open-slide is a React-based slide framework that lets coding agents create presentations from natural-language descriptions. It provides the canvas, scaling, navigation, hot reload, and presentation mode while agents write the slide components. The catalogue skills and instructions support agent-based slide authoring and revision.
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.
npx skills add 1weiho/open-slide --skill slide-authoringgit clone --depth 1 https://github.com/1weiho/open-slideWrote 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.
[](https://agentmods.dev/skills/1weiho/open-slide/slide-authoring)<a href="https://agentmods.dev/skills/1weiho/open-slide/slide-authoring"><img src="https://agentmods.dev/badge/skills/1weiho/open-slide/slide-authoring/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.
<a href="https://agentmods.dev/skills/1weiho/open-slide/slide-authoring"><img src="https://agentmods.dev/badge/skills/1weiho/open-slide/slide-authoring.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00163 | $0.06078 |
| Opus 5 | $0.00081 | $0.03039 |
| Sonnet 5 | $0.00033 | $0.01216 |
| Haiku 4.5 | $0.00016 | $0.00608 |
Grade A, and why
slide-authoring 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 374 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Authoring open-slide pages
This skill is the technical reference for everything that happens inside slides/<id>/index.tsx. It does not own a workflow:
create-slideowns "draft a new deck" — it asks the user scoping questions, then delegates the how to this skill.apply-commentsowns "process inspector markers" — it finds markers and applies edits, but the edits themselves follow the rules here.current-slideresolves deictic references ("this page", "the slide I'm on") to a concreteslideId+pageIndex. Consult it first when the user references the current slide without naming it, then come back here for how to edit it.- Any ad-hoc slide edit (manual tweak, one-off fix) should also consult this skill before touching the file.
When any of those paths reach the point of writing React code for a page, this is the source of truth. Do not duplicate the knowledge below into other skills — link here instead.
Primitive references
Each framework primitive has a full reference file under references/ in this skill — contract, worked examples, and its own anti-patterns. This file keeps only the always-on rules and a short summary per primitive. Read the relevant reference file before using a primitive on a page:
| Primitive | Read before | File |
|---|---|---|
design const + var(--osd-X) tokens |
writing any new slide (default baseline) | references/design-system.md |
Assets + <ImagePlaceholder> |
importing images/videos or leaving a placeholder | references/assets.md |
| Webfonts | loading any non-system font | references/webfonts.md |
useSlidePageNumber() |
rendering a page-number footer | references/page-numbers.md |
<Steps> / <Step> |
staging a page's reveal | references/steps.md |
SlideTransition |
declaring any enter/exit animation | references/transitions.md |
MorphElement + morph |
morphing a shared element across pages | references/morph.md |
Hard rules
- Put the slide under
slides/<kebab-case-id>/. - Entry is
slides/<id>/index.tsx. Images/videos/fonts go underslides/<id>/assets/. - Do not touch
package.json,open-slide.config.ts, or other slides. - Do not add dependencies. Only
react,@open-slide/core, and standard web APIs are available. - A slide is one
index.tsxplusassets/— nothing else. Do not create sibling.tsx/.tsfiles (Card.tsx,components/,helpers.ts, etc.); helper components and constants go insideindex.tsx. Do not createREADME.mdor other prose files either — speaker notes / a talk script belong in thenotesexport (see Speaker notes below), not in a markdown file.
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 374 lines · 163 tokens per session scan A 72856cae99bb
slide-authoring is a skill published in the GitHub repository 1weiho/open-slide (7,459 stars, last pushed yesterday), licensed MIT. It adds 163 tokens to every session and 6,078 once invoked, about $0.0008 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 2026-08-30.
Other skills, from other repositories
tmux
Remote-control tmux sessions for interactive CLIs by sending keystrokes, capturing pane output, and managing terminal multiplexer windows. Enables parallel coding-agent orchestration, background process management, and REPL interaction via sockets. Use when the agent needs to launch, monitor, or coordinate…
notion-to-blog
Transfer a blog post from Notion to the Wasp blog. Fetches content, downloads and optimizes images, and creates a properly formatted MDX file.
channels-setup
Use when a developer wants to build their first CopilotKit Channels agent and get it answering in Slack or Microsoft Teams — "set up a channel", "connect my agent to Slack", "get my agent into Teams", or starting from nothing and wanting a working channel end to end. Covers the whole path: inspecting or scaffolding…
things-mac
Manage Things 3 via the things CLI on macOS (add/update projects+todos via URL scheme; read/search/list from the local Things database). Use when a user asks Otto to add a task to Things, list inbox/today/upcoming, search tasks, or inspect projects/areas/tags.
obsidian
Work with Obsidian vaults (plain Markdown notes) and automate via obsidian-cli. Use when the user asks about notes, vault management, PKM, knowledge base organization, wikilinks, or personal knowledge management in Obsidian.
computer-use
Read and drive native desktop applications through the accessibility layer — list on-screen apps, snapshot one window as a numbered element tree, then click / type / set a value / scroll / drag / run a named action, by element index or by screen coordinates. Use for work in a desktop app rather than a web page. Full…