From cocounsel-legal
Use this skill when a user wants to verify, validate, or check the status of legal citations — either from a Deep Research report or from any document containing case law, statute, or regulatory citations. Checks whether cited authority is still good law, identifies negative treatment, and flags citations that could not be resolved.
How this skill is triggered — by the user, by Claude, or both
Slash command
/cocounsel-legal:citation-verificationThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Validates legal citations by checking each against Westlaw's database for
Validates legal citations by checking each against Westlaw's database for current status, negative treatment, and resolution accuracy. Works on citations from a completed Deep Research report or from user-supplied text.
The cocounsel-legal MCP server must be connected. Verify it is available
before starting verification. If the server is not connected, inform the
user and stop.
cocounsel-legal:deep-researchEvery citation status reported by this skill must come from a Westlaw query via the CoCounsel Legal MCP server. Never report a citation's treatment status from model knowledge — model knowledge cannot reflect real-time KeyCite or Shepard's status.
Source attribution. Tag every verification result:
[Westlaw verified] — status confirmed via MCP query[unresolved — verify manually] — query returned no result or an
ambiguous match; do not guess the statusWhen a citation cannot be resolved. If the MCP server returns no match or an ambiguous result:
unresolved — do NOT infer statusanswer_text.Group extracted citations by type:
| Type | Examples |
|---|---|
| Case law | Smith v. Jones, 123 F.3d 456 (9th Cir. 2020) |
| Statute | 42 U.S.C. § 1983; Cal. Civ. Code § 1542 |
| Regulation | 17 C.F.R. § 240.10b-5 |
| Administrative | SEC No-Action Letter, FTC Advisory Opinion |
| Secondary | Restatement (Third) of Torts § 46 |
For each citation, call the MCP server to check:
Use legal_research_start_deep_research with a targeted verification
query for each batch of citations (group by jurisdiction to stay within
the 3-jurisdiction limit).
Output a verification table:
## Citation Verification Report
| # | Citation | Type | Status | Treatment | Notes |
|---|---|---|---|---|---|
| 1 | *Smith v. Jones*, 123 F.3d 456 (9th Cir. 2020) | Case law | ✅ Good law | Followed | — |
| 2 | *Doe v. Roe*, 456 F.2d 789 (5th Cir. 1998) | Case law | ⚠️ Caution | Distinguished by 3 courts | Review before citing |
| 3 | *State v. Black*, 789 P.2d 012 (Cal. 2015) | Case law | ❌ Overruled | Overruled by *White v. Green* (2022) | Do not cite as authority |
| 4 | Cal. Bus. & Prof. Code § 17200 | Statute | ✅ Current | — | Amended 2023 — verify current text |
Status markers:
After the table, provide:
cocounsel-legal:deep-research)npx claudepluginhub chgreer1070/claude-for-legal --plugin cocounsel-legalGuides completion of development work by verifying tests, detecting environment, and presenting structured options for merge, PR, or cleanup.
Guides creation and editing of skills using test-driven development with pressure scenarios and subagents to verify agent compliance.
Dispatches multiple subagents concurrently for independent tasks without shared state. Use when facing 2+ unrelated failures or subsystems that can be investigated in parallel.