CSlawyer1985/legal-skillhub / skills/authority-verification
authority-verification
VerifiedVerifies 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.
| File | Kind | Size |
|---|---|---|
| LICENSE.txt | markdown | 10.5 KB |
| SKILL.md | skill md | 3.8 KB |
| references/CASEDEV-WORKFLOW.md | markdown | 3.1 KB |
| references/EVALS.md | markdown | 1.0 KB |
| references/EXAMPLES.md | markdown | 1.7 KB |
| references/OUTPUT-TEMPLATE.md | markdown | 696 B |
| references/RUNTIME.md | markdown | 1.2 KB |
| scripts/verify_authority.py | script | 3.5 KB |
| scripts/verify_authority.sh | script | 1.3 KB |
| scripts/verify_authority.ts | script | 3.1 KB |
references/CASEDEV-WORKFLOW.md
View on GitHub# case.dev Authority Verification Workflow
This skill uses generic authority-verification terminology instead of vendor-branded citator language.
## Table of Contents
- [Scope](#scope)
- [Endpoint Map](#endpoint-map)
- [Recommended Sequence](#recommended-sequence)
- [Status Handling](#status-handling)
- [Terminology Rules](#terminology-rules)
- [Python SDK Notes](#python-sdk-notes)
## Scope
case.dev Legal Research supports:
- citation verification
- legal source search
- deep multi-query research
- similar-authority discovery
- citation extraction from text or URLs
- full document retrieval with highlights
It does not claim proprietary editorial treatment labels or branded citator signals.
## Endpoint Map
Docs:
- `POST /legal/v1/verify`
- `POST /legal/v1/find`
- `POST /legal/v1/research`
- `POST /legal/v1/similar`
- `POST /legal/v1/citations`
- `POST /legal/v1/citations-from-url`
- `POST /legal/v1/full-text`
Primary CLI equivalents:
```bash
casedev legal:v1 verify --text "531 U.S. 98"
casedev legal:v1 find --query "qualified immunity excessive force" --jurisdiction us-federal
casedev legal:v1 research \
--query "employment discrimination disparate impact" \
--additional-queries "Title VII disparate impact theory" \
--additional-queries "Griggs v Duke Power significance"
casedev legal:v1 similar --url "https://www.courtlistener.com/opinion/118365/bush-v-gore/"
casedev legal:v1 get-full-text --url "https://www.courtlistener.com/opinion/118365/bush-v-gore/"
```
## Recommended Sequence
1. Verify the exact citation with `legal.verify`.
2. If verified, use the returned URL with `legal.fullText`.
3. Expand to related authorities with `legal.similar`.
4. If the issue is broader than one citation, use `legal.research` with 2-4 additional phrasings.
5. If reviewing a document, extract its authorities first with `legal.citations` or `legal.citationsFromUrl`.
## Status Handling
`verified`
: Citation matches a real authority in the database.
`not_found`
: No matching authority found. Check typos, reporter, year, or hallucinated text.
`multiple_matches`
: More than one plausible match. Manual review is required before citing.
## Terminology Rules
Use:
- verified citation
- candidate authority
- related authority
- source document
- manual treatment review
Avoid:
- Shepardize
- Shepardizing
- Shepard's report
- Shepard's Signal
- KeyCite
- good law
## Python SDK Notes
Docs use:
```python
import casedev
client = casedev.Casedev(api_key=os.environ["CASEDEV_API_KEY"])
```
Common calls:
```python
client.legal.v1.verify(text="531 U.S. 98")
client.legal.v1.find(query="qualified immunity excessive force", jurisdiction="us-federal")
client.legal.v1.research(
query="employment discrimination disparate impact",
additional_queries=[
"Title VII disparate impact theory",
"Griggs v Duke Power significance",
],
jurisdiction="us-federal",
num_results=15,
)
client.legal.v1.similar(url="https://www.courtlistener.com/opinion/118365/bush-v-gore/")
client.legal.v1.get_full_text(url="https://www.courtlistener.com/opinion/118365/bush-v-gore/")
```
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| 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: 115k | Updated | Claude CodeCodex | Verified | Install |
| add-runner-evalpaperclipai/paperclipAdd or extend a Paperclip Runner protocol evaluation definition, roster, assertion, or report fixture with provenance and narrow validation. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| 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: 115k | Updated | Claude CodeCodex | Verified | Install |
| 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: 115k | Updated | Claude CodeCodex | Verified | Install |