deck-build
Skill0 starsChanged 4 days agoMITView on GitHub
Build a self-contained editable bento slide file using a verified Bento shell, theme tokens, content, and optional favicon.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- 30XCOMPANY/30x-ai-native-gtm-startertheir own version, first seen Oct 15, 2026
- jammyfu/open-game-skillstheir own version, first seen Oct 11, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- jammyfu/open-game-skills★ 13same name
- 30XCOMPANY/30x-ai-native-gtm-starter★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository6 other files it gives its agents.
- .github/copilot-instructions.mdCopilot instructions
- deck-authorSkill
- deck-qaSkill
- faviconSkill
- site-buildSkill
- theme-extractSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 8
Use scripts/deck-build.mjs to build a standalone .bento.html.
- Distinctive: line 10
Keep all generated content in the user-selected output directory.
- Very specific: line 18
Run node scripts/validate.mjs path/to/deck.bento.html and perform slide-by-slide browser review.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Build a bento deck
Use scripts/deck-build.mjs to build a standalone .bento.html. It fetches the signed Bento Slides manifest, verifies the pinned ECDSA signature and shell SHA-256, then splices a valid bento/slides document into the shell. A previously verified local cache is used only when network access fails.
- Keep all generated content in the user-selected output directory.
- Escape
<in the embedded JSON and verify that the document reads back identically. - For a new deck, do not mint
docIdor collaboration credentials. For an existing deck being restyled, preserve itsdocId. - Build editable text and shapes rather than rasterized slides.
- Match the source: content goes onto the theme's own layouts with source geometry, theme color references, embedded licence-permitted fonts, and PowerPoint-calibrated line placement and spacing. Pick a master with
--variant dark|light|N|nameand a layout per slide with<!-- layout: name -->under a heading. - Font options:
--fonts dir[,dir]adds licensed font folders,--no-font-downloadskips Google Fonts (open-licensed only), and--no-fontsskips embedding. Report every "Font not embedded" line to the user. - Spaced, wrapped bodies become grouped per-paragraph text boxes so gaps match PowerPoint; use
--single-bodywhen the user wants one editable box. Overflowing placeholders grow around their anchor, and long sections paginate. - A custom icon is embedded in the deck shell; Bento may replace the document title during save, so validate the saved title/icon behavior in a browser before making durability claims.
- Run
node scripts/validate.mjs path/to/deck.bento.htmland perform slide-by-slide browser review. When a PowerPoint rendering (PDF export or screenshots) of the source is available, compare it with the deck at the same size for colors, fonts, and positions.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

