Is the Adversarial Analysis skill free?

Yes. The skill itself is free from fedec65/bettercallclaude. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Adversarial Analysis SkillProof Score?

8.0/10 — installs cleanly 4/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 3/5.

How do I install Adversarial Analysis?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Adversarial Analysis with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Adversarial Analysis

Three-agent Swiss legal debate (advocate/adversary/judge) with calibrated risk probabilities -- but full-mode citation verification needs plugin-level MCP servers a bare skill copy won't have.

by fedec65 · fedec65/bettercallclaude

Works with setup

Install — copy the command Download source ↗

Test report

Verdict: Works with setup
Score: 8.0/10
Tested: Jul 14, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 9ebfebb

The repo's own README says 'MCP servers connect automatically, no setup, no API keys required' -- true only when installed through the official Cowork Desktop marketplace; a plain GitHub-clone-and-copy of the skill folder (this protocol's install method) leaves out the plugin-level .mcp.json entirely, so the skill's own citation-verification bar (>95% verified BGE citations) is unreachable and it silently drops to the 'Reduced Mode' the SKILL.md itself defines and discloses.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 4/5
Triggers reliably 5/5
Output vs. baseline 8/10
Docs & honesty 3/5

What Adversarial Analysis does

Structures legal position analysis as an Advocate/Adversary/Judicial three-way debate ending in a probability-weighted Erwaegung-style synthesis, for stress-testing an argument before filing. Triggers on 'stress-test this position' / 'check weaknesses before filing' style requests; explicitly excludes first-pass research and drafting, which belong to sibling skills. Real BGE citation verification depends on hosted MCP servers wired at the plugin level, not inside the skill folder itself, so a standalone skill copy runs in an honestly-disclosed reduced mode.

How to install Adversarial Analysis

git clone https://github.com/fedec65/bettercallclaude.git
cd bettercallclaude
mkdir -p ~/.claude/skills
cp -r bettercallclaude/skills/adversarial-analysis ~/.claude/skills/adversarial-analysis

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Adversarial Analysis

/adversarial-analysis Three-agent Swiss legal debate (advocate/adversary/judge) with calibrated risk probabilities -- but full-mode citation verification needs plugin-level MCP servers a bare skill copy won't have.

It also activates on plain-language prompts like these:

Stress-test my termination defense before we file the appeal
Poke holes in this contract argument like opposing counsel would
Give me a probability-weighted read on how strong this legal position is

Frequently asked questions

Is the Adversarial Analysis skill free?: Yes. The skill itself is free from fedec65/bettercallclaude. SkillProof publishes the install command and an independent test verdict at no cost.
Does Adversarial Analysis work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 14, 2026. Verdict: Works with setup. The repo's own README says 'MCP servers connect automatically, no setup, no API keys required' -- true only when installed through the official Cowork Desktop marketplace; a plain GitHub-clone-and-copy of the skill folder (this protocol's install method) leaves out the plugin-level .mcp.json entirely, so the skill's own citation-verification bar (>95% verified BGE citations) is unreachable and it silently drops to the 'Reduced Mode' the SKILL.md itself defines and discloses.
What is the Adversarial Analysis SkillProof Score?: 8.0/10 — installs cleanly 4/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 3/5.
How do I install Adversarial Analysis?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Adversarial Analysis with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.