agentleFS
hsigstadhsigstad/research-kit/skills/dropbox/SKILL.md

dropbox

Skill0 starsChanged 4 months agoMITView on GitHub

Browse, upload, or download files on Dropbox via rclone. Use when the user wants to share files with collaborators or check what's on Dropbox.

  • Reads credentials

3 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 1

    Distinctive

    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
  1. Very specific:

    When a project's path.py reads PROJECT_DATA from .env, the rclone remote equivalent lives at:

    line 63
  2. Distinctive:

    Always confirm with the user before:

    line 79
  3. Very specific:

    Use --progress for uploads/downloads so the user sees progress.

    line 86

“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Dropbox

Browse, upload, and download files on Dropbox using rclone.

Backing up a pipeline/project artifact (corpus, cache, scraped raw) rather than sharing an ad-hoc file? Use the backup skill — it covers the format (per-file ZSTD vs tar.zst) and location (data/ shared lake vs pipelines/<slug>/) decisions, plus verify + audit steps.

Available remotes

  • bi-dropbox: — BI/work Dropbox. Contains shared coauthor folders and data/ directory.
  • personal-dropbox: — Henrik's personal Dropbox. Parts synced locally to ~/Dropbox.

Common operations

Browse:

rclone lsd <remote>:path          # list directories
rclone ls <remote>:path           # list files with sizes

Upload:

rclone copy /local/path <remote>:destination/ --progress

Download:

rclone copy <remote>:path /local/destination/ --progress

Sync (mirror local to remote):

rclone sync /local/path <remote>:destination/ --progress --dry-run  # preview first

Parsing the request

The user may say things like:

  • /dropbox upload camara-MG.csv to TCEAndreiHenrik
  • /dropbox what's in the data folder?
  • /dropbox download the latest file from ArntzenFivaSigstad

Extract:

  1. Action — browse, upload, download, or sync
  2. Remote — which Dropbox account (guess from context: coauthor folders → bi-dropbox, personal shared folders like TCEAndreiHenrik → personal-dropbox)
  3. Path — remote path and/or local path

Known shared folders

  • bi-dropbox:data/ — shared datasets (TCEs, TSE, etc.)
  • personal-dropbox:TCEAndreiHenrik/ — shared with Andrei Leite (segredo project)
  • Coauthor folders on bi-dropbox follow the pattern {Surname1}{Surname2} (e.g., ArntzenFivaSigstad, ChenChoiSigstad)

Per-project Dropbox roots

When a project's path.py reads PROJECT_DATA from .env, the rclone remote equivalent lives at:

Projectrclone remote
electoral-justicepersonal-dropbox:electoraljustice/ (data under data/, e.g. data/eleicao_suplementar/)
segredopersonal-dropbox:TCEAndreiHenrik/ (coauthor)
deterrencebi-dropbox:ChenChoiSigstad/data/
serasabi-dropbox:AlencarAmoniMarianiSigstad/
procurebi-dropbox:DarcioHenrik/data/

For cross-project shared data under ~/research/data/, see ~/research/data/SYNC_MAP.yaml.

Before destructive operations

Always confirm with the user before:

  • rclone sync (can delete files on remote)
  • Overwriting existing files
  • Uploading large directories

Gotchas

  • Use --progress for uploads/downloads so the user sees progress.
  • Quote paths with spaces: "bi-dropbox:folder with spaces/file.csv"
  • rclone copy does not delete files at destination (safe). rclone sync does (dangerous).

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.