ai-inventory
EU AI Act per-system inventory — track each AI system's role (provider, deployer, importer,…
Reference: review of an inbound vendor agreement against the team playbook in `~/.claude/plugins/config/claude-for-legal/commercial-legal/CLAUDE.md`. Flags deviations, assesses risk, generates specific redline language, and routes to the right approver. Loaded by
$ npx -y skills add anthropics/claude-for-legal --skill vendor-agreement-review --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/vendor-agreement-reviewContext preview
The summary Claude sees to decide when to auto-load this skill.
Reference: review of an inbound vendor agreement against the team playbook in `~/.claude/plugins/config/claude-for-legal/commercial-legal/CLAUDE.md`. Flags deviations, assesses risk, generates specific redline language, and routes to the right approver. Loaded by
name: vendor-agreement-review description: > Reference: review of an inbound vendor agreement against the team playbook in `~/.claude/plugins/config/claude-for-legal/commercial-legal/CLAUDE.md`. Flags deviations, assesses risk, generates specific redline language, and routes to the right approver. Loaded by /commercial-legal:review when a vendor MSA, services agreement, or similar is detected. user-invocable: false
**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`.
---
Before producing output, check where it's going. If the user has named a destination (a channel, a distribution list, a counterparty, "everyone"), ask whether it's inside the privilege circle. Public channels, company-wide lists, counterparty/opposing counsel, vendors, and clients (for work product) waive the protection. When the destination looks outside the circle, flag it and offer (a) the privileged version for legal only, (b) a sanitized version for the broader channel, or (c) both — don't silently apply a privileged header and then help paste it somewhere the header won't protect it. See the canonical `## Shared guardrails → Destination check` in this plugin's CLAUDE.md.
Read a vendor agreement against the playbook this team actually uses (in `~/.claude/plugins/config/claude-for-legal/commercial-legal/CLAUDE.md`), find every term that deviates, and tell the lawyer what to do about each one — with specific redline language, not vague "consider revising."
The output is a review memo the lawyer can act on in one pass. Every issue has a severity, a business-impact explanation, a proposed fix, and an escalation call if one is needed.
**Before reading the contract, read `~/.claude/plugins/config/claude-for-legal/commercial-legal/CLAUDE.md`.** If it's missing or still has placeholders, surface this bounce:
> I notice you haven't configured your practice profile yet — that's how I tailor playbook positions, escalation, and house style to your practice. > > **Two choices:** > - Run `/commercial-legal:cold-start-interview` (2 minutes) to configure your profile, then I'll review tailored to YOUR playbook. > - Say **"provisional"** and I'll review against generic defaults — US jurisdiction, middle risk appetite, lawyer role, no playbook (flag all common vendor-contract risks from first principles) — and tag every output `[PROVISIONAL — configure your profile for tailored output]` so you can see what I do before committing.
If the user says "provisional," run the review normally using these generic defaults: middle risk appetite, lawyer role, US jurisdiction, no playbook (flag the common vendor-side risks from first principles — unlimited liability, no data-breach carveout, uncapped indemnity, auto-renewal without notice, etc. — rather than matching to configured positions). Tag the reviewer note and every finding block with `[PROVISIONAL]`. At the end of the output, append:
> "That was a generic run against default assumptions. Run `/commercial-legal:cold-start-interview` to get output calibrated to YOUR practice — your playbook, your jurisdiction, your risk appetite. 2 minutes."
**Which side?** Before applying the playbook, determine which side the company is on for this contract. 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 (a reseller agreement, a partnership, a revenue share), ask: "Which side is [company] on for this agreement — vendor or customer?" Read the matching playbook section (`### Sales-side playbook` or `### Purchasing-side playbook`) from the config. Note which side in the output so the reviewer knows which playbook was applied. If the matching side is `[Not configured]`, stop and tell the user to run `/commercial-legal:cold-start-interview --side <side>` before this review can proceed.
This skill is typically used for purchasing-side contracts (vendors supplying you), but the side check still applies — a "vendor agreement" could be your own template sent to a vendor as part of a reseller arrangement (sales-side).
The playbook in `~/.claude/plugins/config/claude-for-legal/commercial-legal/CLAUDE.md` is the source of truth. It tells you:
If the contract has the deal-breaker, flag it at the top of the memo and stop the detailed review. There's no point spending 30 minutes on liability caps if the agreement gives the vendor rights to use customer data for training.
Read the whole agreement once, fast. Answer:
| Question | Answer | |---|---| | What kind of agreement is this? | MSA / SaaS subscription / Professional services / License / Other | | Who are we? | Customer / Vendor (this plugin assumes customer — flag if not) | | Counterparty | Name, and are they a BigCo (won't negotiate) or a startup (will)? | | Dollar value | Annual / total contract value if stated | | Term | Length, renewal mechanics | | Is there a DPA? | Attached / reference
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…