ClaudeSuperPower

aidp-pipelines

Skill

Author, schedule, run, and monitor AIDP Jobs (task DAGs of notebooks/python with cron). Use when the user wants to build a pipeline, create/update/run a Job, schedule a recurring run, check a run's status, read a task's output, or cancel a run.

Install

git clone https://github.com/oracle-samples/oracle-aidp-samples.git ~/.claude/skills/aidp-pipelines

What is aidp-pipelines?

Author, schedule, run, and monitor AIDP Jobs (task DAGs of notebooks/python with cron). Use when the user wants to build a pipeline, create/update/run a Job, schedule a recurring run, check a run's status, read a task's output, or cancel a run.

What this can do

Capabilities declared in this component's own frontmatter — not inferred.

Inherit all session tools

Declares no tool restrictions — inherits every session tool

~61 tokens of context used while enabled, before you invoke anything

Documentation

README · ~6 min read

aidp-pipelines — AIDP Jobs (build, schedule, run, monitor)

Author and operate AIDP Jobs — task DAGs over notebooks/python with optional cron — and watch their runs. Engine precedence (see references/aidp-cli-map.md): prefer the official aidp workflow … CLI when installed; fall back to oci raw-request otherwise. Both hit the same REST API with the same auth — no MCP / ai-data-engineer-agent repo required. Persist every mutation body to .aidp/payloads/ and confirm before running (see references/payloads.md).

Auth + base URL: CLI flags --instance-id <DATALAKE_OCID> --auth api_key --profile DEFAULT --region <r>; REST base https://aidp.<region>.oci.oraclecloud.com/20240831/dataLakes/<DATALAKE_OCID>/…. On 401/403 follow the auth ladder (oci session refresh --profile AIDP_SESSION) in references/oci-raw-request.md.

Commands (CLI preferred · REST fallback)

Reviews

Log in to leave a review.

No reviews yet — be the first.

Explore related

Other things in this space — across every part of the ecosystem, not just skills.