paper-claim-auditlisted

> **Fallback（本整合包补充）**：若 `mcp__codex__codex` 不可用，按本包 `skills/shared-references/reviewer-adapter.md` 的降级链适配（CLI → 零上下文子智能体/子会话 → 新对话人工中转）；本 skill 是 verdict 类审计，同模型降级评审只可给出 FAIL/WARN，不得作为 PASS 依据（见 acceptance-gate.md）。 # Paper Claim Audit: Zero-Context Evidence Verification > 🔒 **Do not wrap this skill in `/loop`, `/schedule`, or `CronCreate`.** It is > verdict-bearing — it judges paper-to-evidence fidelity with a deliberately > zero-context fresh reviewer. Re-firing that verdict on a wall-clock timer adds > no new signal (it changes only when the *paper or results* change). Schedule > the *external wait that precedes it* — paper draft ready → then audit > **once**. See > [`shared-references/external-cadence.md`](../shared-references/external-cadence.md). Verify that every claim in the paper matches raw evidence for: **$ARGUMENTS** ## Why This Exists The executor writes experiments AND writes the paper. It "knows" what the results should be. This creates confirmation bias: - Rounding 84.7% up to 85.3% - Reporting best seed instead of average - Citing metrics from a different experiment config - Claiming "improves by 15%" when the delta is actually 12.8% A **fresh reviewer with zero prior context** catches these because it has no expectations — it just compares paper text vs raw files. ## How This Differs From Other Audit Skills | Skill | Question it answers | |-------|-------------------| | `/experiment-audit` | Is the experiment code honest? (fake GT, normalization fr