一键导入
visual-audit
Perform adversarial visual audit of Quarto or Beamer slides checking for overflow, font consistency, box fatigue, and layout issues.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Perform adversarial visual audit of Quarto or Beamer slides checking for overflow, font consistency, box fatigue, and layout issues.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | visual-audit |
| description | Perform adversarial visual audit of Quarto or Beamer slides checking for overflow, font consistency, box fatigue, and layout issues. |
| disable-model-invocation | true |
| argument-hint | [QMD or TEX filename] |
Perform a thorough visual layout audit of a slide deck, checking for overflow, font consistency, box fatigue, and spacing issues.
Read the slide file specified in $ARGUMENTS
For Quarto (.qmd) files:
quarto render Quarto/$ARGUMENTSFor Beamer (.tex) files:
Audit every slide for:
OVERFLOW:
FONT CONSISTENCY:
.smaller when spacing would sufficeBOX FATIGUE:
.quotebox used for non-quotationsSPACING:
fig-align: center on plotsLAYOUT:
. . .) for problem→solution moments.positive/.negative semantic colors not used on binary contrastsProduce a report organized by slide:
Follow the spacing-first principle: Priority order for fixes:
Convert a PDF (or any document) to clean markdown so Claude can read it efficiently. Tries Microsoft MarkItDown first; falls back to OpenDataLoader-PDF for complex layouts (multi-column papers, dense tables, math). Use when user says "convert this PDF", "make this document readable", "turn paper.pdf into markdown", "preprocess this document", or before reading any PDF for analysis.
Enforce the replication-protocol.md rule by cross-checking numeric claims in a manuscript against the actual R / Stata / Python outputs. Report PASS/FAIL per claim against tolerance thresholds. Use before submission and before releasing a replication package.
Deep consistency audit of the entire repository infrastructure. Launches 4 parallel specialist agents to find factual errors, code bugs, count mismatches, and cross-document inconsistencies. Then fixes all issues and loops until clean. Use when: after making broad changes, before releases, or when user says "audit", "find inconsistencies", "check everything".
Draft a structured preregistration document (OSF, AsPredicted, or AEA RCT Registry style) from a research spec or free-form study description. Output is a Markdown file with hypotheses, design, sampling plan, analysis plan, exclusions, and inference criteria — annotated with MUST / SHOULD / MAY clarity flags. Use when user says "preregister", "draft a preregistration", "OSF preregistration", "AsPredicted", "AEA RCT registry", "PAP", "preanalysis plan", or before launching an experiment / data collection / analysis on data the analyst has not yet seen. NOT a registry submission tool — produces a document the user uploads to OSF / AsPredicted / AEA themselves.
Adversarial QA workflow comparing Quarto HTML against Beamer PDF benchmark. Iterates between critic (finds issues) and fixer (applies fixes) until APPROVED or max iterations reached.
Comprehensive manuscript review with three modes: single-pass (default), --adversarial critic-fixer loop, and --peer [journal] simulated peer-review pipeline (editor + 2 dispositioned referees + editorial decision, calibrated to a target journal). R&R continuation via --peer --r2/--r3; hostile-editor stress test via --peer --stress. Auto-invokes /review-r + /audit-reproducibility on referenced scripts unless --no-cross-artifact.