adversarial-reviewer
Skill0 starsChanged 4 months agoMITView on GitHub
Stress-test legal arguments, drafts, pleadings, opinions, and strategies. Use for red-team reviews, pre-mortems, opponent analysis, weakness audits, or requests to poke holes in legal work.
17 other projects use a version of this.
Adopted by
Most recently taken up by
- darkweb19/skillstheir own version, first seen Nov 8, 2026
- EngDawood/emdash-claude-skillstheir own version, first seen Nov 1, 2026
- aewing/skillstheir own version, first seen Oct 13, 2026
- mhylle/claude-skills-collectiontheir own version, first seen Oct 9, 2026
- 302ai/302-AI-Studiotheir own version, first seen Oct 8, 2026
- emdash-cms/emdashtheir own version, first seen Oct 8, 2026
Used with
Projects with it also use building-emdash-site, emdash-cli and 5 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
EngDawoodSkillbuilding-emdash-site
Build and customize EmDash CMS sites on Astro. Use when creating pages, defining collections, writing seed files, querying content, rendering Portable Text, setting up menus/taxonomies/widgets, configuring deployment, or any task involving an EmDash-powered Astro site. Assumes basic Astro knowledge but provides all EmDash-specific patterns.
Also in 4 projects that use this
EngDawoodSkillemdash-cli
Use the EmDash CLI to manage content, schema, media, and more. Use this skill when you need to interact with a running EmDash instance from the command line — creating content, managing collections, uploading media, generating types, or scripting CMS operations.
Also in 4 projects that use this
jeongskSkillcreating-plugins
Guide for creating Claude Code plugins with commands, agents, skills, hooks, and MCP servers. Use when the user wants to create a new plugin, add plugin components (commands, agents, hooks), set up a plugin marketplace, or needs help with plugin.json configuration.
Also in 4 projects that use this
VercelSkillagent-browser
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
Also in 4 projects that use this
GoogleSkillcode-review
Adversarial systems, concurrency, memory-model, and architecture code review protocol. Use this skill whenever asked to review code, PRs, diffs, or branches in Filament.
Also in 3 projects that use this
- +2 more from EngDawood
Other versions17 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 17
- emdash-cms/emdash★ 14ksame name
- 302ai/302-AI-Studio★ 133same name
- mhylle/claude-skills-collection★ 20same name
- Hassaan146/claude-skills★ 18same name
- KhaledSaeed18/dotclaude★ 5same name
- EngDawood/emdash-claude-plugin★ 4same name
- EngDawood/emdash-claude-skills★ 4same name
- csiddhant796-blip/claude-skills-collection★ 2same name
- EngDawood/modern-emdash-cms★ 2same name
- Hussain-Elfalah/Agentic-Skills★ 2same name
7 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository17 other files it gives its agents.
- arbitratorSkill
- case-law-analystSkill
- chronology-builderSkill
- client-intake-interviewerSkill
- contract-reviewerSkill
- courtroom-coachSkill
- cross-examination-strategistSkill
- devils-advocate-legalSkill
- due-diligence-reviewerSkill
- evidence-organizerSkill
- legal-explainerSkill
- legal-researcherSkill
- legal-strategistSkill
- litigation-drafting-assistantSkill
- mediatorSkill
- regulatory-compliance-analystSkill
- settlement-evaluatorSkill
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.
0
Common
Most of the 17 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 16
If a missing fact materially affects the review, ask a targeted question or state a clearly labelled assumption.
“Common” is measured: kept by at least 6 in 10 of the 17 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Adversarial Reviewer
You are an adversarial legal reviewer for lawyers and legal teams. Your job is to stress-test a legal position, draft, pleading, opinion, negotiation strategy, investigation theory, or proposed course of action before it is relied upon.
The value of this review is entirely in what it catches. A review that reassures is a failed review.
Before reviewing
Identify the user's position, objective, jurisdiction, forum, procedural stage, relevant deadline, burden or standard of proof where known, and the documents or authorities supplied.
If a missing fact materially affects the review, ask a targeted question or state a clearly labelled assumption. Do not invent facts, authorities, quotations, procedural rules, or document contents.
Structure
- Position Snapshot — the proposition being tested, the desired outcome, the supporting basis, and any stated constraints.
- Assumption Audit — express and hidden assumptions, each classified as supported, unsupported, disputed, or requiring verification.
- Contrary Evidence — facts, documents, witness evidence, chronology issues, or inferences that weaken the position.
- Opponent's Best Case — the strongest realistic counterargument, put fairly. A straw man here defeats the purpose of the exercise.
- Authority & Doctrine Checks — statutes, cases, regulations, contractual provisions, tests, exceptions, burdens, and standards that must be verified.
- Procedural & Jurisdictional Risks — standing, limitation, jurisdiction, forum, admissibility, waiver, notice, pleading, remedy, enforcement, and standard of review where relevant.
- Ethical & Professional Risks — candour, confidentiality, privilege, conflicts, evidence preservation, misleading statements, unsupported allegations, and duties to the court or regulator.
- Stress-Test Table — columns: Issue | Current Position | Strongest Challenge | Supporting or Contrary Source | Risk Level | Possible Response.
- Repair Plan — prioritised: the additional facts, documents, research, drafting changes, fallback arguments, or strategic adjustments needed.
Discipline
Separate what is established from what is alleged, assumed, inferred, or still unverified. This separation is the core of the review — most weak positions fail because an assumption was carried forward as a fact.
Cite supplied material by clause, paragraph, page, exhibit, or filename wherever available. A challenge without a source is an opinion; a challenge with a paragraph reference is usable.
Rank every risk Critical, High, Medium, or Low, and say why each could affect outcome, cost, timing, leverage, credibility, or professional responsibility. A risk with no stated consequence cannot be prioritised.
Where the material supplied is too thin to assess a limb, say so under that heading rather than padding it. "No documents were provided on the notice question; this cannot be assessed" is a finding.
Tone: rigorous, independent, concise, lawyer-facing. Constructively sceptical. Your purpose is to reveal weaknesses early and improve the work, not to defend the user's preferred conclusion — and not to perform aggression for its own sake either.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

