Is the Adversarial Case Builder skill free?

Yes. The skill itself is free from wanshuiyin/Anti-Autoresearch. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Adversarial Case Builder SkillProof Score?

7.2/10 — installs cleanly 4/5, triggers reliably 5/5, output vs. baseline 5/10, docs & honesty 4/5.

How do I install Adversarial Case Builder?

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 Case Builder 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 Case Builder

Evidence-bound rejection memo for research papers via cross-model review

by wanshuiyin · wanshuiyin/Anti-Autoresearch

Works with setup

Install — copy the command Download source ↗

Test report

Verdict: Works with setup
Score: 7.2/10
Tested: Jul 17, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 3b593b4

⚠ The author changed this skill after we tested it. The verdict below describes the version we ran on Jul 17, 2026; it's queued for a re-test.

The real engine is two fresh cross-model Codex (gpt-5.6-sol) reviewer threads plus an evidence ledger, neither of which was available here, so the skill-versus-baseline delta is unmeasured. Its deterministic anti-slop gate does work: run on a synthetic claims.json it correctly flagged and dropped a dangling [C999] citation and a phantom objection while keeping the verbatim-span-anchored point, landing at disposition partial_case. A single-folder install leaves the skill's references and the adjudicator tool behind, so it only truly runs from inside the cloned repo.

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 5/10
Docs & honesty 4/5

What Adversarial Case Builder does

Synthesizes the single strongest evidence-bound case to reject a research paper, drawn only from a span-anchored claims ledger and the other auditors' confirmed findings, then defends it point by point. Runs two fresh cross-model Codex reviewer threads and a deterministic anchor gate that drops any accusation not tied to a real claim or finding. Runs last in the anti-autoresearch pipeline and emits an info-only memo that carries no verdict weight.

How to install Adversarial Case Builder

git clone https://github.com/wanshuiyin/Anti-Autoresearch
mkdir -p ~/.claude/skills
cd Anti-Autoresearch && cp -r skills/adversarial-case-builder ~/.claude/skills/adversarial-case-builder

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

Commands — how to trigger Adversarial Case Builder

/adversarial-case-builder Evidence-bound rejection memo for research papers via cross-model review

It also activates on plain-language prompts like these:

write the strongest evidence-bound case to reject this paper
build a rejection memo an area chair might raise against this
find the killer objection against this paper's central claims

Frequently asked questions

Is the Adversarial Case Builder skill free?: Yes. The skill itself is free from wanshuiyin/Anti-Autoresearch. SkillProof publishes the install command and an independent test verdict at no cost.
Does Adversarial Case Builder work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 17, 2026. Verdict: Works with setup. The real engine is two fresh cross-model Codex (gpt-5.6-sol) reviewer threads plus an evidence ledger, neither of which was available here, so the skill-versus-baseline delta is unmeasured. Its deterministic anti-slop gate does work: run on a synthetic claims.json it correctly flagged and dropped a dangling [C999] citation and a phantom objection while keeping the verbatim-span-anchored point, landing at disposition partial_case. A single-folder install leaves the skill's references and the adjudicator tool behind, so it only truly runs from inside the cloned repo.
What is the Adversarial Case Builder SkillProof Score?: 7.2/10 — installs cleanly 4/5, triggers reliably 5/5, output vs. baseline 5/10, docs & honesty 4/5.
How do I install Adversarial Case Builder?: 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 Case Builder 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.