Skip to main content
skill CX Codex official · Anthropic

client-intake — Claude Code skill: structured client intake

Runs a structured client intake: practice-area questions, cross-area issue spotting, conflict flags and a formatted case summary.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add anthropics/claude-for-legal --skill client-intake -a claude-code
Open on GitHub

What client-intake does

The skill walks through intake questions for a specific practice area — immigration, housing, family, consumer. While the template runs, it listens for issues outside that area: a housing client mentions immigration status, a consumer client mentions threats from a partner. Those cross-area findings land in the summary as separate items, because whether the clinic handles or refers them is the professor's call, not the skill's.

Output is a formatted case summary with an AI-assisted label, verification prompts and supervision routing. Conflicts get surfaced, not resolved: opposing party names, related parties, positional conflicts all go to professor review. Triage classification — Urgent, Time-sensitive, Standard, May be out of scope — feeds the queue rather than deciding case acceptance.

Everything hangs off ~/.claude/plugins/config/claude-for-legal/legal-clinic/CLAUDE.md, which holds practice areas, intake templates, supervision style and flag triggers. If a guide exists at ~/.claude/plugins/config/claude-for-legal/legal-clinic/guides/<practice-area>.md, its questions and red flags replace the generic defaults. The skill also has to emit a copy-paste-ready /legal-clinic:deadlines --add ... block for every deadline the intake turns up — answer dates, hearings, filing windows, eviction court dates. It never decides whether to take the case; that stays with the student's analysis and the professor's judgment.

What it helps with

  • run a first intake interview from a practice-area template
  • catch an issue from a neighbouring practice area mid-interview
  • raise a conflict of interest for professor review
  • sort a new matter by urgency before it hits the queue
  • pull every deadline out of the conversation into /legal-clinic:deadlines

Example prompts for the agent

  • /legal-clinic:client-intake
  • Start a client intake: housing, landlord sent a notice
  • Write up a new client's situation and flag the deadlines

How to install client-intake

1Skills CLI (Vercel)

npx skills add anthropics/claude-for-legal --skill client-intake -a claude-code

2Manually: put the files in place

~/.claude/skills/client-intake/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/client-intake/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about client-intake

How do I install client-intake in Claude?

Run npx skills add anthropics/claude-for-legal --skill client-intake -a claude-code. The skill lands at ~/.claude/skills/client-intake/SKILL.md.

What does client-intake do?

It runs a structured intake from a practice-area template, spots cross-area issues and conflicts, classifies the matter by urgency and produces a formatted case summary with an AI-assisted label.

Does the skill decide whether to accept the case?

No. It speeds up information gathering and structuring; accepting the case is the student's analysis and the professor's judgment.

Source text

SKILL.md · Apache-2.0
---
name: client-intake
description: >
  Structured intake — practice-area templates, cross-area issue spotting,
  conflict flags, and triage classification. Produces a formatted case summary
  the student analyzes and the professor reviews. Does NOT decide case
  acceptance. Use when starting a new client intake, running an intake
  interview, or writing up a new client's situation.
argument-hint: "[optional: practice area hint]"
---

# /client-intake

1. Load `~/.claude/plugins/config/claude-for-legal/legal-clinic/CLAUDE.md` → practice areas, intake templates, supervision style, flag triggers.
2. Use the workflow below.
3. Route to practice-area template. Listen for cross-area issues throughout.
4. Conflict check flags. Triage classification.
5. Output formatted case summary with AI-assisted label, verification prompts, supervision routing.

```
/legal-clinic:client-intake
```

---

# Client Intake

## Purpose

Intake is one of the biggest bottlenecks in clinics. A student might spend 45 minutes interviewing, another hour writing it up, more time spotting the issues. Meanwhile the waitlist grows.

This skill structures the conversation, produces the write-up, spots issues across practice areas, and flags conflicts — so the student's time goes to analysis, not transcription.

**What it doesn't do:** decide whether to take the case. That's the student's analysis and the professor's judgment. Claude accelerates the information-gathering and structuring, not the lawyering.

## Load context

`~/.claude/plugins/config/claude-for-legal/legal-clinic/CLAUDE.md` → practice areas, intake templates (per practice area if multiple), supervision style, jurisdiction, flag triggers.

## Read the supervisor guide

Check for a practice-area guide at `~/.claude/plugins/config/claude-for-legal/legal-clinic/guides/<practice-area>.md`. If one exists, use its intake questions, red flags, and good-fit criteria instead of the generic defaults below. If one doesn't exist, use the generic intake and note at the end of the intake summary: "This was a generic intake — your supervisor can tailor the questions for your clinic type with `/legal-clinic:build-guide`."

When the intake starts before the practice area is routed (Step 1 of the workflow below), re-check for the guide after routing — the guide path depends on which practice area the intake landed in.

## Workflow

### Step 1: Practice area routing

Which practice area does this intake start in? The client may not know — they know their problem, not the legal category.

> "Tell me what's going on — what brought you to the clinic today?"

From the answer, route to the appropriate intake template. If the clinic handles multiple areas and the problem spans them (housing client mentions immigration status, family client mentions domestic violence), note all relevant areas — cross-area issue spotting is a feature, not a bug.

### Step 2: Practice-area-specific intake

Each practice area asks different questions. Use the template from `~/.claude/plugins/config/claude-for-legal/legal-clinic/CLAUDE.md` for this area. Defaults if none provided:

**Immigration:**
- Current status and how entered
- Any prior applications, removals, encounters with ICE/CBP
- Country conditions relevant to any asylum/withholding claim
- Family members and their statuses
- Criminal history (sensitive — explain why asking)
- Timeline urgency: any pending hearings, deadlines, NTAs

**Housing:**
- Type of housing (private, subsidized, public)
- What happened: notice received, lockout, conditions problem, deposit dispute
- Lease terms and payment history
- Habitability issues (repairs requested, landlord response, documentation)
- Timeline urgency: notice date, court date if any

**Family:**
- Relationship and what's at issue (custody, support, divorce, protection)
- Children involved — ages, current arrangement
- Safety: any violence, threats, fear (handle carefully — see cross-area flags)
- Existing court orders
- Timeline urgency: any hearings scheduled

**Consumer:**
- Type of debt or dispute
- Who's contacting them and how (FDCPA relevance)
- Documentation: contracts, statements, collection letters
- Has anything been filed against them
- Timeline urgency: answer deadlines, garnishment, judgment

### Step 3: Cross-practice-area issue spotting

While running the practice-area template, listen for issues outside that area:

| Client says | Also flags |
|---|---|
| "I'm worried about my immigration status" | Immigration issue — even in a housing intake |
| "My partner [threatening behavior]" | DV / family law / protective order — even in a consumer intake |
| "I can't work because of my injury" | Possible benefits/disability claim |
| "They're taking money from my paycheck" | Garnishment — consumer/employment overlap |
| "The landlord said he'd call ICE" | Housing + immigration + possible retaliation claim |

Note every cross-area issue in the summary. The clinic may handle it, refer it, or both — that's the professor's call. The student should see it.

### Step 4: Conflict check flags

Per whatever conflict-check process `~/.claude/plugins/config/claude-for-legal/legal-clinic/CLAUDE.md` describes. At minimum:

- Opposing party name(s) — does the clinic represent or have represented them?
- Related parties — anyone else the student or clinic might have a conflict with?
- Positional conflicts — is this case asking for something that would hurt another clinic client?

Flag for professor review. Don't resolve the conflict — surface it.

### Step 5: Triage classification

Not a case-acceptance decision — a triage input:

| Classification | Means |
|---|---|
| **Urgent** | Deadline in days, safety issue, irreversible harm imminent |
| **Time-sensitive** | Deadline in weeks, harm ongoing but not immediately irreversible |
| **Standard** | No immediate deadline, can queue normally |
| **May be out of scope** | Issue is outside clinic's practice areas — flag for referral assessment |

### Step 6: Supervision flag check

Per `~/.claude/plugins/config/claude-for-legal/legal-clinic/CLAUDE.md` supervision style and flag triggers. If formal queue or configurable flags are enabled, and a trigger is present (deadline mentioned, DV indicator, immigration status at issue, etc.), note the flag.

### Step 7: Deadline handoff — required deliverable

If the intake surfaces any timeline deadline (answer due, hearing, statute-of-limitations cutoff, cure period, filing window, notice window, ICE check-in, removal hearing, eviction court date, protective order renewal), **emit a copy-paste-ready `/legal-clinic:deadlines --add ...` block as part of the intake output**. This is a required deliverable, not a suggestion — the intake identifies deadlines, and the student shouldn't have to re-transcribe them into the deadline skill.

Format each deadline as a fenced code block the student can copy, with every field pre-populated from the intake:

```
/legal-clinic:deadlines --add
  case=[case slug or client-last-name-keyword]
  type=[response|hearing|statute-of-limitations|discovery|cure-period|filing-window|notice|other]
  description="[one-line description of what is due]"
  due=[VERIFY — student + supervisor compute from triggering event]
  source="[triggering event + statute/rule cite, e.g., 'UD complaint served 2026-05-04, CCP § 1167']"
  owner=[student name]
  warnings=[14,7,3,1]
```

Rules:
- One block per deadline surfaced. Do not combine. Each one will route through the deadlines skill's pre-add duplicate check.
- Leave the `due=` value as `[VERIFY — student + supervisor compute]` when the deadline is jurisdictional (response deadline, SOL, notice window under a specific rule). The deadlines skill will not compute for you; the student + supervisor do the math and update the entry.
- When a date is given in the triggering document (a hearing date on a summons, an ICE check-in date, a renewal deadline on a protective order), put that date in `due=`. When the date is computed (count N days from triggering event), leave the `[VERIFY]` marker.
- If no deadline is surfaced in the intake, omit this section — don't fabricate one.

## Output

```markdown
# Intake Summary: [Client name or ID]

---
[AI-ASSISTED DRAFT — requires student analysis and attorney review]

**Privilege and confidentiality.** This summary is derived from client communications that may be privileged, confidential, or both. It inherits the source's privilege status. Distributing it beyond the privilege circle (including outside the clinic) can waive privilege. Keep it in the clinic's privileged file store, mark it appropriately, and make distribution decisions with your supervisor.
---

**Date:** [date] | **Intake by:** [student] | **Practice area:** [primary + any cross-area]

## Bottom line

[Take the case / Decline because X / Need more info on Y — next step is Z]

## Client's situation (in their words)

[The narrative the client gave, before legal categorization. This is the human story.]

## Legal issues identified

*Every statutory, ordinance, regulatory, rule, or case citation in this section carries a provenance tag (see plugin CLAUDE.md `## Shared guardrails` for the tag vocabulary). `[user provided]` if the supervisor uploaded the text, `[statute / regulator site]` if you fetched it this session from an official source, a research-connector tag (`[CourtListener]`, etc.) if it came from a tool result in this conversation, `[model knowledge — verify]` otherwise. The default is `[model knowledge — verify]`. A supervising attorney who cannot verify a cite against a connector needs to see the tag to know what to check first.*

### Primary ([practice area])
- [Issue 1]: [one line with any cite tagged, e.g., "RLTO §5-12-080 `[model knowledge — verify]`"]
- [Issue 2]: [one line]

### Cross-practice-area flags
- [Other area]: [what the client said that raised it]
  [UNCERTAIN: whether clinic handles this or refers — professor call]

## Key facts

| Fact | Source | Documentation |
|---|---|---|
| [fact] | [client statement / document provided] | [have it / need it] |

## Conflict check

**Opposing party:** [name(s)]
**Related parties:** [any]
**Flag:** [clear / needs conflict check against clinic database]

## Triage

**Classification:** [Urgent / Time-sensitive / Standard / May be out of scope]
**Driving deadline:** [if any — date and what it is]

## Deadlines to log

[One `/legal-clinic:deadlines --add ...` block per surfaced deadline — Step 7.
If none, omit this section.]

## Jurisdictional notes

*Every statute, ordinance, rule, or case citation in this section carries a provenance tag — same vocabulary as `## Legal issues identified`. Default `[model knowledge — verify]`. When no research connector is reachable for this session, record it in the **Sources:** line of the reviewer note (see plugin CLAUDE.md `## Outputs`) — do not emit a standalone banner.*

[State-specific or local-rule-specific issues relevant to this case type, per
CLAUDE.md jurisdiction, with each cite tagged]

## Supervision flags

[If supervision style includes flags: which fired and why. If formal queue:
"QUEUED for [professor]."]

---

## Verification prompts for the student

Before analysis, verify:
- [ ] [Specific fact the intake relies on — confirm with client or documents]
- [ ] [Deadline date — confirm from the actual notice/court document, not client's memory]
- [ ] [Any legal conclusion above is a starting hypothesis — research before relying on it]

## What this summary does NOT do

This summary does not decide whether the clinic takes this case. That's your
analysis and [Professor]'s judgment. It structures what the client told you
so you can spend your time on the analysis instead of the write-up.
```

## Practice-area intake template references

Store practice-area-specific question sets at `references/intake-templates/[area].md`. Cold-start populates these from the professor's intake form(s); if none provided, use the defaults above.

## What this skill does NOT do

- **Decide case acceptance.** Student analyzes, professor decides.
- **Resolve conflicts.** Flags them for the professor.
- **Give advice during intake.** Intake is gathering; advice comes after analysis and professor review.
- **Produce a final document.** The summary is a starting point — the student reads it, corrects anything mischaracterized, and builds the analysis from it.

## 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.

© anthropics · Apache-2.0 · anthropics/claude-for-legal

Similar skills

All skills for Agent setup: memory, context, orchestration →

From the same set118

outline-builder Builds course outline scaffolds from legal notes and syllabi while deliberately refusing to write the rules for you. CX Codex +1 608installs launch-review Reviews a product launch against the team's legal framework and risk calibration, then produces a review memo. Use it with a PRD or launch tracker ticket before shipping. CX Codex +1 606installs written-consent Drafts a unanimous written consent of the board or a committee in your house format, pulls the closest precedent from the consents repository and builds the signatory checklist. CX Codex +1 606installs oss-review Audits project dependencies and SBOMs for copyleft obligations and license conflicts. Prepares a legal memo before shipping binaries, deploying SaaS, or open-sourcing code. CX Codex +1 606installs skills-qa Runs a skill through thirteen design parameters and three legal failure modes, then hands you a verdict before you commit to it. CX Codex +1 605installs demand-received Reads an inbound demand letter, pulls out the key fields, checks it against your matter log, scores how strong the claim is and lays out the response options. CX Codex +1 605installs internal-investigation A reference framework for internal legal investigations from intake to final memo. It tracks evidence gaps, processes documents, and supports work-product privilege. CX Codex +1 605installs customize Updates one part of an AI governance practice profile without repeating the cold-start interview. Use it for risk settings, escalation contacts, registry entries, or workspace paths. CX Codex +1 605installs

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor