anthropics/claude-for-legal

# /ai-inventory

## When this runs

The user wants to manage their AI system inventory under the EU AI Act. The
core idea the skill exists to enforce: **role and tier are per-system, not
per-company.** A single organization can be a *provider* of System A, a
*deployer* of System B, and an *importer* of System C. Each combination
triggers a different set of obligations under the AI Act. The inventory
exists so those assessments are tracked where you can find them — the
obligations themselves are derived in conversation, not from a table.

## What to do

# /aia-generation

1. Read `~/.claude/plugins/config/claude-for-legal/ai-governance-legal/CLAUDE.md`. Confirm impact assessment house style is populated.
2. Determine risk track (fast or full) from governance tier and use case characteristics, using the framework below.
3. Run intake — conversational, not a form.
4. Regulatory classification for each regime in the footprint — research tier, prohibited-practice exposure, and applicable obligations; cite primary sources.
5. Write assessment in house style (from seed doc, or default if none captured).
6. Policy diff against `~/.claude/plugins/config/claude-for-legal/ai-governance-legal/CLAUDE.md` AI policy commitments.
7. Output: assessment doc + conditions list + handoff flags (privacy PIA, vendor review if needed).

```
/ai-governance-legal:aia-generation "AI résumé screening for HR"
```

# /cold-start-interview

1. Check `~/.claude/plugins/config/claude-for-legal/ai-governance-legal/CLAUDE.md` — if populated and no `--redo`, confirm before overwriting.
2. Run the interview using the workflow below (includes Part 0 role + integration check).
3. Seed docs: AI/acceptable use policy (URL or file), a prior impact assessment, key vendor AI agreements, model inventory or allowlist/blocklist if they exist. Read all provided.
4. Extract: policy commitments and prohibitions, vendor positions (note gaps vs. stated), impact assessment structure, approved/prohibited tool lists.
5. Migration: if a populated CLAUDE.md (no `[PLACEHOLDER]` markers) exists at `~/.claude/plugins/cache/claude-for-legal/ai-governance-legal/*/CLAUDE.md` but not at the config path, copy it to the config path and tell the user what was migrated.
6. Write `~/.claude/plugins/config/claude-for-legal/ai-governance-legal/CLAUDE.md` (create parent directories as needed). Show summary. Offer first task.

## Flags

- `--redo` — re-run the full interview and overwrite `~/.claude/plugins/config/claude-for-legal/ai-governance-legal/CLAUDE.md`.
- `--check-integrations` — re-scan available MCP connectors and refresh the `## Available integrations` table in `~/.claude/plugins/config/claude-for-legal/ai-governance-legal/CLAUDE.md` without re-running the full interview. Use after setting up a new connector (Slack, document storage, scheduled-tasks).

# /customize

## When this runs

The user typed `/ai-governance-legal:customize`. They want to change something
in their practice profile — a risk posture, an escalation contact, a playbook
position, a jurisdiction, an output format — without re-running the whole
cold-start interview and without hand-editing YAML.

## What to do

1. **Read the config.** Read
   `~/.claude/plugins/config/claude-for-legal/ai-governance-legal/CLAUDE.md`
   (and `~/.claude/plugins/config/claude-for-legal/company-profile.md` one

# /matter-workspace

Practitioners work across multiple clients and matters. A matter workspace keeps one client or engagement's context separate from every other. This skill manages those workspaces.

## Subcommands

- `/ai-governance-legal:matter-workspace new <slug>` — create a new matter workspace, run a short intake, write `matter.md`
- `/ai-governance-legal:matter-workspace list` — list matters with status and active flag
- `/ai-governance-legal:matter-workspace switch <slug>` — set the active matter
- `/ai-governance-legal:matter-workspace close <slug>` — archive a matter (move to `~/.claude/plugins/config/claude-for-legal/ai-governance-legal/matters/_archived/`, never delete)
- `/ai-governance-legal:matter-workspace none` — detach from any active matter, work at practice-level only

## Instructions

# /policy-monitor

**Sweep mode** (no argument or `--sweep`):
1. Read `~/.claude/plugins/config/claude-for-legal/ai-governance-legal/CLAUDE.md` → outputs folder path, AI policy document, last sweep date.
2. Use the framework below. Scan outputs folder for files since last sweep.
3. For each output: extract approved practices → diff against current policy commitments and use case registry.
4. Classify gaps: REQUIRED (policy misrepresents current practice) vs ADVISABLE (policy silent).
5. For each gap: quote current policy, describe gap, draft suggested language.
6. Flag any use cases in outputs not yet added to the `~/.claude/plugins/config/claude-for-legal/ai-governance-legal/CLAUDE.md` registry.
7. Present results to the human. Only after acknowledgment, update `Last policy sweep` and `gaps_found` in `~/.claude/plugins/config/claude-for-legal/ai-governance-legal/CLAUDE.md`.

**Direct query mode** (with description argument):
1. Read `~/.claude/plugins/config/claude-for-legal/ai-governance-legal/CLAUDE.md` → current policy commitments, use case registry, actual policy document.
2. Parse proposed practice. Diff against policy: use case coverage, automation level, affected parties, disclosure, vendor data use, oversight.

# /policy-starter

1. Read `~/.claude/plugins/config/claude-for-legal/ai-governance-legal/CLAUDE.md`. If the practice profile is unpopulated, stop and direct to `/ai-governance-legal:cold-start-interview`.
2. Use the framework below.
3. Run the scope interview — which sections does the policy need to cover, who's the audience, what's the deployment context. Do not skip to drafting.
4. Web search for the current published model policies and guidance relevant to the deployment context (ABA, state bars, ILTA, CLOC, NIST, peer-firm / peer-company policies, current state AI laws, EU AI Act, sector regulators as applicable).
5. Draft the selected sections, sourced from the model policies, with `[review]` flags on every choice point and `[review]` open questions at the bottom of each section.
6. Output with the draft header ("DRAFT FOR INTERNAL LEGAL REVIEW — NOT FOR DISTRIBUTION"), the sources block, the reviewer note, and the adoption checklist.
7. Close with the next-steps decision tree.

```
/ai-governance-legal:policy-starter
/ai-governance-legal:policy-starter "we need an AI policy for our 30-lawyer firm"
/ai-governance-legal:policy-starter "update our existing policy for the 2026 state AI laws"

# /reg-gap-analysis

1. Read `~/.claude/plugins/config/claude-for-legal/ai-governance-legal/CLAUDE.md`. Confirm regulatory footprint and use case registry are populated.
2. Use the framework below.
3. Scope: does this regulation apply? (Jurisdiction, threshold, builder/deployer, sector.) If not, one line and done.
4. Extract requirements. Diff against current state in `~/.claude/plugins/config/claude-for-legal/ai-governance-legal/CLAUDE.md`.
5. Prioritize gaps. Output: remediation plan with must-do / should-do / already compliant / accepted gaps.
6. Save as dated markdown doc for the file.

```
/ai-governance-legal:reg-gap-analysis "EU AI Act high-risk provisions"
```

---

# /use-case-triage

1. Read `~/.claude/plugins/config/claude-for-legal/ai-governance-legal/CLAUDE.md`. Confirm registry is populated — if not, stop and direct to setup.
2. Use the framework below. Clarify the use case if vague.
3. Registry lookup → red line check → classify.
4. Output: classification, reasoning, conditions table (if conditional), governance tier, cross-plugin handoffs.
5. Propose registry update if use case wasn't already in the registry.

```
/ai-governance-legal:use-case-triage "Sales team wants to score leads with AI automatically"
```

---

# /vendor-ai-review

1. Read `~/.claude/plugins/config/claude-for-legal/ai-governance-legal/CLAUDE.md`. Confirm vendor governance positions are populated — if not, stop and direct to setup.
2. Use the framework below.
3. Confirm document type (AI addendum / main agreement AI provisions / ToS). If only an AUP was provided, ask for the full terms.
4. Term-by-term review: training on data, confidentiality of inputs, model changes, output IP, liability, incident notification, human review rights, use restrictions, audit rights.
5. AI addendum gap check if DPA exists but no AI addendum.
6. AI policy consistency diff vs. `~/.claude/plugins/config/claude-for-legal/ai-governance-legal/CLAUDE.md`.
7. Output: bottom line, term-by-term, recommended redlines, if-they-won't-move routing.

```
/ai-governance-legal:vendor-ai-review openai-enterprise-agreement.pdf
```

# /amendment-history

Loads a base agreement and all amendments, then either summarizes what
changed over time or traces a specific provision to its current
controlling language.

## Instructions

1. **Get the documents:** From file upload, [CLM ID (coming soon)], or [repository link (coming soon)]. Accept multiple files in one invocation. If none
   provided, ask.

2. **Detect the mode** by parsing the request per the mode
   detection rules below. If a provision name is clearly stated, go straight
   to Mode 2. If no provision is mentioned, run Mode 1. Ask only if

# /cold-start-interview

Runs the cold-start interview. First run writes `~/.claude/plugins/config/claude-for-legal/commercial-legal/CLAUDE.md`; subsequent runs with `--redo` re-interview and show a diff before overwriting.

## Instructions

1. **Check current state:** Read `~/.claude/plugins/config/claude-for-legal/commercial-legal/CLAUDE.md`. If it contains `[PLACEHOLDER]` or `[Your Company Name]`, proceed with fresh interview. If populated and `--redo` not passed, ask: "Looks like you're already set up. Want to re-run the interview? This will overwrite `~/.claude/plugins/config/claude-for-legal/commercial-legal/CLAUDE.md` (I'll show you a diff first)."

2. **Follow the interview script below.**

3. **Ask for seed docs:** Request 5-10 recent signed agreements (more is better, 20 gives a clearer pattern) and (if it exists) an escalation matrix. Accept file paths, Google Drive links, or [CLM] record IDs.

4. **Read the seed docs** and extract actual playbook positions. Note deltas between stated positions and what was signed.

# /customize

## When this runs

The user typed `/commercial-legal:customize`. They want to change something
in their practice profile — a risk posture, an escalation contact, a playbook
position, a jurisdiction, an output format — without re-running the whole
cold-start interview and without hand-editing YAML.

## What to do

1. **Read the config.** Read
   `~/.claude/plugins/config/claude-for-legal/commercial-legal/CLAUDE.md`
   (and `~/.claude/plugins/config/claude-for-legal/company-profile.md` one

# /escalation-flagger

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.

## Instructions

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.

# /matter-workspace

Practitioners work across multiple clients and matters. A matter workspace keeps one client or engagement's context separate from every other. This command manages those workspaces.

## Subcommands

- `/commercial-legal:matter-workspace new <slug>` — create a new matter workspace, run a short intake, write `matter.md`
- `/commercial-legal:matter-workspace list` — list matters with status and active flag
- `/commercial-legal:matter-workspace switch <slug>` — set the active matter
- `/commercial-legal:matter-workspace close <slug>` — archive a matter (move to `~/.claude/plugins/config/claude-for-legal/commercial-legal/matters/_archived/`, never delete)
- `/commercial-legal:matter-workspace none` — detach from any active matter, work at practice-level only

## Instructions

# NDA Review

## Matter context

**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`.

---

## Destination check

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.

## Purpose

# /renewal-tracker

Surfaces what's renewing and when you have to cancel by.

## Instructions

1. **Read `~/.claude/plugins/config/claude-for-legal/commercial-legal/renewal-register.yaml`** (the config directory — survives plugin updates).

2. **Default mode:** Mode 2 — what's coming up in the next 90 days, grouped by urgency using half-open intervals so each deadline lands in exactly one band: 🔴 0–13 days, 🟠 14–44 days, 🟡 45–89 days. Days 14, 45, and 90 are boundaries — each belongs to exactly one band, not two.

3. **`--days N`:** Change the window.

4. **`--missed`:** Mode 4 — cancel-by deadlines that passed without recorded cancellation.

# /review

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.

## Instructions

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.**

# /review-proposals

Steps through pending playbook update proposals from the monitor agent and applies approved changes to `~/.claude/plugins/config/claude-for-legal/commercial-legal/CLAUDE.md`.

## Instructions

1. **Load the playbook-monitor agent** and run Step 5 (review and approval flow).

2. **If no proposals file exists** or it is empty: respond *"No pending proposals. Playbook is up to date."* Do not proceed further.

3. **Present proposals one at a time.** For each, show the full proposal block and offer four options: Accept, Reject, Edit, Defer.

4. **For Accept or Edit:** show the exact diff to `~/.claude/plugins/config/claude-for-legal/commercial-legal/CLAUDE.md` before writing. Only apply after the attorney explicitly confirms.

# SaaS / Subscription Agreement Review

## Matter context

**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`.

---

## Purpose

SaaS agreements have a distinct risk profile from one-time vendor contracts. The dollars compound over renewals, the data accumulates, and the switching cost grows every month. This skill reviews with that in mind.

It runs the standard playbook check from `~/.claude/plugins/config/claude-for-legal/commercial-legal/CLAUDE.md` and adds a SaaS-specific overlay on the terms that bite hardest in subscription deals.

# Stakeholder Summary

## Matter context

**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`.

---

## Destination check

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.

## Purpose

# Vendor Agreement Review

## Matter context

**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`.

---

## Destination check

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.

## Purpose

# AI Tool Handoff

## Matter context

**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 `/corporate-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/corporate-legal/matters/<matter-slug>/`. Never read another matter's files unless `Cross-matter context` is `on`.

---

## Purpose

Luminance and Kira are good at one thing: reading 500 contracts and finding every change-of-control clause. They're less good at judgment — deciding whether a particular CoC provision is actually triggered by this deal structure.

This skill hands off the bulk extraction to the right tool, then runs the QA layer on what comes back.

# Board Minutes

## Matter context

**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 `/corporate-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/corporate-legal/matters/<matter-slug>/`. Never read another matter's files unless `Cross-matter context` is `on`.

---

## Purpose

Board minutes are a legal record. They need to be accurate, complete, and in a format that will hold up under scrutiny — whether that's a financing due diligence review, a regulatory inquiry, or an M&A data room. This skill drafts them in your house format so you spend your time reviewing and correcting, not formatting and re-typing.

## Load context

# /closing-checklist

1. Read `~/.claude/plugins/config/claude-for-legal/corporate-legal/deals/[code]/closing-checklist.yaml` and use the modes below.
2. If status update provided: Mode 3 (update item).
3. Otherwise Mode 4: blocking items, critical path, days to close.

---

## Matter context

**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 `/corporate-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/corporate-legal/matters/<matter-slug>/`. Never read another matter's files unless `Cross-matter context` is `on`.

---

# /cold-start-interview

1. Check `~/.claude/plugins/config/claude-for-legal/corporate-legal/CLAUDE.md`. If `--new-deal`, skip to per-deal setup. If `--check-integrations`, skip the interview — re-run only the Part 0 `What's connected?` check and rewrite the `## Available integrations` table in `~/.claude/plugins/config/claude-for-legal/corporate-legal/CLAUDE.md`. When probing: only report ✓ if an MCP tool call actually succeeded. Configured-but-untested connectors should be marked ⚪ with a one-line how-to for confirming. Never report ✓ based on `.mcp.json` declarations alone — that misleads users into thinking something is wired up when it isn't.
2. Run the interview below (Part 0 first — role + integrations — then modules).
3. Seed docs: diligence request list + one prior issues memo.
4. Extract: categories, thresholds, memo format, AI tool config.
5. Migration: if a populated CLAUDE.md (no `[PLACEHOLDER]` markers) exists at `~/.claude/plugins/cache/claude-for-legal/corporate-legal/*/CLAUDE.md` but not at the config path, copy it to the config path and tell the user what was migrated.
6. Write `~/.claude/plugins/config/claude-for-legal/corporate-legal/CLAUDE.md` (create parent directories as needed). For `--new-deal`, write `~/.claude/plugins/config/claude-for-legal/corporate-legal/deals/[code]/deal-context.md`.

---

## Purpose

Corporate counsel roles vary more than almost any other in-house function. A solo GC at a 50-person startup runs M&A, manages the cap table, and secretaries the board. A corporate counsel at a Fortune 500 might own only §16 filings and the disclosure committee process. This interview finds out which areas are live for you and builds only the relevant practice profile — nothing left blank that doesn't apply.

# /customize

## When this runs

The user typed `/corporate-legal:customize`. They want to change something
in their practice profile — a risk posture, an escalation contact, a module
toggle, an output format — without re-running the whole cold-start interview
and without hand-editing YAML.

## What to do

1. **Read the config.** Read
   `~/.claude/plugins/config/claude-for-legal/corporate-legal/CLAUDE.md`
   (and `~/.claude/plugins/config/claude-for-legal/company-profile.md` one

# Deal Team Summary

## Matter context

**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 `/corporate-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/corporate-legal/matters/<matter-slug>/`. Never read another matter's files unless `Cross-matter context` is `on`.

---

## Purpose

The deal lead doesn't read 200 findings. They read: what's material, what changed since last brief, what needs a decision. This skill compresses the diligence output to the right level for the reader.

## Load context

# /diligence-issue-extraction

1. Load `~/.claude/plugins/config/claude-for-legal/corporate-legal/CLAUDE.md` + `~/.claude/plugins/config/claude-for-legal/corporate-legal/deals/[code]/deal-context.md`.
2. Use the workflow below.
3. Check `ai-tool-handoff` — if category is bulk and tool is configured, hand off first.
4. Read docs, apply materiality filter, extract per category.
5. Findings in house memo format. Hand off consents to closing checklist.

---

## Matter context

**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 `/corporate-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/corporate-legal/matters/<matter-slug>/`. Never read another matter's files unless `Cross-matter context` is `on`.

# /entity-compliance

1. Load `~/.claude/plugins/config/claude-for-legal/corporate-legal/CLAUDE.md` → `## Entity Management` (entity table, jurisdictions, registered agent).
2. Route to the correct mode below based on flag:
   - No flag or `--init`: Mode 1 — initialize tracker from entity table
   - `--report`: Mode 2 — surface upcoming deadlines and overdue items
   - `--update`: Mode 3a (manual) or 3b (--from-report upload) — update status
   - `--sweep`: Mode 3c — walk through unknown/overdue items one by one
   - `--audit`: Mode 4 — full health audit
   - `--export`: Mode 5 — produce CSV or table export
3. Read/write `~/.claude/plugins/config/claude-for-legal/corporate-legal/entities/compliance-tracker.yaml`.
4. After any update: show summary of changes and next action.

---

# /integration-management

1. Load `deal-context.md` for deal code, target, close date, deal lead.
2. Load `integration-tracker.yaml` if it exists (or create on --init).
3. Use the workflow below.
4. Route by flag:
   - `--init`: Mode 1 — read PA, build phased workplan, consent tracker
   - `--contracts`: Mode 2 — import contract list (repository or upload), tier and classify
   - `--report`: Mode 3 — generate status report
   - `--update`: Mode 4 — manual update or parse uploaded status document
   - `--export`: Mode 5 — CSV or table export
5. Read/write `~/.claude/plugins/config/claude-for-legal/corporate-legal/deals/[code]/integration-tracker.yaml`.
6. After any write: show summary of changes and surface any new flags.

# /material-contract-schedule

1. Load purchase agreement → Material Contract definition + schedule format.
2. Use the workflow below.
3. Apply definition to diligence findings. Flag edge cases.
4. Format per agreement. Consent overlay feeds closing checklist.

---

## Matter context

**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 `/corporate-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/corporate-legal/matters/<matter-slug>/`. Never read another matter's files unless `Cross-matter context` is `on`.

---

# /matter-workspace

Practitioners work across multiple clients and matters. A matter workspace keeps one client or engagement's context separate from every other. This skill manages those workspaces.

## Subcommands

- `/corporate-legal:matter-workspace new <slug>` — create a new matter workspace, run a short intake, write `matter.md`
- `/corporate-legal:matter-workspace list` — list matters with status and active flag
- `/corporate-legal:matter-workspace switch <slug>` — set the active matter
- `/corporate-legal:matter-workspace close <slug>` — archive a matter (move to `~/.claude/plugins/config/claude-for-legal/corporate-legal/matters/_archived/`, never delete)
- `/corporate-legal:matter-workspace none` — detach from any active matter, work at practice-level only

## Instructions

# /tabular-review

1. Load `~/.claude/plugins/config/claude-for-legal/corporate-legal/CLAUDE.md` → diligence structure, thresholds, house format.
2. Confirm: what documents, what columns, where does the output go.
3. Build the typed schema. Write `.review-schema.yaml`. Confirm with the user.
4. Sample run (3–5 docs). Adjust schema. Confirm.
5. Fan out — one sub-agent per document, parallel. Each cell: value + state + verbatim quote + location.
6. Normalization pass. Flag outliers and inconsistencies.
7. Output: `.xlsx` or Google Sheets (ask which), plus `.csv` + `_sources.csv` + markdown always. Work-product header.
8. Summary: verification workload (counts of not_present / unclear / needs_review per column), flagged columns, where the files are, reminder that every cell is a lead not a finding.

```
/corporate-legal:tabular-review
/corporate-legal:tabular-review --schema .review-schema.yaml --docs ./vdr/02-Contracts/

# /written-consent

1. Load `~/.claude/plugins/config/claude-for-legal/corporate-legal/CLAUDE.md` → Board & Secretary (consents repository, resolution language, state of incorporation, board composition).
2. Use the workflow below.
3. Identify the action and classify (routine / review-flag).
4. If review-flag: show outside counsel warning and confirm before proceeding.
5. Search consents repository for closest precedent. If no repository: use seed consents from `~/.claude/plugins/config/claude-for-legal/corporate-legal/CLAUDE.md`.
6. Draft consent in house format using precedent as base.
7. Output: consent draft + signatory checklist + review prompts.

---

## Matter context

# /cold-start-interview

1. Check `~/.claude/plugins/config/claude-for-legal/employment-legal/CLAUDE.md`. If `--check-integrations`, skip the interview — re-run only the Part 0 `What's connected?` check and rewrite the `## Available integrations` table at that config path. When probing: only report ✓ if an MCP tool call actually succeeded. Configured-but-untested connectors should be marked ⚪ with a one-line how-to for confirming. Never report ✓ based on `.mcp.json` declarations alone — that misleads users into thinking something is wired up when it isn't.
2. Run the interview below (Part 0 first — role + integrations — then footprint): states/countries, hiring/term review triggers, severance practice.
3. Seed docs: handbook + 3 termination memos.
4. Build jurisdiction-specific escalation table.
5. If a populated CLAUDE.md (no `[PLACEHOLDER]` markers) exists at `~/.claude/plugins/cache/claude-for-legal/employment-legal/*/CLAUDE.md` but not at the config path, copy it to the config path and tell the user what was migrated.
6. Write `~/.claude/plugins/config/claude-for-legal/employment-legal/CLAUDE.md`, creating parent directories as needed.

---

# Cold-Start Interview: Employment Counsel

## Purpose

# /customize

## When this runs

The user typed `/employment-legal:customize`. They want to change something
in their practice profile — a jurisdiction, a risk posture, an escalation
contact, a handbook position — without re-running the whole cold-start
interview and without hand-editing YAML.

## What to do

1. **Read the config.** Read
   `~/.claude/plugins/config/claude-for-legal/employment-legal/CLAUDE.md`
   (and `~/.claude/plugins/config/claude-for-legal/company-profile.md` one

# /expansion-kickoff

Starts an international expansion project for a new country — gathers intake,
runs EOR vs. entity framing, drafts cross-functional questions, surfaces
country-specific flags, and creates a persistent tracker.

## Instructions

1. Load `~/.claude/plugins/config/claude-for-legal/employment-legal/CLAUDE.md` → jurisdictional footprint, escalation table.
2. Load the `international-expansion` reference skill and run the full workflow.
3. If a tracker file already exists for this country (`~/.claude/plugins/config/claude-for-legal/employment-legal/expansion-[slug].yaml`),
   flag it: "An expansion tracker for [country] already exists. Use
   `/employment-legal:expansion-update [country]` to update it, or confirm
   you want to start over."

# /expansion-update

Returns to an open expansion tracker and updates item status based on what
has happened since the last session. Recalculates what is now unblocked,
flags anything overdue, and surfaces the next priorities.

## Instructions

1. Load `~/.claude/plugins/config/claude-for-legal/employment-legal/CLAUDE.md`.

2. Identify the tracker file: `~/.claude/plugins/config/claude-for-legal/employment-legal/expansion-[slug].yaml`. If it doesn't
   exist, respond: "No expansion tracker found for [country]. Run
   `/employment-legal:expansion-kickoff [country]` to start one."

# Handbook Updates

## Matter context

**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 `/employment-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/employment-legal/matters/<matter-slug>/`. Never read another matter's files unless `Cross-matter context` is `on`.

---

## Purpose

Handbook changes have ripple effects. Change the PTO policy and you've affected the final pay calculation, the leave policy cross-reference, and three state supplements. This skill finds the ripples before they become inconsistencies.

## Load context

# /hiring-review

1. Load `~/.claude/plugins/config/claude-for-legal/employment-legal/CLAUDE.md` → jurisdictional footprint, hiring review triggers, restrictive covenant policy.
2. Use the workflow below.
3. Check: jurisdiction, classification, restrictive covenants, background check compliance.
4. Flag anything that hits the jurisdiction-specific escalation table.

---

## Matter context

**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 `/employment-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/employment-legal/matters/<matter-slug>/`. Never read another matter's files unless `Cross-matter context` is `on`.

---

# Internal Investigation Skill

## Matter context

**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 `/employment-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/employment-legal/matters/<matter-slug>/`. Never read another matter's files unless `Cross-matter context` is `on`.

---

## Output header

Prepend the work-product header from `~/.claude/plugins/config/claude-for-legal/employment-legal/CLAUDE.md` → `## Outputs` (it differs by user role — see `## Who's using this`). Every file, log, memo, and summary produced by this skill opens with that header.

> **Distribution discipline.** Every file this skill creates — log entries, memo drafts, audience summaries, document notes — inherits the privilege and confidentiality status of the underlying investigation. Distribution beyond the privilege circle (forwarding to non-attorneys outside the investigation team, cc'ing HR without scoping, handing to the business side) can waive privilege over the entire investigation. Store these files where privileged materials live, label per the work-product header, and make every distribution decision deliberately.

# International Expansion Skill

## Matter context

**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 `/employment-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/employment-legal/matters/<matter-slug>/`. Never read another matter's files unless `Cross-matter context` is `on`.

---

## Purpose

International hiring gets handled sloppily at scaleups because nobody owns
the full picture. Legal knows the employment-law questions but not the PE
risk questions. Finance knows the cost model but not the employee-representation
triggers. HR knows the comp benchmarks but not the Day 1 compliance requirements.

# /investigation-add

Adds data to an open investigation log. Processes document batches using
documented pull criteria, surfaces significant items, logs everything
reviewed for coverage verification.

## Instructions

1. Load `~/.claude/plugins/config/claude-for-legal/employment-legal/CLAUDE.md`.
2. Load the `internal-investigation` reference skill and run Mode 2 (Add data).
3. After processing, show the surface ratio and list of surfaced items.
4. Prompt to update the sources checklist if the data covers a checklist item.

## Examples

# /investigation-memo

Drafts the first cut of the privileged investigation memo from the log,
or updates an existing draft when new data has been added.

## Instructions

1. Load the `internal-investigation` reference skill and run Mode 4 (Draft or update memo).
2. If drafting for the first time, warn if high-priority sources are still
   open on the checklist.
3. If updating, show what changed before rewriting.
4. All output is marked PRIVILEGED AND CONFIDENTIAL — ATTORNEY WORK PRODUCT.

## Examples

# /investigation-open

Opens a new investigation matter — runs intake, generates the sources
checklist, and creates the persistent investigation log.

## Instructions

1. Load `~/.claude/plugins/config/claude-for-legal/employment-legal/CLAUDE.md`.
2. Load the `internal-investigation` reference skill and run Mode 1 (Open).
3. If a matter with the same slug already exists, warn before overwriting.

## Examples

```

# /investigation-query

Answers questions against the investigation log — what witnesses said,
where accounts conflict, what gaps exist, what the strongest evidence is
on each issue.

## Instructions

1. Load the `internal-investigation` reference skill and run Mode 3 (Query).
2. Always cite log entry IDs in the answer.
3. If the log contains nothing relevant to the question, say so explicitly —
   "I have not seen any information on [topic] in this investigation log
   ([N] entries reviewed)" — and offer to flag it as a gap.

# /investigation-summary

Drafts a stripped-down, audience-appropriate summary from the privileged
investigation memo. HR summaries contain no privilege analysis. Leadership
summaries are high-level. Outside counsel briefings include full context.

## Instructions

1. Load the `internal-investigation` reference skill and run Mode 5 (Audience summary).
2. If no memo exists yet, offer to draft the memo first.
3. HR summaries must not include attorney mental impressions, credibility
   methodology, or legal exposure analysis.

## Examples

# /leave-tracker

Checks all open leaves with hard legal deadlines and surfaces only the ones
requiring a decision or action. Not a status board — tells you what you need
to do and why.

## Instructions

1. Load the `leave-tracker` agent and run the full workflow.

2. If no HRIS is connected and no `~/.claude/plugins/config/claude-for-legal/employment-legal/leave-register.yaml` exists, prompt
   the attorney to upload a leave spreadsheet or use
   `/employment-legal:log-leave` to add entries.

# /log-leave

Adds a new leave entry to `~/.claude/plugins/config/claude-for-legal/employment-legal/leave-register.yaml` with the minimum
information needed to start tracking deadlines. Use when an employee goes on
leave and you want the tracker to watch the clocks from day one.

## Instructions

1. Read `~/.claude/plugins/config/claude-for-legal/employment-legal/CLAUDE.md` → jurisdiction table and Systems section.

2. Ask all of the following in a single prompt — do not drip them one at a time:

   > A few quick questions to set up leave tracking:
   >

# /matter-workspace

Practitioners work across multiple clients and matters. A matter workspace keeps one client or engagement's context separate from every other. This skill manages those workspaces.

## Subcommands

- `/employment-legal:matter-workspace new <slug>` — create a new matter workspace, run a short intake, write `matter.md`
- `/employment-legal:matter-workspace list` — list matters with status and active flag
- `/employment-legal:matter-workspace switch <slug>` — set the active matter
- `/employment-legal:matter-workspace close <slug>` — archive a matter (move to `~/.claude/plugins/config/claude-for-legal/employment-legal/matters/_archived/`, never delete)
- `/employment-legal:matter-workspace none` — detach from any active matter, work at practice-level only

## Instructions

# /policy-drafting

1. Load `~/.claude/plugins/config/claude-for-legal/employment-legal/CLAUDE.md` → jurisdictional footprint, handbook location.
2. Use the workflow below.
3. Draft core policy. Check each jurisdiction in footprint for required variants.
4. Output: core policy + state supplements. Flag where law is currently shifting.

---

## Matter context

**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 `/employment-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/employment-legal/matters/<matter-slug>/`. Never read another matter's files unless `Cross-matter context` is `on`.

---

# /termination-review

1. Load `~/.claude/plugins/config/claude-for-legal/employment-legal/CLAUDE.md` → termination review triggers, high-risk flags, severance practice, jurisdiction rules.
2. Use the workflow below.
3. Walk the checklist. Check every high-risk flag.
4. Final pay timing per employee's jurisdiction. Severance + release if applicable.
5. If any high-risk flag fires: escalate per table, don't proceed without sign-off.

---

## Matter context

**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 `/employment-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/employment-legal/matters/<matter-slug>/`. Never read another matter's files unless `Cross-matter context` is `on`.

# /wage-hour-qa

1. Load `~/.claude/plugins/config/claude-for-legal/employment-legal/CLAUDE.md` → jurisdictional footprint.
2. Use the workflow below.
3. Identify jurisdiction the question is about. If not specified, ask.
4. Answer per that jurisdiction's rule. Cite. Flag if it's a close call or law is shifting.

---

## Matter context

**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 `/employment-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/employment-legal/matters/<matter-slug>/`. Never read another matter's files unless `Cross-matter context` is `on`.

---

# /worker-classification

Runs the applicable classification tests for the jurisdiction and flags where
the proposed arrangement doesn't match the structure you're trying to use.
Prospective only — for existing relationships, consult counsel.

## Instructions

1. Load `~/.claude/plugins/config/claude-for-legal/employment-legal/CLAUDE.md` → jurisdictional footprint, escalation table.
2. Run the full workflow below.
3. If the attorney provides details upfront, extract what's available and ask
   only about the gaps. Do not re-ask information already provided.

## Examples

# Westlaw Deep Research

Westlaw Deep Research searches Westlaw's database of caselaw, statutes, and administrative decisions and returns a written research report that explains, analyzes, or synthesizes relevant authority.

Deep Research employs an agentic process that mirrors the methodology of human researchers, utilizing Westlaw's proprietary tools to systematically analyze the trusted content available on Westlaw and Practical Law.

This skill will autonomously run the full research cycle: start, poll, report.

## Prerequisites

The `cocounsel-legal` MCP server must be connected. Verify it is available before starting research. If the server is not connected, inform the user and stop.

## When to Use

# /cease-desist

Two modes. Pick one:

- `/ip-legal:cease-desist --send` — draft a cease-and-desist letter calibrated to your enforcement posture. Loud gate runs before delivery.
- `/ip-legal:cease-desist --receive` — triage a C&D someone sent you. Produces an options memo with a recommendation.

## Instructions

1. **Read the practice profile.** Load `~/.claude/plugins/config/claude-for-legal/ip-legal/CLAUDE.md`. If it contains `[PLACEHOLDER]` markers or does not exist, stop and say: "This plugin needs setup before it can give you useful output. Run `/ip-legal:cold-start-interview` — the C&D skill depends on your enforcement posture, approval matrix, and practice-area mix, none of which are configured yet."

2. **Check matter workspaces.** Per `## Matter workspaces`: if `Enabled` is `✗`, skip — skills use practice-level context. If enabled and there is no active matter, ask: "Which matter is this for? Run `/ip-legal:matter-workspace switch <slug>` or say `practice-level`."

3. **Dispatch on `$ARGUMENTS`:**

# /clearance

**This is a triage, not a clearance opinion.** A trademark clearance opinion
requires a full professional search and registered trademark counsel's
judgment. A "no obvious conflicts" result means the triage
didn't find anything — it does not mean the mark is clear. Clients have been
sued over marks that passed a knockout search.

## Instructions

1. Read `~/.claude/plugins/config/claude-for-legal/ip-legal/CLAUDE.md`. If it
   contains `[PLACEHOLDER]`, stop and direct to `/ip-legal:cold-start-interview`.
2. Follow the workflow below.
3. Run intake (mark, goods/services, classes, jurisdictions, visual/stylization).

# /cold-start-interview

Runs the cold-start interview. First run writes `~/.claude/plugins/config/claude-for-legal/ip-legal/CLAUDE.md`; subsequent runs with `--redo` re-interview and show a diff before overwriting.

## Instructions

1. **Check current state:** Read `~/.claude/plugins/config/claude-for-legal/ip-legal/CLAUDE.md`. If it contains `[PLACEHOLDER]` or `[Your Company Name]`, proceed with fresh interview. If populated and `--redo` not passed, ask: "Looks like you're already set up. Want to re-run the interview? This will overwrite `~/.claude/plugins/config/claude-for-legal/ip-legal/CLAUDE.md` (I'll show you a diff first)."

2. **Follow the interview script below.**

3. **Ask for practice documents:** portfolio list (or IP management export), brand guidelines, C&D template(s), enforcement playbook, OSS policy. Accept file paths, Google Drive links, or IP-management record IDs.

4. **Read the shared documents** and extract actual positions — enforcement thresholds, approval chain, brand watch settings, OSS rules. Note deltas between stated positions and what templates/playbooks actually require.

# /customize

## When this runs

The user typed `/ip-legal:customize`. They want to change something in their
practice profile — a risk posture, an escalation contact, a portfolio
position, an enforcement tactic — without re-running the whole cold-start
interview and without hand-editing YAML.

## What to do

1. **Read the config.** Read
   `~/.claude/plugins/config/claude-for-legal/ip-legal/CLAUDE.md`
   (and `~/.claude/plugins/config/claude-for-legal/company-profile.md` one

# /fto-triage

**This is not a freedom-to-operate opinion.** A formal FTO opinion requires a
comprehensive search, full claim construction, and element-by-element
infringement analysis by registered patent counsel. Patent infringement is
strict liability; willful infringement triples damages. A "no obvious blocking
patents" result from this skill means the triage didn't find one — it does
not mean the product is clear.

## Instructions

1. Read `~/.claude/plugins/config/claude-for-legal/ip-legal/CLAUDE.md`. If it
   contains `[PLACEHOLDER]`, stop and direct to `/ip-legal:cold-start-interview`.
2. Follow the workflow below.

# /infringement-triage

**This is a triage, not a finding of infringement or non-infringement.**
Infringement analysis is fact-intensive and legally complex. Acting on a
triage — sending a cease-and-desist, refusing to stop, filing suit, or
deciding not to — without attorney review is how companies end up on the
wrong side of fee awards, Rule 11 sanctions, declaratory-judgment actions,
and (for patents) treble damages.

## Instructions

1. Read `~/.claude/plugins/config/claude-for-legal/ip-legal/CLAUDE.md`. If it
   contains `[PLACEHOLDER]`, stop and direct to `/ip-legal:cold-start-interview`.
2. Follow the workflow below.

# /invention-intake

**This is a first-pass screen by a non-specialist, not a patentability
opinion.** The screen never concludes that an invention is patentable — it
concludes that it passes the initial screen and warrants a prior-art search
and registered-practitioner review, that it needs more information, or that
it hits a disqualifier. A prior-art search is a separate step; this skill
does not do one.

## Instructions

1. Read `~/.claude/plugins/config/claude-for-legal/ip-legal/CLAUDE.md`. If it
   contains `[PLACEHOLDER]`, stop and direct to `/ip-legal:cold-start-interview`. If the
   practice profile shows trademark- or copyright-only (no patent practice),

# /ip-clause-review

Reviews the IP clauses in an agreement against the practice profile in `~/.claude/plugins/config/claude-for-legal/ip-legal/CLAUDE.md`. Flags assignment gaps, ownership ambiguity, license-scope issues, and IP warranty/indemnity problems. Produces a memo with per-clause findings, prioritized by risk, with suggested redline language where appropriate.

## Instructions

1. **Load `~/.claude/plugins/config/claude-for-legal/ip-legal/CLAUDE.md`.** If placeholders present, stop and prompt: "Run `/ip-legal:cold-start-interview` first — I need to learn your practice profile before I can review IP clauses against it."

2. **Get the agreement:** From file path, Drive link, or pasted text. If none provided, ask.

3. **Follow the workflow below.** In particular:
   - Establish the agreement type and which side the company is on for IP (granting / receiving / both). The side question is per-document, not a one-time setup answer.
   - Run the assignment gap check first if the agreement is an employment, consulting, SOW, or work-for-hire document.
   - Produce per-clause findings prioritized by risk.