archive-index
Skill1 starsChanged 2 months agoMITView on GitHub
Refresh and use the searchable index of the entire society archive. Use to get a fast overview of everything the society has ever done, or to locate which note/year/term discusses a topic before reading it in detail. Regenerates _converted/ and ARCHIVE_INDEX.md from the raw Box Notes.
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
- event-proposalSkill
- meeting-minutesSkill
- read-boxnoteSkill
- captureSkill
- new-scriptSkill
The file
Files
Archive Index
Keeps the archive readable and searchable so the president never has to open raw
.boxnote files or hold four years of history in their head.
What it produces
_converted/— a Markdown mirror of every.boxnote, same folder layout._converted/ARCHIVE_INDEX.md— one file containing the full text of every note, section-separated by source path. Grep this to find anything fast.
Refresh (run after Box Notes are added or edited)
From the society root (Scoiety Folders/):
python ".claude/skills/read-boxnote/boxnote_to_text.py" --all "."
python ".claude/skills/read-boxnote/boxnote_to_text.py" --index "." -o "_converted/ARCHIVE_INDEX.md"Office documents (Word/Excel — e.g. Google Drive exports)
2022–2025 live in Box Notes; 2025–26 arrived as a Google Drive export of .docx/
.xlsx. office_to_md.py mirrors those into _converted/ and builds an index
(PDFs/images/video are inventoried, not converted):
python ".claude/skills/archive-index/office_to_md.py" "2025-2026 google drive" \
--outdir "_converted/2025-2026 google drive" \
--index "_converted/DRIVE_2025-2026_INDEX.md"The 2025–26 detail (team minutes, ~20 event proposals, feedback sheets, research
drafts) is greppable in _converted/DRIVE_2025-2026_INDEX.md.
Use it to answer questions
- Locate: grep
_converted/ARCHIVE_INDEX.mdfor the topic/event/name/year.grep -in "hackathon\|escape room\|budget" "_converted/ARCHIVE_INDEX.md" - Read in full: open the specific
_converted/<year>/<term>/<note>.mdthat the index pointed to, for dates/attendees/decisions/outcomes. - Cite: reference the converted file path so the user can click through.
Good first-overview queries
- Recurring events across years (workshops, competitions, trips, socials).
- Which budgets were approved vs. rejected (search
budget,approv,reject). - Committee rosters per year (search
President,Secretary,Working Group). - Venues and external contacts reused (search
lab,functions room, company names).
Pair this with the archive-historian agent for a written, cited synthesis
rather than raw grep output. Respect rules/data_privacy.md when quoting.
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.

