates-stamped source records. Defines the bracket citation format, multi-source citation rules, quotation handling, the verification pass that runs before output, and the [UNVERIFIED] flag protocol. Use this skill any time another skill produces a legal work product that cites Bates-stamped pages, including medical chronologies, deposition summaries, demand letters, case briefs, and discovery responses. Also use any time the user asks how to format a citation or verify that a claim is supported by the source.
skill-name
Replace with a specific description of what this skill does and when to use it. Include keywords that help agents identify relevant tasks.
writing-surgical-consultation-notes
Creates structured surgical consultation responses with assessment and surgical candidacy determination. Use when responding to surgical consults, evaluating surgical candidates, or documenting surgical recommendations.
writing-operative-reports
Creates structured operative notes with findings, technique, specimens, and estimated blood loss. Use when dictating operative reports, documenting surgical procedures, or recording intraoperative findings.
writing-irb-submissions
Creates IRB submission packages with protocol summaries, consent forms, and risk-benefit analysis. Use when submitting to IRB, preparing ethics applications, or writing consent documents.
writing-grant-applications-research
Structures NIH/foundation grant applications with specific aims, significance, and innovation sections. Use when writing research grants, preparing NIH applications, or structuring grant proposals.
writing-admission-orders
Generates structured admission order sets with diagnosis-specific protocols and safety checks. Use when admitting patients, creating admission orders, or setting up inpatient care plans.
validating-new-laboratory-tests
Structures test validation with precision, accuracy, linearity, and reference range establishment. Use when validating new assays, documenting method comparisons, or establishing reference ranges.
validating-clinical-data-quality
Structures data quality assessment with completeness, accuracy, and consistency validation. Use when auditing clinical data, assessing data quality, or validating data integrity.