ai-inventory
EU AI Act per-system inventory — track each AI system's role (provider, deployer, importer,…
Aggregate diligence findings into a deal team briefing at the right altitude for the audience — exec summary for leadership, working summary for the team. Use when user says "brief the deal team", "what's the state of diligence", "summarize findings for [audience]", "deal
$ npx -y skills add anthropics/claude-for-legal --skill deal-team-summary --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/deal-team-summaryContext preview
The summary Claude sees to decide when to auto-load this skill.
Aggregate diligence findings into a deal team briefing at the right altitude for the audience — exec summary for leadership, working summary for the team. Use when user says "brief the deal team", "what's the state of diligence", "summarize findings for [audience]", "deal
name: deal-team-summary description: > Aggregate diligence findings into a deal team briefing at the right altitude for the audience — exec summary for leadership, working summary for the team. Use when user says "brief the deal team", "what's the state of diligence", "summarize findings for [audience]", "deal update", or on the briefing cadence.
**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`.
---
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.
Per `~/.claude/plugins/config/claude-for-legal/corporate-legal/CLAUDE.md` — what the business reads vs. what's for the file. Default tiers:
| Audience | Gets | Doesn't get | |---|---|---| | **Board / exec sponsor** | Top 3-5 material issues, price/structure impact, decision items | Category detail, green findings, process | | **Deal lead** | All reds, all yellows, progress, decision items, next steps | Green finding detail | | **Working team** | Everything — full findings, status by category, gaps | Nothing withheld |
Ask which tier if not obvious.
[WORK-PRODUCT HEADER — per plugin config ## Outputs — differs by role; see `## Who's using this`] > This brief aggregates privileged diligence findings and inherits the sources' privilege and confidentiality status. Distribution beyond the privilege circle (including to broader business teams) can waive privilege — confirm the distribution list matches the privilege circle before sending. # [Deal code] — Diligence Brief — [date] **Status:** [On track / Issues identified / Material findings] **Coverage:** [X]% of VDR reviewed ## Material findings [3-5 max. One paragraph each. What it is, why it matters to the deal, what we're doing about it.] ## Decisions needed - [ ] [Specific decision — price adjustment, indemnity ask, walk-away trigger] — [who decides] — [by when] ## Since last brief [What changed. New findings, findings resolved, coverage progress.]
Same as above plus:
## All open issues by category ### 🔴 Red [Finding title + one-line — link to full finding for detail] ### 🟡 Yellow [same] ## Progress | Category | Docs reviewed | Coverage | Reds | Yellows | Status | |---|---|---|---|---|---| | [name] | [N/M] | [%] | [N] | [N] | [Complete / In progress / Blocked] | ## Gaps and follow-ups - [Supplemental request items outstanding] - [Questions to management] ## Next 72 hours [What's getting reviewed, what briefings are scheduled]
Full finding detail. Same structure as above but every finding gets its full house-format block, not a one-liner.
If this is a recurring brief (per `~/.claude/plugins/config/claude-for-legal/corporate-legal/CLAUDE.md` cadence), lead with what changed:
Deal leads care more about movement than state. "Still 12 yellows" is less useful than "2 new yellows, 3 resolved."
End with the next-steps decision tree per CLAUDE.md `## Outputs`. Customize the options to what this skill just produced — the five default branches (draft the X, escalate, get more facts, watch and wait, something else) are a starting point, not a lock-in. The tree is the output; the lawyer picks.
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…