kill-argument SKILL.md skillA

kill-argument from autoconference/autoconference-skill is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add autoconference/autoconference-skill/kill-argument@git:20260924.6751570

Pins git:20260924.6751570 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
autoconference/autoconference-skill
Path
skills/aris/kill-argument/SKILL.md
Versions recorded
1
Latest version
git:20260924.6751570, committed Sep 24, 2026
Size
24,876 bytes
Repository stars
13
License
Apache-2.0

Two-thread adversarial review: a fresh reviewer constructs the strongest 200-word rejection memo, then a second fresh reviewer defends the paper point-by-point and surfaces still-unresolved critical issues. Use when user says "kill argument", "adversarial review", "hostile review", "rebuttal preparation", "reviewer-2 simulation", or before submitting a theory paper that has already passed standard review rounds.

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

# Kill Argument Exercise: Adversarial Attack-Defense Review

> 🔒 **Do not wrap this skill in `/loop`, `/schedule`, or `CronCreate`.** It is
> verdict-bearing — it produces an adversarial accept/reject verdict (attack →
> adjudication). Re-firing it on a wall-clock timer adds no new signal (the
> attack changes only when the *paper* changes). Schedule the *external wait
> that precedes it* — draft stable → then run this **once** before submission.
> See
> [`shared-references/external-cadence.md`](../shared-references/external-cadence.md).

Stress-test the headline claims of a paper against the strongest possible rejection argument: **$ARGUMENTS**

## Why This Exists

Standard score-based reviews (`/research-review`, `/auto-paper-improvement-loop`) tend to produce **balanced** weakness lists.  Each weakness gets ~equal attention, ranked CRITICAL > MAJOR > MINOR.  Empirically, this misses one specific failure mode: the **single most damaging argument** a reviewer would write in a rejection paragraph — the one sentence that, if a senior area chair reads it, kills the paper.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add autoconference/autoconference-skill/kill-argument@sha256:074e7cb2baa97e63

The line at the top of this page pins the label git:20260924.6751570, 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_3h3wspz45tfqwqyd.svg)](https://markdownregistry.com/a/art_3h3wspz45tfqwqyd)

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

Versions

The registry has recorded 1 version of this file, committed on Sep 24, 2026.

versioncommittedcommitsizeaudit
git:20260924.6751570 latest2026-09-24 6751570 24,876 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 (24876 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

autoconference/autoconference-skill · 13 stars · license Apache-2.0 · pushed 2026-11-01 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_3h3wspz45tfqwqyd
GET https://markdownregistry.com/api/v1/resolve?ref=autoconference/autoconference-skill/kill-argument
GET https://markdownregistry.com/api/v1/blob/074e7cb2baa97e63232107940634581520d2c61dcfb62fdd3668d25bb48e9306

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 autoconference/autoconference-skill

AGENTS.md AGENTS.md file
autoconference/autoconference-skill · AGENTS.md
git:20261012.47d7c48 · audit A · 13 stars
CLAUDE.md CLAUDE.md file
autoconference/autoconference-skill · CLAUDE.md
git:20260930.323ad9e · audit B · 13 stars
paper-writing SKILL.md skill
autoconference/autoconference-skill · paper-writing/SKILL.md · Turn gate-passed evidence into a submission-shaped LaTeX paper whose layout, tables, equations, citations, and prose…
git:20261008.34ebde7 · audit A · 13 stars
evidence-preserving-research SKILL.md skill
autoconference/autoconference-skill · research/SKILL.md · Evidence-preserving autonomous research on a computational method. Use in a study repository to run comparable…
git:20261008.34ebde7 · audit B · 13 stars
ablation-planner SKILL.md skill
autoconference/autoconference-skill · skills/aris/ablation-planner/SKILL.md · Use when main results pass result-to-claim (claim_supported=yes or partial) and ablation studies are needed for paper…
git:20260924.6751570 · audit A · 13 stars
analyze-results SKILL.md skill
autoconference/autoconference-skill · skills/aris/analyze-results/SKILL.md · Analyze ML experiment results, compute statistics, generate comparison tables and insights. Use when user says "analyze…
git:20260924.6751570 · audit A · 13 stars
claims-drafting SKILL.md skill
autoconference/autoconference-skill · skills/aris/claims-drafting/SKILL.md · Draft patent claims for an invention. Use when user says "撰写权利要求", "draft claims", "写权利要求书", "claim drafting", or wants…
git:20260924.6751570 · audit A · 13 stars
experiment-bridge SKILL.md skill
autoconference/autoconference-skill · skills/aris/experiment-bridge/SKILL.md · Workflow 1.5: Bridge between idea discovery and auto review. Reads EXPERIMENT_PLAN.md, implements experiment code…
git:20260924.6751570 · audit A · 13 stars
experiment-plan SKILL.md skill
autoconference/autoconference-skill · skills/aris/experiment-plan/SKILL.md · Turn a refined research proposal or method idea into a detailed, claim-driven experiment roadmap. Use after…
git:20260924.6751570 · audit A · 13 stars
figure-spec SKILL.md skill
autoconference/autoconference-skill · skills/aris/figure-spec/SKILL.md · Generate deterministic publication-quality architecture, workflow, and pipeline diagrams from structured JSON…
git:20260924.6751570 · audit A · 13 stars
formula-derivation SKILL.md skill
autoconference/autoconference-skill · skills/aris/formula-derivation/SKILL.md · Structures and derives research formulas when the user wants to 推导公式, build a theory line, organize assumptions, turn…
git:20260924.6751570 · audit A · 13 stars
idea-discovery SKILL.md skill
autoconference/autoconference-skill · skills/aris/idea-discovery/SKILL.md · Workflow 1: Full idea discovery pipeline to go from a broad research direction to validated, pilot-tested ideas. Use…
git:20260924.6751570 · audit A · 13 stars

Every file in autoconference/autoconference-skill

Other files named kill-argument

kill-argument SKILL.md skill
wanshuiyin/auto-claude-code-research-in-sleep · skills/skills-codex/kill-argument/SKILL.md · Two-thread adversarial review: a fresh reviewer constructs the strongest 200-word rejection memo, then a second fresh…
git:20261019.8fdc2d5 · audit A · 18,383 stars
kill-argument SKILL.md skill
wanshuiyin/auto-claude-code-research-in-sleep · skills/kill-argument/SKILL.md · Two-thread adversarial review: a fresh reviewer constructs the strongest 200-word rejection memo, then a second fresh…
git:20261019.8fdc2d5 · audit A · 18,383 stars

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