boxes
Skill8 starsChanged 10 days agoMITView on GitHub
Create a structured Boxes diagram from a scene or system.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- lulufoo/lulu-boardword for word, first seen Nov 8, 2026
Other versions1 project uses a version of this.
Word for word · 1
- lulufoo/lulu-board★ 8100% same
Edited · 0
None found.
Wrote their own version · 0
None found.
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 repository3 other files it gives its agents.
- mermaidSkill
- sketchSkill
- lulu-board-skillsSkill
The file
We split this skill into the rules it gives an agent
7 rules. About 0 are common, 1 is distinctive, and 6 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.
6
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 22
Run $BOARD_CLI assets. If it fails, stop and report.
- Very specific: line 25
When using an icon, load files["icons.json"].path.
- Very specific: line 39
Use cloud mode only when one of these holds: the user asks to save, keep, or update a cloud diagram, or to search cloud diagrams.
- Very specific: line 41
If login fails or times out, use short-link mode and tell the user why.
- Distinctive: line 42
If the user pastes a viewer URL, load pointers.
- Very specific: line 48
No scene to draw (and not an update): show https://luluboard.app/ and stop.
- Very specific: line 49
Write the BMD Source to .cache/boxes/<name>.bmd.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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
boxes
Define one diagram with the boxes protocol and open it on the public viewer.
Done when a tool url is shown.
CLI
The shared CLI reference defines $BOARD_CLI.
- Load cli before the first
$BOARD_CLIcall of a session.
References
Load what the current write needs.
- Run
$BOARD_CLI assets. If it fails, stop and report. - Load vocab from
files["vocab.md"].path. - Load demo.bmd only when a complete example helps.
- When using an icon, load
files["icons.json"].path.
Author
What to write.
- BMD Source is the
.bmdbody. The file has no identity. - Author one BMD Source string that follows vocab.
- Mint without style. On update, leave those lines unchanged.
Mode
Pick short link or cloud. Short link is the default.
- Use cloud mode only when one of these holds: the user asks to save, keep, or update a cloud diagram, or to search cloud diagrams; the user pastes a
#b:link; this session already created the diagram in cloud mode. Load cloud. - Otherwise use short-link mode.
- If
loginfails or times out, use short-link mode and tell the user why. - If the user pastes a viewer URL, load pointers.
Short link flow
Publish unsigned.
- No scene to draw (and not an update): show
https://luluboard.app/and stop. - Write the BMD Source to
.cache/boxes/<name>.bmd.<name>is a short English name for the diagram. - Run
$BOARD_CLI preview-diagram --file <file>. - Show only the
urlfield and stop. - To change, edit the file and publish again. That creates a new short url.
- To keep, use cloud mode (
#b:).
Open wording
Show the url. One line.
Boundaries
- CLI contract:
$BOARD_CLI --help. - CLI success completes the skill; do not open the URL, drive the viewer, or screenshot the layout unless the user explicitly requests visual verification.
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.

