Official agent skill

Ramp

by anthropics in anthropics/claude-for-legal

Student semester onboarding — clinic procedures, tool walkthrough, practice exercises before real cases.

OfficialApache-2.0Auto-check passed

Install Ramp

skills CLI
$ npx skills add anthropics/claude-for-legal --skill ramp -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install anthropics/claude-for-legal ramp --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/anthropics/claude-for-legal.git skills-src && mkdir -p .claude/skills && cp -r skills-src/legal-clinic/skills/ramp .claude/skills/ramp && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
ramp
GitHub stars
9.6k
Used in
3 other repos
Token cost
~2k tokens
SKILL.md length
1,071 words
Files
1
Skills in repo
147
Repo updated
First seen
Licence
Apache-2.0

At a glance

Student semester onboarding — clinic procedures, tool walkthrough, practice exercises before real cases.

  • Works in 4 steps: Check… → Use the walkthrough below. → Walk through: clinic context (from… → …
  • A new clinic student says onboard me
  • SKILL.md covers Purpose, Load context, The walkthrough and /ramp --card, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Ramp is an agent skill from anthropics/claude-for-legal, published by the product's own GitHub organization. Student semester onboarding — clinic procedures, tool walkthrough, practice exercises before real cases. Reads the handbook the professor uploaded at setup and teaches it interactively. Use when a new clinic student says "onboard me", "I'm new to the clinic", "getting started", or at the start of each semester; pass --card for the one-page reference.

Its SKILL.md is about 2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: A suite of plugins for legal workflows. The licence is Apache-2.0.

When your agent uses it

  • A new clinic student says onboard me
  • Im new to the clinic
  • Getting started
  • At the start of each semester

Example prompts

  • “onboard me”
  • “m new to the clinic”
  • “getting started”
  • “/ramp”

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Check ~/.claude/plugins/config/claude-for-legal/legal-clinic/CLAUDE.md is set up. If placeholders: "Ask [professor] to run…
  2. Use the walkthrough below.
  3. Walk through: clinic context (from handbook) → commands → practice exercises (fake intake, practice draft, research roadmap) →…
  4. card: generate the one-page reference card.

What it can do on your machine

Read from SKILL.md and the folder at commit 4a6c651. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Ramp loads about 2k tokens when it runs. Until then it costs about 89 tokens; SKILL.md has 1,071 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~89
When it runs · the whole SKILL.md, loaded when a task matches
~2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from anthropics/claude-for-legal at commit 4a6c651, republished under its Apache-2.0 licence (© anthropics). 1,071 words, ~1,972 tokens.

Download SKILL.mdSave it as .claude/skills/ramp/SKILL.md (or your agent's skills folder).
name
ramp
description
Student semester onboarding — clinic procedures, tool walkthrough, practice exercises before real cases. Reads the handbook the professor uploaded at setup and teaches it interactively. Use when a new clinic student says "onboard me", "I'm new to the clinic", "getting started", or at the start of each semester; pass --card for the one-page reference.
argument-hint
[--card for the one-page reference]

/ramp

  1. Check ~/.claude/plugins/config/claude-for-legal/legal-clinic/CLAUDE.md is set up. If placeholders: "Ask [professor] to run /legal-clinic:cold-start-interview first."
  2. Use the walkthrough below.
  3. Walk through: clinic context (from handbook) → commands → practice exercises (fake intake, practice draft, research roadmap) → verification habits.
  4. --card: generate the one-page reference card.
/legal-clinic:ramp
/legal-clinic:ramp --card

Ramp: Semester Onboarding

Purpose

Every semester, the clinic loses its entire workforce and rebuilds from scratch. New students need to learn procedures, case management, filing conventions, and practice-area basics before they're useful. Traditionally that takes weeks of reading PDFs and asking the professor the same questions every semester.

This skill is the guided walkthrough. It reads what the professor uploaded during cold-start — the handbook, the filing guides, the local rules — and teaches it interactively, with practice exercises so students try the tools in a low-stakes setting before a real client is on the line.

Audience: students. Professors don't run this (they run /cold-start-interview).

Load context

~/.claude/plugins/config/claude-for-legal/legal-clinic/CLAUDE.md → clinic profile, practice areas, jurisdiction, handbook path, supervision style, practice-area templates.

If that file is missing or still has placeholders: "The clinic hasn't been set up yet. Ask [supervising professor] to run /cold-start-interview first."

The walkthrough

Opening

Welcome to [clinic name]. I'm going to walk you through how this clinic works and how to use these tools — about twenty minutes, and you can pause anytime. By the end you'll have run a practice intake, drafted a practice document, and you'll know what to do when you get your first real case.

One thing up front: everything I generate is a starting point, not a final answer. You do the analysis. [Professor] reviews your work [per supervision style]. I handle the formatting and the first draft so you spend your time on the lawyering, not on writing "Dear Judge" for the twentieth time.

Part 1: This clinic (5 min)

Read from ~/.claude/plugins/config/claude-for-legal/legal-clinic/CLAUDE.md and the ingested handbook. Cover, interactively:

  • Practice areas — what the clinic handles, what it doesn't (and where to refer if someone walks in with an out-of-scope issue)
  • Clients — who they are, what they're facing, languages
  • Jurisdiction — which courts, which judges, what the local quirks are
  • Case management — how cases are tracked, where files live, what a well-documented case looks like
  • Supervision — how review works in this clinic (per the supervision style in CLAUDE.md). Be specific: "Before anything goes to a client or a court, [it goes in the review queue / you check with Professor X / etc.]"

Don't lecture — check understanding. "So if a client comes in with an eviction notice but also mentions they're undocumented, what do you do?" (Answer: both issues get noted in intake; the immigration question may need a referral or a flag to the professor, depending on the clinic's scope.)

Part 2: The commands (5 min)

Walk through each command the student will actually use:

CommandWhen you use itWhat you get
/client-intakeClient interviewFormatted case summary with issues spotted, conflict flags, triage
/draft [doc type]Need a first draft of a common documentPractice-area template filled from case notes — starting point, not final
/memoNeed to analyze a case internallyIRAC-format memo with research gaps flagged
/research-start [issue]Starting legal researchRoadmap: statutes to check, case law areas, search terms — leads, not authoritative cites
/status [audience]Updating someone on a caseSummary tailored to client / professor / court
/client-letter [type]Routine correspondenceAppointment confirm, doc request, status update from templates

For each: what it does, what it explicitly doesn't do, what the student verifies before relying on it.

Show full SKILL.md (495 more words)Show less
Part 3: Practice exercises (8-10 min)

Low-stakes. Fake client. Real tools.

Exercise 1 — Practice intake:

Here's a fake client scenario: [practice-area-appropriate hypo — e.g., for a housing clinic, "Maria got a 3-day notice to quit last Tuesday. She's two months behind on rent after losing her job. The apartment has had a broken heater since November. She has two kids."]

Run /client-intake and interview me as if I'm Maria. I'll answer as Maria would. At the end, look at the case summary it produces — what issues did it spot? Did it catch the habitability defense?

Debrief: what the intake caught, what the student should have probed deeper on, what gets flagged for the professor.

Exercise 2 — Practice draft:

Using Maria's intake, run /draft eviction-answer. You'll get a first draft.

Read it. What's right about it? What's wrong? What would you change before showing it to [Professor]?

The point: the draft is competent but not final. The student learns to read critically, not accept.

Exercise 3 — Research roadmap:

Run /research-start "habitability defense to eviction in [state]". You'll get a roadmap — statutes, case law areas, search terms.

None of those citations are verified. That's on purpose. Pick one statute from the roadmap and tell me how you'd verify it's current and applies here.

The point: /research-start is a starting place, not a citation. The student still does the research.

Part 4: Verification habits (2 min)

The habits that matter:

  • Every output is a starting point. If it went to a client or a court without you reading it critically, something went wrong.
  • Verify every citation before it goes in anything. /research-start gives leads, not authorities.
  • Check jurisdiction-specific details. The plugin knows your state from setup, but local court quirks change — double-check against current local rules.
  • When uncertain, it says so. If an output has a [UNCERTAIN: ...] flag, that's a prompt to research or ask the professor, not to delete the flag and move on.
  • [Supervision reminder per CLAUDE.md style] — what gets reviewed before it goes out, and how.
Closing

That's it. You've run an intake, drafted a document, and built a research roadmap. Your first real case will feel similar, except the client is real and the professor is reading your work.

The one-page reference card: /ramp --card

/ramp --card

Generate the one-page student reference card per the one-page card spec. Contents:

  • The commands (table from Part 2, condensed)
  • What Claude can help with / what it can't (starting points yes, final work product no, authoritative citations no)
  • Verification habits (the bullets from Part 4)
  • Who to ask when stuck (professor name from CLAUDE.md)

Printable. One page. Hand it out on day one.

What this skill does NOT do

  • Replace the professor's orientation. It covers procedures and tools; the professor covers judgment, strategy, and the things you only learn by watching someone good do it.
  • Teach substantive law. Practice-area orientation, not a doctrinal course.
  • Certify the student as ready. The professor decides when a student takes a real case.

© anthropics, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in legal-clinic/skills/ramp of anthropics/claude-for-legal.

Open the folder on GitHubat commit 4a6c651

Used in 3 other repositories

We found 3 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 3 other GitHub owners. This page covers the copy in anthropics/claude-for-legal, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Ramp next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Ramp compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Ramp this skillanthropics/claude-for-legal9.6k3 repos~2kAutomated safety check: PassApache-2.0
Manim Video Productionbrowser-use/video-use28k6 repos~3kAutomated safety check: PassMIT
Logseq Review Workflow Evallogseq/logseq45k—~1kAutomated safety check: PassAGPL-3.0
Baoyu URL To Markdownsdyckjq-lab/llm-wiki-skill2.5k2 repos~3.2kAutomated safety check: PassNone
DeepTutor CLIHKUDS/DeepTutor41k—~2.8kAutomated safety check: PassApache-2.0
Obsidian CLIAtmosphere/atmosphere3.8k13 repos~795Automated safety check: PassApache-2.0

Similar skills

  • Manim Video Production

    browser-use/video-use

    Produces math and technical explainer videos with Manim Community Edition: concept animations, equation derivations, algorithm walkthroughs and data stories.

    28k GitHub starsUsed in 6 repos~3k tokens
    Media & CreativeAuto-check passed
  • Compare two revisions of the Logseq logseq-review-workflow skill by running the same review prompt against isolated before and after skill snapshots, collecting both outputs, and producing a…

    45k GitHub stars~1k tokensUpdated today
    Knowledge ManagementAuto-check passed
  • Baoyu URL To Markdown

    sdyckjq-lab/llm-wiki-skill

    Fetch any URL and convert to markdown using Chrome CDP. An agent skill from sdyckjq-lab/llm-wiki-skill.

    2.5k GitHub starsUsed in 2 repos~3.2k tokens
    Knowledge ManagementAuto-check passed
  • DeepTutor CLI

    HKUDS/DeepTutor

    Teaches the agent to set up and run DeepTutor from the command line: chat and capabilities, knowledge bases, partners, memory, sessions, notebooks and the server or Web app.

    41k GitHub stars~2.8k tokensUpdated yesterday
    EducationAuto-check passed
  • Obsidian CLI

    Atmosphere/atmosphere

    Interact with Obsidian vaults using the Obsidian CLI to read, create, search, and manage notes, tasks, properties, and more.

    3.8k GitHub starsUsed in 13 repos~795 tokens
    Knowledge ManagementAuto-check passed
  • AI Engineering Placement Quiz

    rohitg00/ai-engineering-from-scratch

    Runs a 10-question quiz across five areas to place a learner in the AI Engineering from Scratch curriculum, so they skip what they already know.

    66k GitHub stars~2k tokensUpdated today
    EducationAuto-check passed

More from anthropics/claude-for-legal

All 147 skills in this repo
  • Legal Clinic Client Intake

    anthropics/claude-for-legal

    Official

    Structures a legal clinic client intake interview and produces a case summary with cross-area issue spotting, conflict flags and triage classification.

    9.6k GitHub starsUsed in 3 repos~3.2k tokens
    Auto-check passed
  • Supervisor Review Queue

    anthropics/claude-for-legal

    Official

    Holds student work in a queue for a legal clinic professor to approve, edit-then-approve or return before anything reaches clients or courts.

    9.6k GitHub starsUsed in 3 repos~1.1k tokens
    Auto-check passed
  • Tabular Document Review

    anthropics/claude-for-legal

    Official

    Builds a review grid with one row per document and one column per data point, each cell cited to a verbatim quote, built for M&A diligence and other batch reviews.

    9.6k GitHub starsUsed in 3 repos~4.3k tokens
    Auto-check passed
  • Product Launch Legal Review

    anthropics/claude-for-legal

    Official

    Runs a category-by-category legal review of a product launch from a PRD or tracker ticket, calibrated to your team's framework, and writes a review memo in house format.

    9.6k GitHub starsUsed in 2 repos~5k tokens
    Auto-check passed
  • Legal Skills Registry Browser

    anthropics/claude-for-legal

    Official

    Searches watched registries for community legal skills, shows matches with descriptions and offers the full SKILL.md before anything is installed.

    9.6k GitHub starsUsed in 2 repos~620 tokens
    Auto-check passed
  • Contract Renewal Tracker

    anthropics/claude-for-legal

    Official

    Shows which contracts renew soon and when notice must be sent by, working from a maintained renewal register, and warns about missed cancellation windows.

    9.6k GitHub starsUsed in 2 repos~3.1k tokens
    Auto-check passed

Questions about Ramp

What does Ramp do?

Student semester onboarding — clinic procedures, tool walkthrough, practice exercises before real cases. Ramp is an agent skill from anthropics/claude-for-legal, published by the product's own GitHub organization. Student semester onboarding — clinic procedures, tool walkthrough, practice exercises before real cases.

When should I use Ramp?

Ramp fits situations like: A new clinic student says onboard me; im new to the clinic; getting started; at the start of each semester.

How do I install Ramp in Claude Code?

Run `npx skills add anthropics/claude-for-legal --skill ramp -a claude-code`. Or copy the skill folder (legal-clinic/skills/ramp in anthropics/claude-for-legal) into .claude/skills/ramp in your project. Claude Code loads it when a task matches its description.

How do I install Ramp in Codex?

Run `npx skills add anthropics/claude-for-legal --skill ramp -a codex`. Or copy the skill folder (legal-clinic/skills/ramp in anthropics/claude-for-legal) into .agents/skills/ramp in your project. Codex loads it when a task matches its description.

Can I use Ramp in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add anthropics/claude-for-legal --skill ramp -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ramp, .gemini/skills/ramp, .github/skills/ramp and .opencode/skills/ramp in your project.

What does Ramp need to run?

SKILL.md names no scripts, command-line tools or credentials: Ramp is instructions for the agent only.

Does Ramp access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Ramp safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Ramp use?

Ramp is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Ramp use?

About 2k tokens (SKILL.md is roughly 7.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Ramp?

Skills that share tags, products or a category with Ramp: Manim Video Production (browser-use/video-use, 28k stars), Logseq Review Workflow Eval (logseq/logseq, 45k stars), Baoyu URL To Markdown (sdyckjq-lab/llm-wiki-skill, 2.5k stars) and DeepTutor CLI (HKUDS/DeepTutor, 41k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Ramp?

anthropics (a GitHub organization, an official publisher) maintains it in anthropics/claude-for-legal, which has 9,629 GitHub stars. The repository holds 147 skills in this directory. The repository was last updated on September 29, 2026.

Source: anthropics/claude-for-legal on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.