What is slides.criticize?

A workflow for reviewing lecture slides for factual mistakes and concrete improvements. It considers the slides' audience, teaching goals, visual clarity, and the order in which ideas are presented.

It helps assess slide content, flow, readability, visual hierarchy, pacing, and audience fit, then report ranked improvements.

Slide decks can contain errors, unexplained terms, too much text, or a confusing progression. A structured review helps identify issues that are supported by the material and suggest specific fixes.

slides.criticize — Skill for Claude Code by gpsaggese/helpers

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add gpsaggese/helpers --skill slides.criticize

Clone the repo

git clone --depth 1 https://github.com/gpsaggese/helpers

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/gpsaggese/helpers/slides.criticize/github.svg)](https://agentmods.dev/skills/gpsaggese/helpers/slides.criticize)

Your own site

<a href="https://agentmods.dev/skills/gpsaggese/helpers/slides.criticize"><img src="https://agentmods.dev/badge/skills/gpsaggese/helpers/slides.criticize/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/gpsaggese/helpers/slides.criticize"><img src="https://agentmods.dev/badge/skills/gpsaggese/helpers/slides.criticize.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 13 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 853 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00013	$0.00853
Opus 5.5	$0.00005	$0.00341
Sonnet 5.5	$0.00003	$0.00171
Haiku 4.5	$0.00001	$0.00085

Measured yesterday against content hash 30a4b3f112fc, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

slides.criticize scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/slides.criticize/SKILL.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Goal

Review and criticize a slide deck, or a subset of its slides, given by the user
Identify mistakes and improvements, focusing on factual errors rather than style
Propose concrete, ranked improvements to content, flow, visual clarity, pacing, and audience fit

Workflow

Read the Material

Read .claude/skills/slides.rules.md for the rules that slides must follow
Read the slide deck file passed by the user
- Note the deck title, target audience, and stated learning objectives (if any)
- Read all slides in order to understand the narrative arc
Find the context of the presentation:
- Venue and duration (lecture, conference talk, workshop, etc.)
- Assumed prior knowledge
- Adjacent or prerequisite slide decks

Criticize

Read .claude/skills/text.criticize/SKILL.md for general approaches to review and criticize text
Evaluate along these axes, reporting only issues you are confident about:
- Slide-level clarity:
  - Too much text per slide (exceeds visible time + cognitive load)
  - Unclear titles or takeaways
  - Missing or weak visual hierarchy
  - Jargon or concepts assumed without intro
- Deck flow & narrative:
  - Abrupt transitions between ideas
  - Slides in wrong order (should come earlier/later)
  - Orphaned or tangential slides
  - Missing bridge slides to connect concepts
  - Pacing (too slow intro, rushed conclusion, uneven rhythm)
- Audience fit:
  - Level too high or too low for stated audience
  - Unexplained background assumptions
  - Missing motivation or context for why this matters
- Structure & consistency:
  - Inconsistent formatting or visual style
  - Slides that break the template (if one exists)
  - Missing the mandatory standalone * Roadmap (first slide) or * Summary (last content slide, before * References); see .claude/skills/slides.rules.md ## Roadmap Slide / ## Summary Slide
  - * Roadmap out of sync with the deck's actual # topics (stale after edits), or * Summary restating stale takeaways
  - Speaker notes missing or incomplete
- Timing & scope:
  - Deck too long or too short for the slot
  - Individual slides that will overrun or underrun their time
  - Candidates to expand, collapse, or split
- Engagement & visuals:
  - Slides that rely only on bullet points (no visuals, examples, or storytelling)
  - Diagrams or images that are unclear or misleading
  - Missing opportunities for interaction or questions

Read the full file on GitHub · 89 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

yesterday First seen · 89 lines · 13 tokens per session scan A 30a4b3f112fc

Subscribe to this mod's changes

slides.criticize is a skill published in the GitHub repository gpsaggese/helpers (158 stars, last pushed today), licensed Apache-2.0. It adds 13 tokens to every session and 853 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-11-06.

Design and UX Learning and teaching

slides.criticize next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
slides.criticizegpsaggese/helpers	Skill	158	today	Apache-2.0	A	13	Claude Code
hps-bauhausnexu-io/open-design	Skill	106k	today	Apache-2.0	A	45	Claude Code, Codex
hps-memphis-popnexu-io/open-design	Skill	106k	today	Apache-2.0	A	49	Claude Code, Codex
html-ppt-zhangzara-playfulnexu-io/open-design	Skill	106k	today	Apache-2.0	A	52	Claude Code, Codex
html-ppt-zhangzara-retro-windowsnexu-io/open-design	Skill	106k	today	Apache-2.0	A	51	Claude Code, Codex
html-ppt-zhangzara-scatterbrainnexu-io/open-design	Skill	106k	today	Apache-2.0	A	52	Claude Code, Codex
frontend-slidesnexu-io/open-design	Skill	106k	today	Apache-2.0	A	45	Claude Code, Codex