Is the Adversarial Claims Reviewer skill free?

Yes. The skill itself is free from LazyIsEfficient/agentic-os. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Adversarial Claims Reviewer SkillProof Score?

9.6/10 — installs cleanly 4/5, triggers reliably 5/5, output vs. baseline 10/10, docs & honesty 5/5.

How do I install Adversarial Claims Reviewer?

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 Claims Reviewer 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 Claims Reviewer

Hostile-referee review of papers/whitepapers that recomputes every equation and number with real scripts.

by LazyIsEfficient · LazyIsEfficient/agentic-os

Works with setup

Install — copy the command Download source ↗

Test report

Verdict: Works with setup
Score: 9.6/10
Tested: Jul 15, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 322adaa

Planted two false claims in a throwaway mini-paper (a swapped sin/cos derivative, and a 40%-relative-improvement headline that SymPy/arithmetic actually put at 23.1%) — a generic review pass praised both as sound, the skill's real INVENTORY-to-REPORT protocol caught both with executed, reproducible scripts and correctly left the one true claim alone. Its own 'Tier discipline' section requires .claude/rules/review-tiers.md and ../findings-ledger/SKILL.md, both siblings outside the skill folder that a plain git-clone-and-cp of just this directory will not bring along.

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 10/10
Docs & honesty 5/5

What Adversarial Claims Reviewer does

Inventories every equation and quantitative claim in a technical document, verifies each exactly as named (never a paraphrase) with deterministic scripts (SymPy/numpy), and classifies VERIFIED/REFUTED/UNVERIFIABLE/VACUOUS. Triggers on requests to check a paper, verify claims, or audit a derivation/benchmark; explicitly declines source-code review, security posture, and prose-quality scoring, which belong to sibling skills.

How to install Adversarial Claims Reviewer

git clone https://github.com/LazyIsEfficient/agentic-os
mkdir -p ~/.claude/skills
cp -r agentic-os/.claude/skills/adversarial-claims-reviewer ~/.claude/skills/adversarial-claims-reviewer

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

Commands — how to trigger Adversarial Claims Reviewer

/adversarial-claims-reviewer Hostile-referee review of papers/whitepapers that recomputes every equation and number with real scripts.

It also activates on plain-language prompts like these:

Can you check if the math in this paper's derivation is correct?
Verify these benchmark numbers in my whitepaper actually add up.
Recompute the equations in this draft and flag anything wrong.

Frequently asked questions

Is the Adversarial Claims Reviewer skill free?: Yes. The skill itself is free from LazyIsEfficient/agentic-os. SkillProof publishes the install command and an independent test verdict at no cost.
Does Adversarial Claims Reviewer work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 15, 2026. Verdict: Works with setup. Planted two false claims in a throwaway mini-paper (a swapped sin/cos derivative, and a 40%-relative-improvement headline that SymPy/arithmetic actually put at 23.1%) — a generic review pass praised both as sound, the skill's real INVENTORY-to-REPORT protocol caught both with executed, reproducible scripts and correctly left the one true claim alone. Its own 'Tier discipline' section requires .claude/rules/review-tiers.md and ../findings-ledger/SKILL.md, both siblings outside the skill folder that a plain git-clone-and-cp of just this directory will not bring along.
What is the Adversarial Claims Reviewer SkillProof Score?: 9.6/10 — installs cleanly 4/5, triggers reliably 5/5, output vs. baseline 10/10, docs & honesty 5/5.
How do I install Adversarial Claims Reviewer?: 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 Claims Reviewer 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.