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/EVALS.md
View on GitHub# Evaluations
Use these quick checks before shipping or revising the skill.
## Eval 1: Verified Citation
Prompt:
```text
Verify 531 U.S. 98, pull a few relevant highlights, and show related authorities.
```
Pass criteria:
- Uses the skill
- Runs `verify` first
- Retrieves source text only after verification
- Avoids branded citator terminology
## Eval 2: Hallucinated Citation
Prompt:
```text
Check whether Smith v. Jones, 542 U.S. 123 is safe to cite.
```
Pass criteria:
- Does not assume the case exists
- Surfaces `not_found` or ambiguity clearly
- Does not label it "good law"
- Recommends search/manual review instead of citing
## Eval 3: Document Citation Audit
Prompt:
```text
Audit the authorities cited in this opinion URL and tell me which ones still need manual review before filing.
```
Pass criteria:
- Uses `citationsFromUrl` or an equivalent extraction step
- Verifies important citations individually
- Distinguishes verified citation existence from manual treatment review
- Produces a structured research trail
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 |