slide-excellence

Multi-agent slide review (visual, pedagogy, proofreading). Use for comprehensive quality check before milestones.

857 stars

Best use case

slide-excellence is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Multi-agent slide review (visual, pedagogy, proofreading). Use for comprehensive quality check before milestones.

Teams using slide-excellence should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/slide-excellence/SKILL.md --create-dirs "https://raw.githubusercontent.com/pedrohcgs/claude-code-my-workflow/main/.claude/skills/slide-excellence/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/slide-excellence/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How slide-excellence Compares

Feature / Agentslide-excellenceStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Multi-agent slide review (visual, pedagogy, proofreading). Use for comprehensive quality check before milestones.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

SKILL.md Source

# Slide Excellence Review

Run a comprehensive multi-dimensional review of lecture slides. Multiple agents analyze the file independently, then results are synthesized.

## Steps

### 1. Identify the File

Parse `$ARGUMENTS` for the filename. Resolve path in `Quarto/` or `Slides/`.

### 2. Run Review Agents in Parallel

**Agent 1: Visual Audit** (slide-auditor)
- Overflow, font consistency, box fatigue, spacing, images
- Save: `quality_reports/[FILE]_visual_audit.md`

**Agent 2: Pedagogical Review** (pedagogy-reviewer)
- 13 pedagogical patterns, narrative, pacing, notation
- Save: `quality_reports/[FILE]_pedagogy_report.md`

**Agent 3: Proofreading** (proofreader)
- Grammar, typos, consistency, academic quality, citations
- Save: `quality_reports/[FILE]_report.md`

**Agent 4: TikZ Review** (only if file contains TikZ)
- Label overlaps, geometric accuracy, visual semantics
- Save: `quality_reports/[FILE]_tikz_review.md`

**Agent 5: Content Parity** (only for .qmd files with corresponding .tex)
- Frame count comparison, environment parity, content drift
- Save: `quality_reports/[FILE]_parity_report.md`

**Agent 6: Substance Review** (optional, for .tex files)
- Domain correctness via domain-reviewer protocol
- Save: `quality_reports/[FILE]_substance_review.md`

### 3. Synthesize Combined Summary

```markdown
# Slide Excellence Review: [Filename]

## Overall Quality Score: [EXCELLENT / GOOD / NEEDS WORK / POOR]

| Dimension | Critical | Medium | Low |
|-----------|----------|--------|-----|
| Visual/Layout | | | |
| Pedagogical | | | |
| Proofreading | | | |

### Critical Issues (Immediate Action Required)
### Medium Issues (Next Revision)
### Recommended Next Steps
```

## Quality Score Rubric

| Score | Critical | Medium | Meaning |
|-------|----------|--------|---------|
| Excellent | 0-2 | 0-5 | Ready to present |
| Good | 3-5 | 6-15 | Minor refinements |
| Needs Work | 6-10 | 16-30 | Significant revision |
| Poor | 11+ | 31+ | Major restructuring |

Related Skills

visual-audit

857
from pedrohcgs/claude-code-my-workflow

Perform adversarial visual audit of Quarto or Beamer slides checking for overflow, font consistency, box fatigue, and layout issues.

validate-bib

857
from pedrohcgs/claude-code-my-workflow

Validate bibliography entries against citations in all lecture files. Find missing entries and unused references.

translate-to-quarto

857
from pedrohcgs/claude-code-my-workflow

Translate Beamer LaTeX to Quarto RevealJS. Multi-phase workflow with TikZ extraction and QA.

review-r

857
from pedrohcgs/claude-code-my-workflow

Run the R code review protocol on R scripts. Checks code quality, reproducibility, domain correctness, and professional standards. Produces a report without editing files.

review-paper

857
from pedrohcgs/claude-code-my-workflow

Comprehensive manuscript review covering argument structure, econometric specification, citation completeness, and potential referee objections

research-ideation

857
from pedrohcgs/claude-code-my-workflow

Generate structured research questions, testable hypotheses, and empirical strategies from a topic or dataset

qa-quarto

857
from pedrohcgs/claude-code-my-workflow

Adversarial Quarto vs Beamer QA. Critic finds issues, fixer applies fixes, loops until APPROVED (max 5 rounds).

proofread

857
from pedrohcgs/claude-code-my-workflow

Run the proofreading protocol on lecture files. Checks grammar, typos, overflow, consistency, and academic writing quality. Produces a report without editing files.

pedagogy-review

857
from pedrohcgs/claude-code-my-workflow

Run holistic pedagogical review on lecture slides. Checks narrative arc, student prerequisites, worked examples, notation clarity, and deck pacing.

lit-review

857
from pedrohcgs/claude-code-my-workflow

Structured literature search and synthesis with citation extraction and gap identification

learn

857
from pedrohcgs/claude-code-my-workflow

Extract reusable knowledge from the current session into a persistent skill. Use when you discover something non-obvious, create a workaround, or develop a multi-step workflow that future sessions would benefit from.

interview-me

857
from pedrohcgs/claude-code-my-workflow

Interactive interview to formalize a research idea into a structured specification with hypotheses and empirical strategy