deck-qa
Skill0 starsChanged 4 days agoMITView on GitHub
Verify a generated bento deck and site structurally and visually, including every slide and the Pages navigation.
In this repository6 other files it gives its agents.
- .github/copilot-instructions.mdCopilot instructions
- deck-authorSkill
- deck-buildSkill
- faviconSkill
- site-buildSkill
- theme-extractSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 8
Run node scripts/validate.mjs on every generated deck.
- Distinctive: line 11
Check favicon/title in the browser and after a save round-trip.
- Distinctive: line 13
Verify the narrated project demo plays, captions are readable, and runtime is approximately 90 seconds.
≈ “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
Verify the output
- Run
node scripts/validate.mjson every generated deck. - Open the deck in a real browser and review every slide at presentation size. Check clipping, contrast, font fallback, image loading, and visual rhythm. When the source PowerPoint can be rendered, compare matching slides side by side for colors, typefaces, and text and shape positions.
- For the launch tier, verify the presentation link launches the deck. For the full tier, verify the first top-menu item is Slides ↗, opens a new tab, and the deck copy is read-only with no notes.
- Check favicon/title in the browser and after a save round-trip. Report limitations if Bento updates the shell.
- Validate site links, mobile layout, and deployment workflow. Do not claim a browser or Pages deployment check unless it actually ran.
- Verify the narrated project demo plays, captions are readable, and runtime is approximately 90 seconds.
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.

