ai-inventory
EU AI Act per-system inventory — track each AI system's role (provider, deployer, importer,…
Route a contract issue to the right approver per the escalation matrix in `~/.claude/plugins/config/claude-for-legal/commercial-legal/CLAUDE.md`, and draft the ask. Use when the user says "who needs to approve this", "escalate this", "does this need GC sign-off", "route this for
$ npx -y skills add anthropics/claude-for-legal --skill escalation-flagger --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/escalation-flaggerContext preview
The summary Claude sees to decide when to auto-load this skill.
Route a contract issue to the right approver per the escalation matrix in `~/.claude/plugins/config/claude-for-legal/commercial-legal/CLAUDE.md`, and draft the ask. Use when the user says "who needs to approve this", "escalate this", "does this need GC sign-off", "route this for
name: escalation-flagger description: > Route a contract issue to the right approver per the escalation matrix in `~/.claude/plugins/config/claude-for-legal/commercial-legal/CLAUDE.md`, and draft the ask. Use when the user says "who needs to approve this", "escalate this", "does this need GC sign-off", "route this for approval", or when another skill finds an issue that exceeds the reviewer's authority. argument-hint: "[describe the issue, or reference a review memo]"
Names the approver for a contract issue per the `~/.claude/plugins/config/claude-for-legal/commercial-legal/CLAUDE.md` escalation matrix and drafts the message so you're not writing "hey got a sec" at 5pm.
1. **Load `~/.claude/plugins/config/claude-for-legal/commercial-legal/CLAUDE.md`** → Escalation section. If missing, say so — the practice profile needs editing.
2. **Characterize the issue:** dollar threshold / term deviation / automatic trigger / business decision.
3. **Match to matrix, name the approver.** Be specific — a person or role, not "legal leadership."
4. **Draft the ask** per the template below: what the contract says, what playbook says, options with recommendation, decision-by date.
5. **Do not send.** Draft it, show it, let the lawyer send.
/commercial-legal:escalation-flagger The Acme MSA has uncapped liability — who approves and what do I say?
/commercial-legal:escalation-flagger Reference: acme-review-memo.md Issue: §8.2 indemnity carveouts
---
**Matter context.** Check `## Matter workspaces` in the practice-level CLAUDE.md. If `Enabled` is `✗` (the default for in-house users), skip the rest of this paragraph — skills use practice-level context and the matter machinery is invisible. If enabled and there is no active matter, ask: "Which matter is this for? Run `/commercial-legal:matter-workspace switch <slug>` or say `practice-level`." Load the active matter's `matter.md` for matter-specific context and overrides. Write outputs to the matter folder at `~/.claude/plugins/config/claude-for-legal/commercial-legal/matters/<matter-slug>/`. Never read another matter's files unless `Cross-matter context` is `on`.
---
Every contracts team has an escalation matrix, written or not. This skill reads the written one (in `~/.claude/plugins/config/claude-for-legal/commercial-legal/CLAUDE.md`), matches a contract issue against it, names the approver, and drafts the ask so the lawyer isn't writing "hey do you have a sec" messages at 5pm.
**Which side?** Before matching to the matrix, determine which side the company is on for the contract whose issue is being escalated. Usually obvious: if the counterparty is a vendor/supplier providing goods or services, you're purchasing-side. If the counterparty is a customer buying your product/service, you're sales-side. If it's not obvious, ask. Read the matching playbook section (`### Sales-side playbook` or `### Purchasing-side playbook`) to evaluate whether the term is inside fallbacks or triggers an automatic escalation — a term that's fine on one side can be a hard-no on the other. Note which side in the drafted ask so the approver knows which playbook was applied.
Read `~/.claude/plugins/config/claude-for-legal/commercial-legal/CLAUDE.md` → `## Escalation`. If it's missing or vague, say so — the cold-start interview should have captured this, and if it didn't, the practice profile needs editing.
Expected structure:
| Can approve | Threshold | Escalates to | Via | |---|---|---|---| | Paralegal | Standard terms, <$50K | Counsel | Slack | | Counsel | Non-standard but within fallbacks, <$500K | GC | Slack or email | | GC | Everything else | CFO/Board | Meeting |
Plus **automatic escalation triggers** — things that escalate regardless of dollar value. Typically: unlimited liability, IP assignment, anything on the "never accept" lists.
What's being escalated?
Don't escalate things that are actually fine. If the term is within the fallbacks in `~/.claude/plugins/config/claude-for-legal/commercial-legal/CLAUDE.md`, it doesn't need to go up.
Is the issue an automatic trigger? → YES: escalate to [person named for that trigger] → NO: continue Is the contract value above the reviewer's threshold? → YES: escalate to whoever has authority at that dollar level → NO: continue Is the term deviation outside all documented fallbacks? → YES: escalate to whoever can approve non-standard terms → NO: reviewer can approve — no escalation needed
Be specific. Not "escalate to legal leadership" — name the person or role from `~/.claude/plugins/config/claude-for-legal/commercial-legal/CLAUDE.md`. If the matrix doesn't name anyone for this situation, say so: "The escalation matrix doesn't cover [situation]. Suggest asking [GC name] who owns this."
The approver should be able to decide from the message alone — no "let me pull up the contract."
**Escalating to:** [name] **Via:** [Slack #channel / email / meeting — per `~/.claude/plugins/config/claude-for-legal/commercial-legal/CLAUDE.md`] **Urgency:** [deadline if there is one] --- Hey [name] — Need your call on the [Counterparty] [agreement type]. [One sentence on deal context.] **The issue:** [Plain English, one paragraph. What they want, why it's outside our standard, what the risk actually is.] **What the contract says:** > "[exact quote]" **What our playbook says:**
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…