Menu
Use when creating, configuring, scheduling, or running claude-code or codex jobs/workflows.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Use when writing and deploying an interactive agent (e.g. a LlamaIndex program) as a served Hopsworks deployment.
Use when writing Streamlit or custom Python apps for Hopsworks, deploying from HopsFS or Git, migrating legacy apps off `APP_BASE_URL_PATH`, or managing app routing/readiness, monitoring, and public sharing. Auto-invoke when user wants to create a dashboard, deploy a Python app to Hopsworks, configure app routing/readiness, or access the feature store from an app. Input an app source + env + memory; output a running app and its URL.
Mount or ingest a table from a supported datasource. Mount tables from a datasource as an external feature group or ingest data into a new feature group using DLTHub. Auto-invoke when user works with external data (Snowflake, BigQuery, Redshift, S3, ADLS, GCS, JDBC, SQL, Databricks Unity Catalog, Postgres, MySQL, Oracle, SAP, MongoDB, CRM, REST APIs).
Use when writing Python code that creates, inserts into, or manages tables or feature groups. Auto-invoke when user writes feature pipelines, feature engineering code, or asks about feature group best practices (online vs offline, batching, OOM, materialization, embeddings, statistics).
Use when a Hopsworks job, app, or deployment needs Python libraries that are not in a base environment. Clone a base environment and install requirements or a wheel into the clone. Auto-invoke when the user hits a missing-package error in a job/app/deployment, asks to install custom dependencies, add a pip requirement, install a wheel, or pick which Python environment a workload should run in.
Use when the user asks where something lives in the Hopsworks UI or how to reach a page (Data Sources, Feature Groups, Feature Views, Model Registry, Deployments, Apps, Agents, Jobs, Jupyter, Project Settings). Knowledge skill: the project-scoped sidebar layout and what sits under each section, so you can point users to the right place.
| name | hops-agent-job |
| description | Use when creating, configuring, scheduling, or running claude-code or codex jobs/workflows. |
An agent job is a set of instructions and a coding agent (claude code or codex) to execute them. An agent job can be run on a schedule or on-demand. It is a background agent: it runs autonomously to automate routine tasks (workflow execution, maintenance) rather than serving interactive queries. Like any Hopsworks job, it is automatically containerized and runs in a project environment.
Prefer a deterministic LLM workflow over a fully autonomous agent when the task is predictable. Reach for an agent only when the task is open-ended and not well-defined in advance.
/hopsfs/...).hops job list # confirm state before; verify the job exists after
Two equivalent interfaces:
hops job ... CLI — preferred for one-off creation and scripted operationsproject.get_job_api() Python SDK — preferred from inside a program / notebook / pipeline script that creates and runs the agent job/hopsfs/... which maps to /Projects/<project>/...). User notebooks/scripts in /hopsfs/Users/<name>/... are already there. Local files on your laptop must be uploaded first — use project.get_dataset_api().upload(...).appPath used in the job config is project-relative, NOT absolute. Example: a script at /hopsfs/Users/meb10000/analytics/foo.py in project af is Users/meb10000/analytics/foo.py.An agent job is created and operated like any Hopsworks job (see hops-job for
the full hops job surface). Upload the instructions/entry, create the job, then
run once or schedule it:
# upload the agent's entry/instructions, then create + run
hops job deploy my-agent-job entry.py --type PYTHON --run --wait
# or schedule it (6-field Quartz cron; @daily shorthand also accepted)
hops job schedule my-agent-job "0 0 * * * ?"
hops job logs my-agent-job # see the agent's run output
The coding-agent runtime (claude-code / codex) is selected by the job's environment/entry as configured on the platform — confirm the exact entry/image convention for your cluster rather than assuming flags.
hops job.project.get_job_api() in the same script.