lazyslides: Skill for Claude Code

.claude/skills/refine-slides/SKILL.md

refine-slides is a skill for Claude Code from Chrisissorry/lazyslides. It costs 33 tokens per session (637 once invoked), scanned A, original, MIT.

A review and improvement guide for an existing LazySlides presentation, checking its structure, layout variety, content amount, notes, images, and animation.

In plain words
What is it for?
Use it to inspect a deck, validate it, report structural and design problems, and apply approved improvements.
Why use it?
It helps identify crowded slides, repetitive layouts, missing organization, absent speaker notes, and other presentation-quality issues before delivery.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

This is Chrisissorry/lazyslides's own configuration. It tells Claude Code how to work on lazyslides itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything lazyslides configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Chrisissorry/lazyslides. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Chrisissorry/lazyslides/develop/.claude/skills/refine-slides/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Chrisissorry/lazyslides

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.

agentmods badge for refine-slides

README.md
[![agentmods](https://agentmods.dev/badge/skills/chrisissorry/lazyslides/refine-slides/github.svg)](https://agentmods.dev/skills/chrisissorry/lazyslides/refine-slides)
Your own site
<a href="https://agentmods.dev/skills/chrisissorry/lazyslides/refine-slides"><img src="https://agentmods.dev/badge/skills/chrisissorry/lazyslides/refine-slides/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.

agentmods 80×15 button for refine-slides

Your own site · 80×15
<a href="https://agentmods.dev/skills/chrisissorry/lazyslides/refine-slides"><img src="https://agentmods.dev/badge/skills/chrisissorry/lazyslides/refine-slides.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 637 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00033 $0.00637
Opus 5 $0.00016 $0.00318
Sonnet 5 $0.00007 $0.00127
Haiku 4.5 $0.00003 $0.00064

Measured 10d ago against content hash cf9a9a633f8f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

refine-slides 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 10d ago.

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/refine-slides/SKILL.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Refine Slides

You are helping the user improve an existing presentation.

Step 1: Load and Validate

  1. Ask which presentation to refine (list presentations/ folders)
  2. Read the presentation's index.md
  3. Run validation first:
    pnpm run validate
    
  4. Fix any errors before proceeding

Step 2: Structural Analysis

Analyze and report:

  • Slide count — is it appropriate for the estimated duration?
  • Template diversity — are templates varied or repetitive? (e.g., 3+ content slides in a row)
  • Visual rhythm — is there a good mix of text-heavy and visual slides?
  • Section structure — are section dividers used to organize the flow?
  • Notes coverage — which slides are missing speaker notes?
  • Design quality — check against the presentation-design skill anti-patterns:
    • Wall of text (>100 words on a slide)
    • Template monotony (3+ consecutive same template)
    • Missing section dividers in decks >8 slides
    • Generic titles ("Overview", "Details")
    • Fragment overuse (>50% of slides)
    • Missing alt text on images
  • Animation strategy — suggest where fragment, auto_animate, or per-slide transition would improve the narrative

Step 3: Content Review

Check each slide for:

  • Title quality — clear, concise, action-oriented?
  • Bullet density — too many items per slide? (aim for 3-5)
  • Nested list depth — more than 2 levels deep is hard to read
  • Quote length — quotes should be impactful, not paragraphs
  • Image paths — do all referenced images exist?
  • References — are sources properly attributed?

Step 4: Prioritized Suggestions

Present findings as a prioritized list:

High Priority

  • Issues that affect readability or correctness

Medium Priority

  • Template swaps that would improve visual variety
  • Slides that could be split or merged

Low Priority

  • Minor wording improvements
  • Optional enhancements (add speaker notes, add references)

Step 5: Apply Changes

After the user approves specific suggestions:

  1. Apply the changes to index.md
  2. Run pnpm run renumber to update slide comments
  3. Run pnpm run validate to verify

Read the full file on GitHub · 86 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.

  1. 10d ago First seen · 86 lines · 33 tokens per session scan A cf9a9a633f8f

Subscribe to this mod's changes

refine-slides is a skill published in the GitHub repository Chrisissorry/lazyslides (5 stars, last pushed 2mo ago), licensed MIT. It adds 33 tokens to every session and 637 once invoked, about $0.0002 per session on Opus 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 2026-08-31.

Related

Other skills, from other repositories

html-ppt-zhangzara-retro-zine

A neighborhood zine on the disappearing corner shops — portraits, voices, and what a block loses when they close. Built as a decision-grade story deck for community, local readers.

nexu-io/open-design · 49 tokens

html-ppt-zhangzara-studio

A photography studio's portfolio-and-rate deck — the signature work, the process, and the packages that win the brief. Built as a decision-grade design craft deck for prospective clients.

nexu-io/open-design · 47 tokens

motion-frames

A single-frame motion-design composition with looping CSS animations — rotating type ring, animated globe, ticking timer, parallax labels. Renders as a hero video poster you can hand straight to HyperFrames or any keyframe-based exporter. Use when the brief asks for "motion design", "animated hero", "loop", "video…

nexu-io/open-design · 91 tokens

webgl-halftone-drift

A self-contained WebGL2 hero: a flowing field screened through a rotated halftone dot grid into a duotone print aesthetic; move the cursor to bend the drift.

nexu-io/open-design · 44 tokens

webgl-holographic-foil

A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.

nexu-io/open-design · 41 tokens

motion-graphics

A short, design-led motion graphic where motion is the message — kinetic typography, stat count-up, chart/data-viz hit, logo sting / brand lockup, lower-third / callout / social overlay, animated map (highlight regions, connect places, zoom to a location), animated tweet / news-article / headline, webpage / UI…

heygen-com/hyperframes · 139 tokens