ai-inventory
EU AI Act per-system inventory — track each AI system's role (provider, deployer, importer,…
Review a vendor agreement, NDA, or SaaS subscription against your playbook. Identifies the agreement structure from titles, routes to the right review skill (vendor-agreement-review, nda-review, saas-msa-review), and integrates the output into a single memo. Use when the user
$ npx -y skills add anthropics/claude-for-legal --skill review --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/reviewContext preview
The summary Claude sees to decide when to auto-load this skill.
Review a vendor agreement, NDA, or SaaS subscription against your playbook. Identifies the agreement structure from titles, routes to the right review skill (vendor-agreement-review, nda-review, saas-msa-review), and integrates the output into a single memo. Use when the user
name: review description: > Review a vendor agreement, NDA, or SaaS subscription against your playbook. Identifies the agreement structure from titles, routes to the right review skill (vendor-agreement-review, nda-review, saas-msa-review), and integrates the output into a single memo. Use when the user says "review this contract", "check this MSA", "is this NDA okay", "look at this SaaS agreement", or attaches an inbound agreement for review. argument-hint: '[file path | Drive link | [CLM ID] | paste text]'
Reviews an inbound agreement against the playbook in `~/.claude/plugins/config/claude-for-legal/commercial-legal/CLAUDE.md`. Identifies the agreement structure from titles, selects the appropriate skill(s), and — if confirm_routing is enabled — checks with the user before proceeding.
1. **Load `~/.claude/plugins/config/claude-for-legal/commercial-legal/CLAUDE.md`.** If placeholders present, stop and prompt: "Run `/commercial-legal:cold-start-interview` first — I need to learn your playbook before I can review against it."
Also read `~/.claude/plugins/config/claude-for-legal/commercial-legal/CLAUDE.md` → `## Review preferences` → `confirm_routing`. If the field is missing, treat it as `true`.
2. **Get the agreement:** From file path, Drive link, [CLM ID], or pasted text. If none provided, ask.
3. **Read the document structure — titles first.**
Before reading the body, extract:
This is the routing signal. Do not rely on body keywords alone — a 40-page MSA with "confidential" throughout is not an NDA.
4. **Select the skill(s) based on document structure.**
Map each identified document or section to a skill:
| Document / section title contains | Skill | |---|---| | Non-Disclosure, NDA, Confidentiality Agreement (as the *main* agreement) | **nda-review** | | Master Services Agreement, Professional Services, Statement of Work, Consulting Agreement | **vendor-agreement-review** | | Subscription, SaaS, Cloud Services, Order Form with auto-renewal, Software License with recurring fees | **saas-msa-review** (overlay on vendor-agreement-review) | | Data Processing Addendum, DPA, Data Processing Agreement (as exhibit or standalone) | note for **vendor-agreement-review** → data protection section | | Service Level Agreement, SLA (as exhibit) | note for **saas-msa-review** → SLA section |
Multiple skills may apply. Common combinations:
When the structure is genuinely ambiguous after reading titles (e.g., a document titled "Agreement" with no exhibits listed), read the first two pages of the body to resolve it — then stop and route.
5. **Confirm routing if enabled.**
If `confirm_routing` is `true` in `~/.claude/plugins/config/claude-for-legal/commercial-legal/CLAUDE.md` (or field is absent):
I'm going to review this as: [agreement type(s)]. Documents identified: - [Main agreement title] → [skill] - [Exhibit A title] → [how it will be handled] - [Exhibit B title] → [how it will be handled] Sound right? (yes / no — or tell me what I got wrong)
Wait for confirmation before proceeding. If the user corrects the routing, apply their instruction and proceed.
If `confirm_routing` is `false`: proceed silently. Log the routing decision at the top of the review memo so the user can see what was applied.
6. **Run the skill(s).** Follow each skill's workflow fully. If multiple skills apply, run them in sequence and integrate the output into a single memo — don't produce separate memos.
7. **Check for escalations:** If any issue exceeds the reviewer's authority per the `~/.claude/plugins/config/claude-for-legal/commercial-legal/CLAUDE.md` matrix, invoke **escalation-flagger** to route and draft the ask.
8. **Offer follow-ups:**
Add to `~/.claude/plugins/config/claude-for-legal/commercial-legal/CLAUDE.md` → `## Review preferences`:
## Review preferences confirm_routing: true # Set to false to skip routing confirmation and proceed automatically
The cold-start interview should ask about this preference. Default is `true` — confirmation on. As trust builds, the user can set it to `false`.
/commercial-legal:review vendor-msa.pdf
/commercial-legal:review https://drive.google.com/file/d/ABC123
/commercial-legal:review [paste agreement text]
Full review memo per the skill's format. Routing decision logged at the top. Deviation-by-deviation, specific redline language, named approver. Saved where `~/.claude/plugins/config/claude-for-legal/commercial-legal/CLAUDE.md` → House style says work product goes.
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…