AgentSkillsCN

qa-quarto

采用对抗式问答流程，将Quarto HTML与Beamer PDF进行基准对比。在批评者发现问题与修正者实施修复之间反复迭代，直至获得“通过”评价，或达到最大迭代次数。

SKILL.md
--- frontmatter
name: qa-quarto
description: 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.
disable-model-invocation: true
argument-hint: "[LectureN, e.g., Lecture1]"
allowed-tools: ["Read", "Grep", "Glob", "Write", "Edit", "Bash", "Task"]

Adversarial Quarto vs Beamer QA Workflow

Compare Quarto HTML slides against their Beamer PDF benchmark using an iterative critic/fixer loop.

Philosophy: The Beamer PDF is the gold standard. The Quarto translation must be at least as good in every dimension.

Workflow

code
Phase 0: Pre-flight → Phase 1: Critic audit → Phase 2: Fixer → Phase 3: Re-audit → Loop until APPROVED (max 5 rounds)

Hard Gates (Non-Negotiable)

GateCondition
OverflowNO content cut off
Plot QualityInteractive charts >= static plots
Content ParityNo missing slides/equations/text
Visual RegressionQuarto >= Beamer in all dimensions
Slide CenteringContent centered, no jumping
Notation FidelityAll math verbatim from Beamer

Phase 0: Pre-flight

  1. •Locate Beamer (.tex/.pdf) and Quarto (.qmd/.html) files
  2. •Check freshness (re-render if QMD newer than HTML)
  3. •Verify TikZ SVGs if applicable

Phase 1: Initial Audit

Launch the quarto-critic agent to compare Beamer vs Quarto comprehensively. Report saved to quality_reports/[Lecture]_qa_critic_round1.md.

Phase 2: Fix Cycle

If not APPROVED, launch quarto-fixer agent to apply fixes (Critical → Major → Minor), re-render, and verify.

Phase 3: Re-Audit

Re-launch critic to verify fixes. Loop back to Phase 2 if needed.

Iteration Limits

Max 5 fix rounds. After that, escalate to user with remaining issues.

Final Report

Save to quality_reports/[Lecture]_qa_final.md with hard gate status, iteration summary, and remaining issues.