ai-inventory
EU AI Act per-system inventory — track each AI system's role (provider, deployer, importer,…
Triage a subpoena served on the company — classify it, analyze scope/burden/privilege, cross-check the portfolio, and produce an objections framework, compliance plan, and deadline calendar. Use when the user says "we got a subpoena", "served with a subpoena", or shares a
$ npx -y skills add anthropics/claude-for-legal --skill subpoena-triage --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/subpoena-triageContext preview
The summary Claude sees to decide when to auto-load this skill.
Triage a subpoena served on the company — classify it, analyze scope/burden/privilege, cross-check the portfolio, and produce an objections framework, compliance plan, and deadline calendar. Use when the user says "we got a subpoena", "served with a subpoena", or shares a
name: subpoena-triage description: Triage a subpoena served on the company — classify it, analyze scope/burden/privilege, cross-check the portfolio, and produce an objections framework, compliance plan, and deadline calendar. Use when the user says "we got a subpoena", "served with a subpoena", or shares a subpoena, CID, or third-party document request to evaluate. argument-hint: "[path-to-subpoena] [--slug=custom-slug]"
1. Read the subpoena from provided path. 2. Classify (third-party-docs / third-party-depo / party / CID / grand-jury). 3. If grand jury → stop, escalate per `~/.claude/plugins/config/claude-for-legal/litigation-legal/CLAUDE.md`. Otherwise continue. 4. Load `~/.claude/plugins/config/claude-for-legal/litigation-legal/matters/_log.yaml` for cross-check. Load `~/.claude/plugins/config/claude-for-legal/litigation-legal/CLAUDE.md` → landscape, privilege conventions, escalation norms. 5. Follow the workflow and reference below. 6. Extract key fields, analyze scope/burden/privilege, produce objections framework + compliance plan + deadline calendar. 7. Write `~/.claude/plugins/config/claude-for-legal/litigation-legal/inbound/[slug]/triage.md`. Copy or link subpoena to `~/.claude/plugins/config/claude-for-legal/litigation-legal/inbound/[slug]/incoming.[ext]`. 8. Hand off: `/legal-hold --issue` if hold not in place; `/matter-intake` if materiality warrants; `/matter-briefing [slug]` if party subpoena in existing matter.
---
Subpoenas arrive with deadlines. The failure modes: missing the deadline, over-producing (privilege waiver, burden we should have objected to), under-producing (contempt exposure), or missing a motion-to-quash window. This skill classifies, analyzes, and produces a compliance plan with objections framework.
The rule cited in Step 0 is the operative one for this subpoena in this forum. Subpoena practice varies materially: federal (FRCP 45) vs. state equivalents, state-to-state variants, local rules, court-specific standing orders, and the subpoena type (trial, deposition, document production) all change objection deadlines, place-of-compliance limits, privilege-log requirements, and cost-shifting. Every rule output here is a starting-point heuristic — confirm currency and the local variant before asserting in writing.
This skill is inherently defensive — a subpoena has been served on the recipient and the posture is respond/object/comply. Read `## Side` in the practice profile. If the user's default side is **plaintiff**, note that receiving a subpoena is common for plaintiffs too (witness subpoenas, third-party requests directed at the plaintiff's own records) but the framing here is always "subpoena served on us, how do we respond." If the user is **defense** (typical), the framing aligns with the default. If the matter has a different posture than the default (e.g., defense practitioner receiving a subpoena in a matter where they're pro se for a family member), prompt the user to confirm posture before proceeding.
**Before analyzing this subpoena, research the applicable rule of civil procedure for the forum (FRCP 45 for federal, the state equivalent otherwise) and the subpoena type (trial, deposition, document production). Identify: place-of-compliance limits, objection deadlines (these often run from the EARLIER of the compliance date or a fixed number of days after service), privilege-log requirements, and who bears costs. Cite with pinpoint references. Verify currency — rules and local variants change. Flag grand-jury subpoenas for immediate criminal-counsel escalation.**
**No silent supplement.** If a research query to the configured legal research tool (Westlaw, CourtListener, Trellis, Descrybe, or firm platform) returns few or no results for the forum's rule, variant, or pinpoint, report what was found and stop. Do NOT fill the gap from web search or model knowledge without asking. Say: "The search returned [N] results from [tool]. Coverage appears thin for [rule / forum / variant]. Options: (1) broaden the search query, (2) try a different research tool, (3) search the web — results will be tagged `[web search — verify]` and should be checked against a primary source before relying, or (4) stop here. Which would you like?" A lawyer decides whether to accept lower-confidence sources; the skill does not decide for them.
**Source attribution.** Tag every rule reference, case, statute, and regulation in the triage output with where it came from: `[Westlaw]`, `[CourtListener]`, `[Trellis]`, `[Descrybe]`, or the MCP tool name for citations retrieved from a legal research connector; `[web search — verify]` for citations from web search; `[model knowledge — verify]` for citations recalled from training data; `[user provided]` for citations the user supplied (e.g., from the subpoena or prior matter work). Citations tagged `verify` carry higher fabrication risk and should be checked first. Never strip or collapse the tags — they are counsel's fastest signal about which citations to verify before asserting in objections or filings.
Subpoenas come in flavors with different rules; confirm the specifics against the rule you just researched:
Reference agents, skills, and data connectors for the legal workflows we see most — in-house commercial, privacy, product, corporate, employment, litigation, regulatory, AI governance, IP, and the learning side of the practice (law school clinics and
EU AI Act per-system inventory — track each AI system's role (provider, deployer, importer,…
Run an AI impact assessment — structured intake, risk analysis, regulatory classification per…
Run the cold-start interview — learns your AI governance practice and writes…
Guided customization of your AI governance practice profile — change one thing without…
Manage matter workspaces — new, list, switch, close, or detach (practice-level).…
Keep the AI policy current with practice — weekly sweep of saved AIAs, triage results, and…