qfieldcloud
Skill0 starsChanged 44 days agoMITView on GitHub
Work with QFieldCloud (field data collection with QField) - list projects and files, download the latest field data for QGIS or R, upload a QGIS project, trigger packaging, follow jobs, read collaborators. Use when the user mentions QField, QFieldCloud, field survey / relevés terrain, "données terrain", or syncing a project to tablets.
- Reads credentials
- Installs packages
In this repository24 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- analystSkill
- build-appSkill
- build-websiteSkill
- business-setupSkill
- content-pipelineSkill
- content-writerSkill
- email-assistantSkill
- email-digestSkill
- ksuite-setupSkill
- meeting-prepSkill
- memorySkill
- odooSkill
- plugin-builderSkill
- qgisSkill
- quarto-slidesSkill
- research-leadSkill
- researchSkill
- r-sessionSkill
- schedulerSkill
- scrum-masterSkill
- skill-creatorSkill
- task-managerSkill
- weekly-reviewSkill
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 43
Every output is JSON with success.
- Very specific: line 67
Never overwrite local edits: download into a new or dedicated folder.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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
QFieldCloud
QFieldCloud (MIT, by OPENGIS.ch) synchronizes QGIS projects with the QField mobile app.
AIGORA reaches it through the official CLI (qfieldcloud-sdk), wrapped by
.claude/skills/qfieldcloud/scripts/qfc.py. No MCP server exists for QFieldCloud; the
wrapper is the connector. It works with the hosted service (app.qfield.cloud) and with a
self-hosted server (QFIELDCLOUD_URL in .env).
Setup (if QFIELDCLOUD_TOKEN is missing)
The user does it in the R console (never ask for their password in the chat):
aigora_qfieldcloud_installer() # pip install qfieldcloud-sdk
aigora_qfieldcloud_login() # asks username + password locally, stores only the token in .env
# self-hosted: aigora_qfieldcloud_login("https://qfield.mon-domaine.ch/api/v1/")Then test: python3 .claude/skills/qfieldcloud/scripts/qfc.py list-projects.
Commands
Q=".claude/skills/qfieldcloud/scripts/qfc.py"
python3 $Q status
python3 $Q list-projects
python3 $Q get-project <PROJECT_ID>
python3 $Q list-files <PROJECT_ID>
python3 $Q download-files <PROJECT_ID> data/qfield/<project-name> [--filter "*.gpkg"] [--force-download]
python3 $Q upload-files <PROJECT_ID> <local_project_dir> [--filter "*.gpkg"]
python3 $Q job-trigger <PROJECT_ID> package # prepare the project for QField devices
python3 $Q job-status <JOB_ID>
python3 $Q list-jobs <PROJECT_ID>
python3 $Q collaborators-get <PROJECT_ID>Every output is JSON with success. Destructive or rights-changing commands (delete-,
patch-, collaborators-add/patch/remove, members-, teams-, logout, delta-push) are refused
unless --confirm is added: explain the effect, get an explicit yes, then rerun with --confirm.
Typical workflows
Bring field data back ("récupère les relevés de la semaine"):
list-projects-> find the project;list-files-> see what changed (dates).download-files <id> data/qfield/<name> --filter "*.gpkg".- Offer: open it in QGIS (
qgisskill: add the layer), or analyse in R (sf::st_read("data/qfield/<name>/<file>.gpkg")), or save a copy to the kDrive folder.
Send a project to the field:
- Prepare the QGIS project (ideally with the QFieldSync plugin in QGIS, which handles
offline layers and attachments). For a plain folder upload:
upload-files <id> <dir>. job-trigger <id> package, then polljob-statusuntilfinished.- Tell the user the devices can now synchronize in QField.
Team overview: collaborators-get <id> (read-only). Changing roles needs --confirm.
Rules
- Field data can be personal or sensitive (owners, addresses, protected species): keep it in
data/(git-ignored) or kDrive, never in memory files, logs or kChat messages. - Never overwrite local edits: download into a new or dedicated folder; use
--force-downloadonly after saying what will be replaced. - Uploading replaces the cloud version of those files for every field user: confirm first.
- The token is a credential: never print it.
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.

