ai-inventory
EU AI Act per-system inventory — track each AI system's role (provider, deployer, importer,…
Pre-drafting context gathering for a demand letter — parties, facts, basis, leverage, BATNA, and privilege filters — written to a structured intake.md the demand-draft skill reads. Use when the user wants to prep a demand letter, run intake before drafting, or capture context
$ npx -y skills add anthropics/claude-for-legal --skill demand-intake --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/demand-intakeContext preview
The summary Claude sees to decide when to auto-load this skill.
Pre-drafting context gathering for a demand letter — parties, facts, basis, leverage, BATNA, and privilege filters — written to a structured intake.md the demand-draft skill reads. Use when the user wants to prep a demand letter, run intake before drafting, or capture context
name: demand-intake description: Pre-drafting context gathering for a demand letter — parties, facts, basis, leverage, BATNA, and privilege filters — written to a structured intake.md the demand-draft skill reads. Use when the user wants to prep a demand letter, run intake before drafting, or capture context for a payment demand, breach/cure notice, cease-and-desist, employment separation, or preservation demand. argument-hint: "[title] [--full]"
1. Load `~/.claude/plugins/config/claude-for-legal/litigation-legal/CLAUDE.md` → demand-letter practice, landscape, risk calibration. 2. Follow the workflow and reference below. 3. Run the adaptive intake (core 8 always; strategic block if material or `--full`). 4. Generate slug from title + counterparty + year-month. 5. Write `~/.claude/plugins/config/claude-for-legal/litigation-legal/demand-letters/[slug]/intake.md`. 6. Confirm with user: "Intake saved. Run `/litigation-legal:demand-draft [slug]` when ready."
---
The drafting is downstream. The value is in the pre-writing — forcing the questions a careless letter skips. Leverage, BATNA, downside tolerance, privilege filters, the actual audience. A demand letter sent without thinking about those is worse than no letter.
> **Posture for this matter.** Demand-letter tone and terms are case-by-case, not a practice default. Ask: > - **Tone:** measured / assertive / aggressive? (depends on the relationship, the amount, and whether litigation is likely) > - **Response window:** what's reasonable given the claim? (14 days is common for payment demands; 30 days for cure; 7 days for cease-and-desist — but the contract or protocol may set it) > - **Marking:** does this need a "without prejudice" or "without prejudice save as to costs" marking? (settlement communications do; assertions of claim often don't; jurisdiction matters — ask if unsure) > - **Signer:** you, the client, the GC, instructed solicitor/counsel? > Don't assume. Read the prior demand correspondence in the matter file if there is any — it establishes the register.
Record the answers in the intake under a `## Posture` section before `## Parties`. These answers govern the rest of the intake and the downstream draft — do not fall back to a practice-level default if the user left any of them blank; ask again.
**1. Demand type** `payment | breach-cure | cease-desist | employment-separation | preservation | other`
**2. Parties**
**3. Triggering event**
*Seed doc opportunity: "If you can share the underlying contract, correspondence, or evidence, the draft will be materially sharper. Paths work."*
**4. Legal / contractual basis**
**5. Desired outcome**
**6. Deadlines**
**7. Prior outreach**
**8. Distribution**
Materiality heuristic: ask the strategic block if any of the following are true.
**Explicit skip option.** When the strategic block is triggered, the user can decline to answer it. Ask plainly:
> This is a material demand by the heuristic. The strategic block (leverage, BATNA, tone, privilege filters) is where most of the pre-writing value lives. Skipping it produces a thinner draft. > - **Answer now** — walk the strategic block (5-7 min) > - **Answer partial** — walk the subset you feel prepared for > - **Skip** — proceed to draft with only the core block; I'
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…