paper-adversarial-reviewlisted
Install: claude install-skill zernie/paperlint
<!-- vigiles:sha256:2da081a03ae7fee3 compiled from skills/paper-adversarial-review/SKILL.md.spec.ts -->
# paper-adversarial-review — be the reviewer who wants to reject it
> **Which review skill?** `paper-adversarial-review` (you are here) = one hostile reviewer, fast defect
> hunt. `pc-panel-review` = the whole PC (N independent lenses incl. an artifact-runner) + a chair
> meta-review — the real pre-submission GATE, run LAST; its **venue-fit mode** is the one-reviewer
> CFP-fit score (formerly `venue-review-sim`). Reach for an atom (this, or venue-fit mode) for a quick
> spot-check; run the panel for the decision.
## Run me
🔴 FIRST, before any other step:
```
node .claude/skills/paper-pipeline/scripts/announce.mjs paper-adversarial-review <paper-dir>
```
An advisory pass cannot be observed failing — silence is both its error state and its normal
state — so starting is an event, and events get written down.
Purpose: catch what a real peer reviewer will hit, while it's still fixable. Peer review is
**read, not run** — reviewers judge the *text, figures, and reported numbers*, rarely execute code.
So the paper must be self-contained and airtight on its face. This skill simulates the skeptical
reviewer and returns an actionable critique.
## How to run it
Prefer a **separate model as the reviewer** (e.g. Fable via a subagent) so it's not the author
grading itself. Give the reviewer the full paper text (Read the `.tex`/`.md`/PDF) and the target
venue + paper type (short/f