native-slides

A workflow for creating editable PowerPoint or Google Slides presentations from an HTML design. Each text box, shape, icon, and chart remains separately selectable instead of being one pasted image.

In plain words
What is it for?
Use it to turn an HTML slide design into a native presentation and compare the result with the original layout.
Why use it?
It helps preserve a finished visual design while making the presentation easy to edit later.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/danielrp551/query-plugins/native-slides
Any agent
npx skills add Danielrp551/query-plugins --skill native-slides
Clone the repo
git clone --depth 1 https://github.com/Danielrp551/query-plugins

Made for: Claude Code, Codex.

Per session 147 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,464 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00147 $0.02464
Opus 5 $0.00073 $0.01232
Sonnet 5 $0.00029 $0.00493
Haiku 4.5 $0.00015 $0.00246

Measured yesterday against content hash 6b6c98cb0477, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

native-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 yesterday.

The scan reads SKILL.md. This mod also ships 11 executable files (scripts/build_pptx_gslides.py, scripts/build_pptx_nativo.py, scripts/deck_config.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

native-slides/skills/native-slides/SKILL.md · 156 lines

How it starts

The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Native Slides

Armar láminas nativas y editables que se vean idénticas al diseño hecho antes en HTML e imagen. Nativo significa que cada caja, pill, barra, ícono y párrafo es una forma o un texto de verdad, seleccionable y editable, no una imagen. Un pptx de imágenes se importa a Google Slides como foto y no se puede tocar; el nativo sí.

La regla de oro es que el diseño se cierra primero en HTML con su imagen, y recién después se lleva a nativo iterando hasta que se vea igualito. El HTML es la referencia contra la que todo se mide. Nunca se dibuja el pptx a ojo en python, eso es adivinar y se nota.

Antes de tocar nada, dos preguntas al usuario

Estas dos van SIEMPRE, antes de empezar a diseñar.

  1. La marca. Preguntar si tiene una paleta de colores, un deck de referencia, o una guía de marca (colores, íconos, tipografía) que use normalmente, para seguir ese estilo. Si tiene un deck en pptx, se le pueden extraer los colores directos de las formas (ver reference/html-referencia.md, sección de paleta). Si no tiene nada, se elige una paleta con criterio y se le muestra.
  2. El destino. Preguntar si es para PowerPoint, Google Slides, o los dos. Cambia el emisor y el validador, no el diseño. Siempre nativo.

El flujo, en orden

  1. Diseñar en HTML con su PNG. Cada lámina es un .slide en 16:9 dentro de un HTML autocontenido (fuente embebida en base64, container queries para escalar). Se renderiza a PNG. Puede ser un artifact pero local, nunca subir a claude.ai (se borraría, y es del usuario). Guardarlo en la carpeta del proyecto, no en un temporal. Detalles y trampas del HTML en reference/html-referencia.md.
  2. Confirmar con el usuario que las láminas en HTML están bien. Esta es la puerta. No se pasa a nativo hasta que el usuario diga que el diseño está listo. Es mucho más barato iterar el diseño en HTML que en pptx.
  3. Llevar a nativo, iterando con validación. Recién acá se arma el pptx. Se extrae la geometría del navegador, se emite en el dialecto del destino, y se itera hasta que el render del motor de verdad se vea igual que el HTML y el PNG. Siempre validando, mirando el render con los propios ojos, por el camino robusto y nunca el fácil. Esta parte es larga y repetitiva, así que conviene delegarla a un subagente (ver más abajo).
  4. Entregar. Un pptx por destino. El de PowerPoint y el de Google Slides son archivos distintos, no el mismo, porque los motores no hablan el mismo dialecto.

Read the full file on GitHub · 156 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. yesterday First seen · 156 lines · 147 tokens per session scan A 6b6c98cb0477

Subscribe to this mod's changes

native-slides is a skill published in the GitHub repository Danielrp551/query-plugins (2 stars, last pushed 1mo ago), licensed MIT. It adds 147 tokens to every session and 2,464 once invoked, about $0.0007 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

agent-host-chat-contributions

Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.

microsoft/vscode · 56 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens