adversarial-claims-reviewer SKILL.md skillA

adversarial-claims-reviewer from lazyisefficient/agentic-os is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add lazyisefficient/agentic-os/adversarial-claims-reviewer@git:20260716.7c29779

Pins git:20260716.7c29779 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
lazyisefficient/agentic-os
Path
.claude/skills/adversarial-claims-reviewer/SKILL.md
Versions recorded
5
Latest version
git:20260716.7c29779, committed Jul 16, 2026
First version recorded
Jun 11, 2026
Size
6,753 bytes
Repository stars
17
License
MIT

Use when adversarially reviewing a document that makes formal or technical claims — math derivations, physics papers, statistical analyses, benchmark reports, whitepapers. Inventories every equation and quantitative claim, verifies each AS NAMED in the text (never a paraphrase or a neighboring statement), and classifies VERIFIED / REFUTED / UNVERIFIABLE / VACUOUS. Triggers on "check this paper", "verify these claims", "is this derivation right", "review this proof", "audit this benchmark…

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Adversarial Claims Reviewer

You are a hostile referee, not a collaborator. Assume the document contains at least one fatal flaw and hunt for it. You are forbidden from softening language, grading on effort, or crediting polish. A document's status equals its REFUTED + UNVERIFIABLE count — nothing else.

## Core rules

1. **Verify the claim AS NAMED, never a neighbor.** If the text calls a formula "the commutator C[f] = ∂²(Af) − A(∂²f)", first check the formula given IS that commutator before checking anything about its value. The motivating failure: a paper whose "commutator" was actually ∂²(Af) − ∂²f — a different object — and whose appendix "verified" a neighboring true statement while the body asserted the false one. Paraphrases, simplifications, and adjacent truths are how false claims survive review.
2. **Non-evidence.** Formatting quality, LaTeX polish, citation density, length, and confident tone carry zero evidentiary weight. Never mention them as mitigation.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add lazyisefficient/agentic-os/adversarial-claims-reviewer@sha256:4c67d139eab70e5b

The line at the top of this page pins the label git:20260716.7c29779, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_bj2qjm7ovfwtdhu6.svg)](https://markdownregistry.com/a/art_bj2qjm7ovfwtdhu6)

2 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 5 versions of this file, between Jun 11, 2026 and Jul 16, 2026, about one every 9 days.

versioncommittedcommitsizeaudit
git:20260716.7c29779 latest2026-07-16 7c29779 6,753 BA view · diff
git:20260713.e86d2822026-07-13 e86d282 6,743 BA view · diff
git:20260623.d4273122026-06-23 d427312 6,810 BA view · diff
git:20260611.250568e2026-06-11 250568e 6,624 BA view · diff
git:20260611.26e6c0d2026-06-11 26e6c0d 5,792 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (6753 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

lazyisefficient/agentic-os · 17 stars · license MIT · pushed 2026-10-19 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_bj2qjm7ovfwtdhu6
GET https://markdownregistry.com/api/v1/resolve?ref=lazyisefficient/agentic-os/adversarial-claims-reviewer
GET https://markdownregistry.com/api/v1/blob/4c67d139eab70e5b3afaa41f718594d02b07f18a7dc7cb016f64410aa2c7037d

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from lazyisefficient/agentic-os

autoresearch SKILL.md skill
lazyisefficient/agentic-os · .claude/skills/autoresearch/SKILL.md · Run Karpathy-style autoresearch optimization on any content. Generates 50+ variants, scores with a 5-expert simulated…
git:20260716.7c29779 · audit A · 17 stars
browser-testing-with-devtools SKILL.md skill
lazyisefficient/agentic-os · .claude/skills/browser-testing-with-devtools/SKILL.md · Tests in real browsers. Use when building or debugging anything that runs in a browser. Use when you need to inspect…
git:20260716.7c29779 · audit A · 17 stars
code-review-and-quality SKILL.md skill
lazyisefficient/agentic-os · .claude/skills/code-review-and-quality/SKILL.md · Conducts multi-axis code review across correctness, readability, architecture, security, and performance. Use before…
git:20261019.3c64a74 · audit A · 17 stars
codebase-cost-estimator SKILL.md skill
lazyisefficient/agentic-os · .claude/skills/codebase-cost-estimator/SKILL.md · Estimate the full development cost of an existing codebase from lines of code, architectural complexity, and…
git:20260716.7c29779 · audit A · 17 stars
content-ops SKILL.md skill
lazyisefficient/agentic-os · .claude/skills/content-ops/SKILL.md · Auto-assembles a domain-specific expert panel (7–10 experts), scores any content or strategy artifact against a typed…
git:20260716.7c29779 · audit A · 17 stars
content-pipeline SKILL.md skill
lazyisefficient/agentic-os · .claude/skills/content-pipeline/SKILL.md · Non-interactive content-production toolkit: mine quotable moments from podcast RSS feeds and meeting notes, discover…
git:20260716.7c29779 · audit A · 17 stars
conversion-ops SKILL.md skill
lazyisefficient/agentic-os · .claude/skills/conversion-ops/SKILL.md · AI-powered conversion rate optimization: landing page audits, CRO scoring, survey segmentation, and lead magnet…
git:20260716.7c29779 · audit A · 17 stars
data-model-documentation SKILL.md skill
lazyisefficient/agentic-os · .claude/skills/data-model-documentation/SKILL.md · Catalog APIs, persistence models, and message/event payloads into DATA_MODEL.md at the project root. Use after…
git:20261019.a94f2ca · audit B · 17 stars
data-model-verification SKILL.md skill
lazyisefficient/agentic-os · .claude/skills/data-model-verification/SKILL.md · Adversarially verifies DATA_MODEL.md property rows against cited Source files. Use after data-model-documenter when…
git:20260716.7c29779 · audit A · 17 stars
deployment-pipelines SKILL.md skill
lazyisefficient/agentic-os · .claude/skills/deployment-pipelines/SKILL.md · Use when authoring or reviewing CI/CD pipelines — GitHub Actions workflows, reusable workflows, composite actions, OIDC…
git:20260716.7c29779 · audit A · 17 stars
findings-ledger SKILL.md skill
lazyisefficient/agentic-os · .claude/skills/findings-ledger/SKILL.md · Use when recording, tallying, or triaging stochastic review findings — the append-only JSONL ledger where Tier 2…
git:20261019.3c64a74 · audit A · 17 stars
game-balancer SKILL.md skill
lazyisefficient/agentic-os · .claude/skills/game-balancer/SKILL.md · Use when tuning the numbers in a game — economy curves, progression rates, difficulty pacing, drop tables, win/loss…
git:20260716.7c29779 · audit A · 17 stars

Every file in lazyisefficient/agentic-os

Browse by kind, by grade A, or by owner.