skills/12-pedrohcgs-claude-code-my-workflow/dot-claude/skills/visual-audit/SKILL.md
Perform adversarial visual audit of Quarto or Beamer slides checking for overflow, font consistency, box fatigue, and layout issues.
npx skillsauth add brycewang-stanford/Awesome-Agent-Skills-for-Empirical-Research visual-auditInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Perform a thorough visual layout audit of a slide deck.
Read the slide file specified in $ARGUMENTS
For Quarto (.qmd) files:
quarto render Quarto/$ARGUMENTSFor Beamer (.tex) files:
Audit every slide for:
OVERFLOW: Content exceeding slide boundaries FONT CONSISTENCY: Inline font-size overrides, inconsistent sizes BOX FATIGUE: 2+ colored boxes on one slide, wrong box types SPACING: Missing negative margins, missing fig-align LAYOUT: Missing transitions, missing framing sentences, semantic colors
Produce a report organized by slide with severity and recommendations
Follow the spacing-first principle:
tools
Autonomous multi-round research review loop using MiniMax API. Use when you want to use MiniMax instead of Codex MCP for external review. Trigger with "auto review loop minimax" or "minimax review".
tools
Autonomous research review loop using any OpenAI-compatible LLM API. Configure via llm-chat MCP server or environment variables. Trigger with "auto review loop llm" or "llm review".
tools
Autonomous multi-round research review loop using MiniMax API. Use when you want to use MiniMax instead of Codex MCP for external review. Trigger with "auto review loop minimax" or "minimax review".
tools
Autonomous research review loop using any OpenAI-compatible LLM API. Configure via llm-chat MCP server or environment variables. Trigger with "auto review loop llm" or "llm review".