Agent skill

Legal Test Builder Patrick Munro

by lawve-ai in lawve-ai/awesome-legal-skills

Builds a high-fidelity interactive legal assessment as a single self-contained HTML artifact.

AGPL-3.0Auto-check passedLegal & Compliance

Install Legal Test Builder Patrick Munro

skills CLI
$ npx skills add lawve-ai/awesome-legal-skills --skill legal-test-builder-patrick-munro -a claude-code

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

GitHub CLI
$ gh skill install lawve-ai/awesome-legal-skills legal-test-builder-patrick-munro --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/lawve-ai/awesome-legal-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/legal-test-builder-patrick-munro .claude/skills/legal-test-builder-patrick-munro && 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
legal-test-builder-patrick-munro
GitHub stars
847
Token cost
~2.3k tokens
SKILL.md length
1,092 words
Files
7 (incl. references)
Skills in repo
154
Repo updated
First seen
Licence
AGPL-3.0

At a glance

Builds a high-fidelity interactive legal assessment as a single self-contained HTML artifact.

  • Works in 6 steps: Gather inputs → Design the task stack → Build the HTML → …
  • The user needs to
  • SKILL.md covers When to use, Step 1: Gather inputs, Step 2: Design the task stack and Step 3: Build the HTML, plus 5 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Legal Test Builder Patrick Munro is an agent skill from lawve-ai/awesome-legal-skills. Builds a high-fidelity interactive legal assessment as a single self-contained HTML artifact. Output includes a live countdown timer, contract review tasks with hover-annotated problem clauses, candidate answer textareas, model answers hidden behind reveal blocks, scenario-based legal memo tasks, strategy and function-building questions, and a pre-submission checklist that encodes the marking criteria. Use when the user needs to (1) assess a legal candidate with a realistic timed exercise, (2) train or onboard…

Its SKILL.md is about 2.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files, including reference files (for example `README.md`, `references/contract-design.md` and `references/html-framework.md`).

It sits in Legal & Compliance, covering Contract review, Legal research and HTML artifacts. The repository describes itself as: A curated list of awesome Agent Skills for automating legal work. The licence is AGPL-3.0.

When your agent uses it

  • The user needs to
  • Assess a legal candidate with a realistic timed exercise
  • Onboard junior lawyers using problem sets rather than doctrine
  • Help a candidate prepare for a real take-home assessment they are facing

Example prompts

  • “legal test”
  • “take-home”
  • “mock exam”
  • “/legal-test-builder-patrick-munro”

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. Gather inputs
  2. Design the task stack
  3. Build the HTML
  4. Severity and priority framework
  5. Checklist design
  6. Two-version output

What it can do on your machine

Read from SKILL.md and the folder at commit 045f738. 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

Legal Test Builder Patrick Munro loads about 2.3k tokens when it runs, and up to ~12k if it reads all its reference files. Until then it costs about 259 tokens; SKILL.md has 1,092 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~259
When it runs · the whole SKILL.md, loaded when a task matches
~2.3k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~12k

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 lawve-ai/awesome-legal-skills at commit 045f738, republished under its AGPL-3.0 licence (© lawve-ai). 1,092 words, ~2,269 tokens.

Download SKILL.mdSave it as .claude/skills/legal-test-builder-patrick-munro/SKILL.md (or your agent's skills folder). This skill also uses 6 other files; get the full folder from GitHub.
name
legal-test-builder-patrick-munro
description
Builds a high-fidelity interactive legal assessment as a single self-contained HTML artifact. Output includes a live countdown timer, contract review tasks with hover-annotated problem clauses, candidate answer textareas, model answers hidden behind reveal blocks, scenario-based legal memo tasks, strategy and function-building questions, and a pre-submission checklist that encodes the marking criteria. Use when the user needs to (1) assess a legal candidate with a realistic timed exercise, (2) train or onboard junior lawyers using problem sets rather than doctrine, (3) help a candidate prepare for a real take-home assessment they are facing, (4) build educational materials for law students, in-house teams, or compliance training, or (5) produce scenario-based training modules on specific legal topics. Triggers on "legal test", "take-home", "mock exam", "contract redline exercise", "candidate assessment", "legal training exercise", "practice test", or similar phrasing even when informal.
metadata.author
Patrick Munro
metadata.license
agpl-3.0
metadata.version
2026-04-25

Produces a production-grade interactive HTML legal assessment as a single self-contained file that works offline and renders cleanly in any modern browser.

When to use

  • Preparing a candidate for a real take-home assessment
  • Assessing legal candidates with a realistic, timed exercise that tests judgment rather than doctrine recall
  • Onboarding junior lawyers through scenario-based learning
  • Building legal training modules for in-house teams or client education
  • Law student moot and drafting exercises
  • Compliance or regulatory training where scenario application is the point

Step 1: Gather inputs

Before building, confirm or infer the following. If not specified, make sensible defaults and flag assumptions visibly in the output so the user can correct them.

InputKey questionsDefault if unspecified
RoleWhat position is being tested or trained for?"Legal Counsel"
OrganisationContext for the scenarioFictional company from the library below
Legal domain(s)Contract law, IP, employment, regulatory, M&A, compliance, privacy, etc.Commercial contracts
Governing lawEnglish law, German law, French law, New York law, etc.English law
Test durationTotal time for the assessment3 hours
DifficultyJunior / Mid / Senior / Partner-equivalentMid-level
PurposeCandidate assessment vs. training vs. exam prepCandidate assessment
Number of tasksHow many distinct exercises3-4 tasks
Model answersIncluded (training / prep) or excluded (live exam)Included as reveals

For candidate prep and training: always include model answers as hidden reveals. For live candidate assessment: generate a second "examiner version" that strips the reveals.

Step 2: Design the task stack

A strong 3-hour test uses this structure. Scale task count and timing to the duration.

Task 01: Contract Review and Redline (50-70 min)

The anchor task. Most revealing of practical legal judgment.

  • Draft a realistic 6-10 clause agreement with 5-8 embedded problems
  • Problems should span critical, high, and medium severity
  • Always include at least one missing clause (something not in the contract at all)
  • Include at least one trap clause that looks standard but is not (e.g., a licence-back that launders an overbroad IP assignment)
  • See references/contract-design.md for problem-embedding patterns

Tests reasoning under novelty. Best structured as a scenario with no clean answer.

  • Give a factual scenario with a genuine legal tension
  • Specify the governing law and any constraints
  • The scenario should be novel enough that the candidate cannot recite a textbook answer
  • See references/scenario-design.md for scenario construction patterns
Task 03: Short Analysis (20-35 min)

A focused issue with one problem and one answer. Good for: conflict of interest, regulatory compliance, specific employment or GDPR question, contractual interpretation.

Task 04: Strategy / Function-Building (30-45 min)

Tests seniority and commercial judgment rather than legal knowledge.

  • Classic framing: "You are the first legal hire. It is Day 90. What have you built, what have you deliberately not built, and what keeps you up at night?"
  • Alternative: "Identify the three highest-priority legal risks and how you would address each."
  • See references/strategy-questions.md for templates by role type

Step 3: Build the HTML

Read references/html-framework.md before writing code. It contains:

  • The full CSS design system (tokens, typography, components)
  • The contract annotation pattern with hover tooltips on problem clauses
  • The reveal block component
  • The timer implementation
  • The checklist component
  • Colour and severity conventions
Core architectural rules
  1. Single file: everything inline. No external dependencies except Google Fonts.
  2. Offline-capable: the test must work without internet access once fonts are cached.
  3. Timer: sticky header, shows hours:minutes:seconds. Colour shifts: normal → amber (under 30 min) → red and pulsing (under 10 min).
  4. Contract problems: annotated with data-title and data-body attributes on <span class="problem"> elements. A JS tooltip renders on hover. The annotation is invisible until hovered.
  5. Reveal blocks: model answers hidden by default. Click to reveal. Never auto-open.
  6. Write areas: <textarea class="write-area"> beneath every question. Candidate writes before revealing.
  7. Checklist: final section with clickable items. Use it to encode the marking criteria.
Show full SKILL.md (453 more words)Show less
Content quality rules
  • Contract text must be realistic. Not obviously fake. Use proper defined terms, clause numbering, and recitals where appropriate.
  • Problems must be embedded naturally. The bad clause should read plausibly. A poorly-drafted clause spotted only because it is obviously wrong is a bad test.
  • Model answers must be opinionated. Not "it depends." State a conclusion, justify it, then acknowledge genuine uncertainty where it exists.
  • Traps must be explicitly called out in a clearly styled trap box. Candidates need to understand not just what the problem is but why the instinctive response is wrong.
  • Hook quotes: include one memorable framing sentence per major section. One line that captures the strategic point, styled in a hook box.
  • Gaps must be flagged honestly. If a model answer involves a developing area of law, say so. A gap box signals "this is uncertain; here is how to handle it."

Step 4: Severity and priority framework

Use this consistently across all problem rows and scenario analyses:

SeverityColourDefinition
CRITICALRedExistential to the organisation's mission, business model, or legal position. A lawyer who misses this fails the test.
HIGHAmberSignificant commercial or legal exposure. Should be caught and negotiated.
MEDIUMBlueSuboptimal but not immediately dangerous. Bonus credit for catching it.

In contract tasks, always include at least 2 CRITICAL problems. The candidates who catch both and articulate why they are existential are the ones worth hiring.

Step 5: Checklist design

The pre-submission checklist is the invisible marking rubric. Design it to:

  • Encode what separates a good answer from an excellent one
  • Include at least 2 items about how the candidate engaged (honest about uncertainty, conclusions first, no padding) rather than only what they wrote
  • End with one sentence capturing the philosophy of the role being tested

Step 6: Two-version output

  • For candidate prep or training: build with model answers (reveals included)
  • For live assessment: strip reveals and model answer content, leaving task instructions, contract text, and write areas. Present as a clean "examiner version."

To generate the clean version, remove all .reveal-block divs and .reveal-body content. The .reveal-header can be removed or left as a "Marking notes" placeholder visible only to the examiner version.

Reference files

Read these before building:

  • references/html-framework.md: complete CSS and JS implementation with all component patterns
  • references/contract-design.md: how to design realistic contracts with well-embedded problems
  • references/scenario-design.md: scenario construction for memo and analysis tasks
  • references/strategy-questions.md: strategy question templates by role type

Output format

Present the final HTML file. Note in the summary:

  1. How many tasks, total time budget
  2. How many embedded contract problems and their severity distribution
  3. Whether model answers are included or excluded
  4. Any legal uncertainty flags the candidate or trainer should be aware of

© lawve-ai, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 6 other files (references) in skills/legal-test-builder-patrick-munro of lawve-ai/awesome-legal-skills.

  • SKILL.md
  • LICENSE.txt
  • README.md
  • references/contract-design.md
  • references/html-framework.md
  • references/scenario-design.md
  • references/strategy-questions.md

Open the folder on GitHubat commit 045f738

Compare with similar skills

Legal Test Builder Patrick Munro 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.

Legal Test Builder Patrick Munro compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Legal Test Builder Patrick Munro this skilllawve-ai/awesome-legal-skills847—~2.3kAutomated safety check: PassAGPL-3.0
Finnish Legal Document Reviewakunikkola/claude-for-legal-finland109—~3.4kAutomated safety check: PassMIT
Clause Comparatorrohasnagpal/legal-ai-skills180—~2.7kAutomated safety check: PassMIT
Contract Drafterrohasnagpal/legal-ai-skills180—~3.6kAutomated safety check: PassMIT
Stakeholder Summaryanthropics/claude-for-legal9.6k2 repos~3.3kAutomated safety check: PassApache-2.0
Legal Concept ComprehensionTHUYRan/Legal-Skills-Chinese874—~7.9kAutomated safety check: PassNone

Similar skills

  • Finnish Legal Document Review

    akunikkola/claude-for-legal-finland

    Checks a Finnish legal document, such as a contract, statement, appeal or decision, in eight stages, looking for errors, gaps and risks before it is signed or submitted.

    109 GitHub stars~3.4k tokensUpdated 3 mo ago
    Legal & ComplianceAuto-check passed
  • Clause Comparator

    rohasnagpal/legal-ai-skills

    Compares the same clause or provision across draft rounds, precedents, public agreements or a portfolio and reports what differs in wording and effect.

    180 GitHub stars~2.7k tokensUpdated today
    Legal & ComplianceAuto-check passed
  • Contract Drafter

    rohasnagpal/legal-ai-skills

    Drafts a complete contract from a term sheet, negotiated heads or plain instructions — parties, recitals, definitions, operative clauses, schedules and boilerplate — in a specified posture and…

    180 GitHub stars~3.6k tokensUpdated today
    Legal & ComplianceAuto-check passed
  • Stakeholder Summary

    anthropics/claude-for-legal

    Official

    Translates a contract review into a summary the business stakeholder will actually read.

    9.6k GitHub starsUsed in 2 repos~3.3k tokens
    Legal & ComplianceAuto-check passed
  • Legal Concept Comprehension

    THUYRan/Legal-Skills-Chinese

    Trigger this skill when the user asks to explain, distinguish, unpack, or understand a legal concept.

    874 GitHub stars~7.9k tokensUpdated 1 mo ago
    Legal & ComplianceAuto-check passed
  • Skill Auditor

    aipoch/medical-research-skills

    A comprehensive auditor for any agent skill — including Manus, OpenClaw/ClawHub, Claude, LobeHub, or custom SKILL.md-based skills.

    1.9k GitHub stars~6.9k tokensUpdated 24 days ago
    Legal & ComplianceAuto-check passed

More from lawve-ai/awesome-legal-skills

All 154 skills in this repo
  • Customs Trade Law Onur Kafkas

    lawve-ai/awesome-legal-skills

    U.S. An agent skill from lawve-ai/awesome-legal-skills.

    847 GitHub stars~4.1k tokensUpdated 8 days ago
    Auto-check passed
  • Eu Data Act Oliver Schmidt Prietz

    lawve-ai/awesome-legal-skills

    Practitioner skill for advising on EU Regulation 2023/2854 (Data Act).

    847 GitHub stars~3.9k tokensUpdated 8 days ago
    Auto-check passed
  • Litigation Deadline Calendar

    lawve-ai/awesome-legal-skills

    Calendar litigation and arbitration deadlines from a scheduling order.

    847 GitHub stars~4.3k tokensUpdated 8 days ago
    Auto-check passed
  • Outlook Emails Lawvable

    lawve-ai/awesome-legal-skills

    Read, search, and download emails and attachments from Microsoft Outlook via OAuth2.

    847 GitHub stars~672 tokensUpdated 8 days ago
    Auto-check passed
  • Ambiguity Report

    lawve-ai/awesome-legal-skills

    Turn an interpretive-ambiguity audit of a legal text — contract, statute, regulation, or judicial opinion — into a polished deliverable.

    847 GitHub stars~4.6k tokensUpdated 8 days ago
    Auto-check passed
  • Az Eu Website Privacy Audit

    lawve-ai/awesome-legal-skills

    Audits a website for compliance with Azerbaijan's Law on Personal Data No.

    847 GitHub stars~3.8k tokensUpdated 8 days ago
    Auto-check passed

Questions about Legal Test Builder Patrick Munro

What does Legal Test Builder Patrick Munro do?

Builds a high-fidelity interactive legal assessment as a single self-contained HTML artifact. Legal Test Builder Patrick Munro is an agent skill from lawve-ai/awesome-legal-skills. Builds a high-fidelity interactive legal assessment as a single self-contained HTML artifact.

When should I use Legal Test Builder Patrick Munro?

Legal Test Builder Patrick Munro fits situations like: the user needs to; assess a legal candidate with a realistic timed exercise; onboard junior lawyers using problem sets rather than doctrine; help a candidate prepare for a real take-home assessment they are facing.

How do I install Legal Test Builder Patrick Munro in Claude Code?

Run `npx skills add lawve-ai/awesome-legal-skills --skill legal-test-builder-patrick-munro -a claude-code`. Or copy the skill folder (skills/legal-test-builder-patrick-munro in lawve-ai/awesome-legal-skills) into .claude/skills/legal-test-builder-patrick-munro in your project. Claude Code loads it when a task matches its description.

How do I install Legal Test Builder Patrick Munro in Codex?

Run `npx skills add lawve-ai/awesome-legal-skills --skill legal-test-builder-patrick-munro -a codex`. Or copy the skill folder (skills/legal-test-builder-patrick-munro in lawve-ai/awesome-legal-skills) into .agents/skills/legal-test-builder-patrick-munro in your project. Codex loads it when a task matches its description.

Can I use Legal Test Builder Patrick Munro 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 lawve-ai/awesome-legal-skills --skill legal-test-builder-patrick-munro -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/legal-test-builder-patrick-munro, .gemini/skills/legal-test-builder-patrick-munro, .github/skills/legal-test-builder-patrick-munro and .opencode/skills/legal-test-builder-patrick-munro in your project.

What does Legal Test Builder Patrick Munro need to run?

SKILL.md names no scripts, command-line tools or credentials: Legal Test Builder Patrick Munro is instructions for the agent only.

Does Legal Test Builder Patrick Munro 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 Legal Test Builder Patrick Munro 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 Legal Test Builder Patrick Munro use?

Legal Test Builder Patrick Munro is published under the AGPL-3.0 licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Legal Test Builder Patrick Munro use?

About 2.3k tokens (SKILL.md is roughly 9.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 9.8k tokens, read only when the agent opens those files.

What are the alternatives to Legal Test Builder Patrick Munro?

Skills that share tags, products or a category with Legal Test Builder Patrick Munro: Finnish Legal Document Review (akunikkola/claude-for-legal-finland, 109 stars), Clause Comparator (rohasnagpal/legal-ai-skills, 180 stars), Contract Drafter (rohasnagpal/legal-ai-skills, 180 stars) and Stakeholder Summary (anthropics/claude-for-legal, 9.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Legal Test Builder Patrick Munro?

lawve-ai (a GitHub organization) maintains it in lawve-ai/awesome-legal-skills, which has 847 GitHub stars. The repository holds 154 skills in this directory. The repository was last updated on October 2, 2026.

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