
demand-intake
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.
- Installs
- 611
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/anthropics/claude-for-legal --skill demand-intake- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads demand-intake automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
/demand-intake
- Load
~/.claude/plugins/config/claude-for-legal/litigation-legal/CLAUDE.md→ demand-letter practice, landscape, risk calibration. - Follow the workflow and reference below.
- Run the adaptive intake (core 8 always; strategic block if material or
--full). - Generate slug from title + counterparty + year-month.
- Write
~/.claude/plugins/config/claude-for-legal/litigation-legal/demand-letters/[slug]/intake.md. - Confirm with user: "Intake saved. Run
/litigation-legal:demand-draft [slug]when ready."
Demand Intake
Purpose
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.
Load context
~/.claude/plugins/config/claude-for-legal/litigation-legal/CLAUDE.md→ Demand-letter practice (insurance-tender timing, materiality threshold for matter creation, any seed-doc templates), landscape (counterparty type, repeat-adversary patterns), risk calibration (to pre-estimate materiality), house style. Tone, compliance period, marking, signer are NOT practice-level defaults — they are set per matter in the## Posture for this matterstep below.
Flags
--full→ run the complete intake regardless of materiality heuristics (for counsel who wants thorough every time)
The intake
Posture for this matter (ask FIRST, before the core)
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.
Core — always asked (8 questions)
1. Demand type
payment | breach-cure | cease-desist | employment-separation | preservation | other
2. Parties
- Sender: our company (and any specific entity if multi-entity)
- Recipient: counterparty — name, entity, address
- Recipient audience: who actually reads (GC? CEO? individual? in-house legal?)
- Relationship:
customer | vendor | ex-employee | competitor | third-party | other
3. Triggering event
- What happened and when (dates matter — statute-of-limitations, notice periods)
- Evidence available (contracts, emails, records, witnesses)
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
- Which provisions — specific contract sections if applicable
- Governing law (jurisdiction, choice-of-law clause)
- Statutes or rules relied on (placeholders OK — the draft will flag
[CITE:___]anyway)
5. Desired outcome
- Specific asks. Not "resolution" — payment of $X by date Y; cessation of specific activity Z; cure within N days; return of specific property.
- If multiple asks, order them (primary vs. fallback)
6. Deadlines
- External deadline driving this (SoL, ongoing harm window, business event)
- Demand compliance deadline — how long we give the recipient. Use the response window captured in
## Posture for this matterabove; do not fall back to a practice-level default.
7. Prior outreach
- Has this been raised informally? When, by whom, in what form?
- Any response so far?
- Why is escalation to a demand letter happening now?
8. Distribution
- Delivery method (ask; no practice-level default)
- Signer — captured in
## Posture for this matterabove - Copies — internal stakeholders, insurance carrier (if tendering pre-demand per practice-level tender-timing rule), counsel
Strategic — asked if material, or if --full
Materiality heuristic: ask the strategic block if any of the following are true.
- Demand type is
cease-desist,breach-cure,employment-separation, orpreservation - Desired outcome dollar value ≥ the medium-severity band from
~/.claude/plugins/config/claude-for-legal/litigation-legal/CLAUDE.mdrisk calibration - Counterparty is a customer, competitor, or frequent adversary per
~/.claude/plugins/config/claude-for-legal/litigation-legal/CLAUDE.mdlandscape - User ran with
--full
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'll flag
strategic_block: skippedin the intake
If the user chooses Skip, the intake file records it:
strategic_block: skipped # answered | partial | skipped
skipped_reason: string | null # captured if user provided one
The draft skill honors the skip — pre-draft gate runs regardless, but sections that depend on strategic-block answers get [SME VERIFY: leverage/tone/privilege not captured in intake] markers. The /demand-draft command also prompts a second time, asking whether the user wants to complete the strategic block before drafting.
9. Leverage and BATNA
- What gives us negotiating power (contractual rights, factual leverage, reputational, commercial)
- What if they refuse — are we prepared to litigate? Go public? Accept a smaller outcome?
- Their likely BATNA — what's their best alternative? (If they don't think we'll sue, the demand is weak.)
10. Downside tolerance
- Reputational exposure if this becomes public
- Precedent risk — does this letter set a pattern that affects other matters?
- Regulatory / disclosure implications (is this the kind of dispute that becomes a 10-Q item?)
- Insurance implications — does sending without tendering waive coverage?
11. Tone posture
- Already captured in
## Posture for this matterabove. Here, probe the trade-off if the user chose a stronger tone than the facts seem to warrant, or a weaker tone than the facts seem to warrant. - Worth naming explicitly: aggressive tone burns the relationship. If you want to keep the business relationship but need to protect the legal position,
measuredis usually the right call.
12. Settlement-communication posture
- Research the settlement-communication protections applicable in the forum (FRE 408 in federal, the state equivalent otherwise). Is this letter a settlement communication that should be protected? Or an assertion of rights that shouldn't be?
- If protected: the draft will include the settlement-communication marker and will be structured so the substance (a discussion of compromise) — not just the label — supports the posture.
- Protection attaches from conduct and context, not merely from labeling. The marker is a belt-and-suspenders choice.
13. Privilege filters
- What's in our internal analysis that must NOT appear in the letter? (Facts we haven't verified, our doubts about our case, strategic reasoning, prior settlement discussions)
- A single badly-worded sentence can waive privilege on related analysis. Be explicit about what stays out.
14. Admission and accord-and-satisfaction risk
- Anything in the letter that the counterparty could later characterize as an admission of fact or liability?
- Does this demand risk inadvertently satisfying (or purporting to accept) a separate claim? (Accord-and-satisfaction: cashing a check marked "payment in full" can end a disputed debt.)
Writing the intake
Slug
[type]-[counterparty-short]-[yyyy-mm]. Confirm uniqueness in ~/.claude/plugins/config/claude-for-legal/litigation-legal/demand-letters/.
~/.claude/plugins/config/claude-for-legal/litigation-legal/demand-letters/[slug]/intake.md
[WORK-PRODUCT HEADER — per plugin config ## Outputs — differs by role; see `## Who's using this`]
# Demand Intake: [title]
**Slug:** [slug]
**Demand type:** [type]
**Drafted by:** [counsel]
**Opened:** [YYYY-MM-DD]
**Status:** intake | ready-to-draft | drafted | sent | closed
**Strategic block:** answered | partial | skipped
**Skipped reason:** [if applicable]
---
## Posture
- **Tone:** [measured / assertive / aggressive — with one-line rationale tied to the relationship and the amount]
- **Response window:** [N days — tied to the claim / contract / protocol]
- **Marking:** [none / without prejudice / without prejudice save as to costs / other — with rationale]
- **Signer:** [name / role — you / client / GC / instructed counsel]
*This is the per-matter posture captured at intake. The draft skill reads from here.*
---
## Parties
- **Sender:** [our entity]
- **Recipient:** [counterparty, entity, address]
- **Recipient audience:** [who reads]
- **Relationship:** [type]
## Triggering event
[What happened, when, evidence]
## Legal / contractual basis
[Provisions, governing law, statutes]
## Desired outcome
[Specific asks in priority order]
## Deadlines
- **External:** [SoL, ongoing harm window]
- **Compliance:** [how long we give them]
## Prior outreach
[History, most recent first]
## Distribution
- **Delivery:** [method]
- **Signer:** [name/role]
- **Copies:** [list]
---
## Strategic (if applicable)
### Leverage & BATNA
[Our power, their likely response]
### Downside tolerance
[Reputational, precedent, regulatory, insurance]
### Tone posture
[relationship-preserving / measured / scorched-earth — with rationale]
### Settlement-communication posture
[Protected or not in the forum — with reasoning. Cite primary source per the applicable rule (FRE 408 or state equivalent).]
### Privilege filters
[What CANNOT appear in the draft]
### Admission / accord-and-satisfaction risk
[Specific risks flagged]
---
## Seed documents
| Doc | Path |
|---|---|
| [underlying contract] | [path or "not shared"] |
| [prior correspondence] | [path or "not shared"] |
| [evidence] | [path or "not shared"] |
---
## Materiality assessment
**Auto-heuristic says:** [material / immaterial — with reasoning]
**User call:** [material / immaterial / TBD at post-send]
Confirm before writing
Show the user the draft intake. Flag anything thin:
Here's the intake. I notice [thin spots]. Before I save, anything to add?
Handoff to drafting
End with:
Intake saved. When ready:
/litigation-legal:demand-draft [slug]
Close with the next-steps decision tree
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.
What this skill does not do
- Draft the letter. That's
demand-draft— the two steps are intentionally separate so counsel can pause for business input, outside counsel consult, or insurance tender before drafting. - Decide whether to send the letter. Some intake sessions end with "actually, don't send — let's negotiate directly." That's a valid outcome; the intake record still has value.
- Run the conflicts check. If the counterparty is a customer or known entity, flag that this should clear conflicts (per
~/.claude/plugins/config/claude-for-legal/litigation-legal/CLAUDE.md) before sending — but the check itself lives in the matter-intake workflow or outside this skill.
FAQ
What does the demand-intake skill do?
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.
How do I install demand-intake?
Run npx skills add https://github.com/anthropics/claude-for-legal --skill demand-intake in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/demand-intake/ (personal) or .claude/skills/demand-intake/ (project).
Which AI agents can use demand-intake?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is demand-intake safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains demand-intake?
It is published by anthropics in anthropics/claude-for-legal, and it is an official skill from the maker of the technology it covers. It has 611 recorded installs.
More from anthropics/claude-for-legal
legal-writing
anthropics/claude-for-legal
Structural feedback on a legal writing draft (memo, brief, paper, exam essay) — organization, analysis depth, clarity, citation form. NEVER rewrites the draft. Use when the user says "feedback on my memo", "read my draft", or "critique my brief".
draft
anthropics/claude-for-legal
First draft of a common clinic document — practice-area templates (asylum applications, eviction answers, protective order petitions, demand letters), jurisdiction-aware formatting, explicitly a starting point requiring student analysis and attorney review. Use when a student needs a first draft of a motion, letter, petition, declaration, or other clinic document.
flashcards
anthropics/claude-for-legal
Generate or drill flashcards for black-letter memorization — Leitner-style buckets, per-subject markdown storage, drill mode with self-assessment. Use when the user says "drill flashcards", "make flashcards from", "quiz me on cards", or wants to memorize rules.
saas-msa-review
anthropics/claude-for-legal
Reference: review of SaaS subscription agreements with attention to the terms that matter most in subscription deals — auto-renewal mechanics, price escalation, data portability, uptime SLAs, and subprocessor rights. Loaded by /commercial-legal:review when a SaaS or subscription agreement is detected.
review
anthropics/claude-for-legal
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.
policy-monitor
anthropics/claude-for-legal
Keep the privacy policy current with practice. Two modes: weekly sweep of saved PIAs, DPA reviews, and triage results to find policy drift; or direct query for a proposed new practice. Use when the user asks "does our policy cover this", "we want to start doing X — does the policy need updating", "run the policy monitor", "policy sweep", or wants to find where the privacy policy no longer matches what the team actually does.
Popular backend & apis skills
find-skills
vercel-labs/skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
entra-app-registration
microsoft/azure-skills
Guides Microsoft Entra ID app registration, OAuth 2.0 authentication, and MSAL integration. USE FOR: create app registration, register Azure AD app, configure OAuth, set up authentication, add API permissions, generate service principal, MSAL example, console app auth, Entra ID setup, Azure AD authentication. DO NOT USE FOR: Key Vault secrets (use azure-keyvault-expiration-audit), general Azure resource security guidance.
google-agents-cli-adk-code
google/agents-cli
This skill should be used when the user wants to "write agent code", "build an agent with ADK", "add a tool", "create a callback", "define an agent", "use state management" — in a project that needs ADK (Agent Development Kit) API patterns and code examples. It provides a quick reference for agent types, tool definitions, orchestration patterns, callbacks, state management, the graph Workflow API, and reference recipes to study. Do NOT use for scaffolding (use google-agents-cli-scaffold) or deployment (use google-agents-cli-deploy).
embedded-captions
heygen-com/hyperframes
Add captions or subtitles to an existing single-subject talking-head video without editing the footage. Use for plain verbatim captions, cinematic captions embedded behind the subject, VFX captions, “炸/特效/酷炫字幕,” or a named identity from the 35-style catalog. Route by visual identity, not by backend engine. The quiet anchor rail is the default; embed every word only when the user explicitly wants a fully cinematic treatment. The workflow runs locally end to end, including transcription and subject matting; split multi-shot footage before applying it.
entra-agent-id
microsoft/azure-skills
Provision Microsoft Entra Agent Identity Blueprints, BlueprintPrincipals, and per-instance Agent Identities via Microsoft Graph, and configure OAuth 2.0 token exchange (fmipath, OBO, cross-tenant) including the Microsoft Entra SDK for AgentID sidecar. USE FOR: Agent Identity Blueprint, BlueprintPrincipal, agent OAuth, fmipath token exchange, agent OBO, Workload Identity Federation for agents, polyglot agent auth, Microsoft.Identity.Web.AgentIdentities. DO NOT USE FOR: standard Entra app registration (use entra-app-registration), Microsoft Foundry agent authoring (use microsoft-foundry).
neon
neondatabase/agent-skills
Overview of Neon, a complete set of cloud backend primitives around Lakebase Postgres: Auth, Object Storage, Functions, the AI Gateway, and Realtime. Start here to choose Neon for undecided login, files, APIs, and LLM calls, set up the CLI or MCP server, and follow the branch-first workflow. Use when building an app or backend on Neon, or when "Neon" or "Lakebase Postgres" is mentioned. Child skill neon-postgres wins for an existing DATABASEURL, SQL, schema, inspect, or search. Child skill neon-auth wins for login, users, sessions, identity routing, and Managed Better Auth setup. Child skill neon-realtime wins for live queries in reactive apps and agents. Also use for object storage, S3, buckets, serverless functions, function triggers, cron, AI gateway, LLM calls, realtime, logs, Loki, Grafana, observability, postgres, database, backend, Claimable Neon, neon.new, or a no-signup database.