read-boxnote
Skill1 starsChanged 2 months agoMITView on GitHub
Convert Box Notes (.boxnote files) into readable Markdown. Use whenever you need to read, search, or quote the society's meeting notes, calendars, event proposals, or member lists — most of the archive is stored as .boxnote (ProseMirror JSON) which is not human-readable as-is. Also builds a full-text index of the whole archive.
In this repository37 other files it gives its agents.
- wsb-data-pipelineSkill
- docx-exportSkill
- harvard-mdxSkill
- humanise-docx-reportSkill
- make-pdfSkill
- bom-builderSkill
- ring-testSkill
- batch-draftSkill
- cold-emailSkill
- cv-intakeSkill
- cv-upgradeSkill
- find-contactSkill
- followupSkill
- humanize-emailSkill
- log-outreachSkill
- outreach-statusSkill
- target-researchSkill
- erc-statusSkill
- log-sessionSkill
- score-auditSkill
- submission-checkSkill
- sumo-statusSkill
- trial-runSkill
- vr-statusSkill
- academic-registerSkill
- aviation-data-sourcesSkill
- business-frameworksSkill
- consultancy-registerSkill
- excel-deliverablesSkill
- forecasting-methodsSkill
- operations-frameworksSkill
- secondary-data-sourcesSkill
- archive-indexSkill
- event-proposalSkill
- meeting-minutesSkill
- captureSkill
- new-scriptSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
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 22
Run from the society root (Scoiety Folders/):
- Very specific: line 40
To read/search the archive: prefer the already-generated _converted/*.md files and _converted/ARCHIVE_INDEX.md.
≈ “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
Reading Box Notes
The society archive is mostly .boxnote files — Box Notes stored as ProseMirror
JSON. They can't be read directly. boxnote_to_text.py (stdlib Python only,
lossless UTF-8) renders them to clean Markdown: headings, bullet/numbered lists,
checkboxes, tables, links, and formatting.
When to use
- You need to read/search/quote any
.boxnote(meeting notes, calendars, proposals, rosters). - Someone added or edited Box Notes and the
_converted/mirror is stale. - You want one searchable file covering the entire archive.
Commands
Run from the society root (Scoiety Folders/):
# One note → screen
python ".claude/skills/read-boxnote/boxnote_to_text.py" "2022 - 2023/Autumn 2022/Meeting #1.boxnote"
# One note → a .md file
python ".claude/skills/read-boxnote/boxnote_to_text.py" "path/to/Note.boxnote" -o out.md
# Convert EVERY .boxnote into a mirror tree under _converted/
python ".claude/skills/read-boxnote/boxnote_to_text.py" --all "."
# Build one master full-text index of every note
python ".claude/skills/read-boxnote/boxnote_to_text.py" --index "." -o "_converted/ARCHIVE_INDEX.md"Normal workflow
- To read/search the archive: prefer the already-generated
_converted/*.mdfiles and_converted/ARCHIVE_INDEX.md. Grep the index to find the note, then open the specific converted file for full context. - After Box Notes change: re-run
--allthen--indexto refresh. - Do not edit files in
_converted/by hand — they're regenerated. Edit the source.boxnotein Box, or a real doc in the term folder.
Notes
- Windows + Python 3.11 confirmed working; no third-party packages needed.
- Output is UTF-8. Terminal (Git Bash) may show
�for smart quotes/bullets — that's a console display quirk only; the written.mdfiles are correct. - Old notes' manual
·bullets and non-breaking spaces are normalized to clean Markdown automatically.
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.

