Agent skill · Audited from source
client-intake
skill · anthropics/claude-for-legalApache-2.0 licenceAudited 31 Oct 2026 · source cb488a888d20
Is it safe? Yes — SAFE, grade B (89/100). We read this skill's source at commit cb488a888d20 and found no filesystem, network or shell access and no hard-coded secrets. What it does: 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…
Cite
Cite this page
ModelsAtlas. “client-intake (anthropics/claude-for-legal)”. Retrieved 31 Oct 2026. https://modelsatlas.com/skills/anthropics/client-intake
Trust audit
Audit 0.4.1 · source read 31 Oct 2026
SAFE means nothing in the source contradicts what the skill says it does. Grade B is shared by 16,667 of 17,602 audited skills.
What the source does
- FilesystemNone observedNo reads or writes in the source
- NetworkNone observedNo outbound calls in the source
- ShellNone observedNo commands run in the source
- DependenciesPinnedNothing floats
- SecretsNone foundNo keys in source
Five audit layers
| Layer | What we check | Result | Findings |
|---|---|---|---|
L0 Provenance | Repo owner, licence, archive status, activity | PASS | 0 |
L1 Static source | Secrets, path traversal, supply chain, hidden code | NA | 0 |
L2 Instructions | Prompt injection, authority framing, hidden directives | PASS | 0 |
L3 Inventory | The files and declarations match the source | PASS | 0 |
L4 Sandbox | Run in isolation and watch behaviour | SKIPPED why | 0 |
Gates applied: no behavioural pass.
Findings (0)
No findings at any severity. We re-audit when the source changes.
Audit 0.4.1 · source sha cb488a888d20 · 31 Oct 2026Report an issue or request a re-scan
Provenance
Who published it, and what the verdict is pinned to
- Publisheranthropics GitHub organizationOwner of the repository this skill is read from
- Source folderanthropics/claude-for-legal/legal-clinic/skills/client-intakeThe exact folder we audited
- LicenceApache-2.0As the repository states it
- Commit pinned for this verdictcb488a888d20A new audit runs when the source changes
- Repository statusNot archivedLast push 1 day ago
- Sandboxed runNot runSkills are read, not executed; layer L4 is skipped
What it tells the agent
Full source on GitHub ↗Its 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…
--- 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: Su
Excerpt, first 6,000 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.
Install
Pinned to the audited commit cb488a8
git clone https://github.com/anthropics/claude-for-legal git -C claude-for-legal checkout cb488a888d20
The author documents no install command, so this uses the repository directly. Our verdict covers commit cb488a888d20 only.
Works in
The author has not said which agents this skill supports, and we have not tested it in any.
Audit history
Every audit, every source change
- ✓SAFE B 89 / 100
first audit · source
cb488a888d20
README badge
For maintainers · shows the latest audit
[](https://modelsatlas.com/skills/anthropics/client-intake/)
The badge shows our verdict and grade for this skill, and links back to this page. It changes when the audit does.
Similar skills
obra/superpowers
Use when creating new skills, editing existing skills, or verifying skills work before deployment
mattpocock/skills
A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.
mattpocock/skills
Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.
Add this badge to your README
[](https://modelsatlas.com/skills/anthropics/client-intake/)
<a href="https://modelsatlas.com/skills/anthropics/client-intake/"><img src="https://modelsatlas.com/skills/anthropics/client-intake/badge.svg" alt="ModelsAtlas: SAFE B"></a>
Questions about client-intake
What does the client-intake skill do?
Is client-intake safe to install?
What can client-intake access on my machine?
How current is this page?
Sources
- github.com/anthropics/claude-for-legal/tree/main/legal-clinic/sk — the audited source at commit cb488a888d20 and every finding aboveObserved · 31 Oct 2026
Spotted something wrong? Report a correction · Methodology
Keep going in your AI
Opens with this page as the source. We add nothing else to the prompt.
- What does the client-intake skill do?
- Is client-intake safe to install?
- What can client-intake access on my machine?