Stats
Actions
Tags
From dataspoke
Manages DataSpoke ingestion sources (UC1) via API: list, inspect, create, edit, delete sources, trigger dry-run and real extractor runs, review run history and emitted datasets.
How this skill is triggered — by the user, by Claude, or both
Slash command
/dataspoke:dataspoke-ingestion [question or action][question or action]This skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Drive Ingestion Control (UC1) through the public API. Acts as a question-answerer about how
Drive Ingestion Control (UC1) through the public API. Acts as a question-answerer about how
ingestion works and, when the user asks, an API writer/launcher. Every call goes through
dataspoke-api; if it reports no access, send the user to /dataspoke:dataspoke-access first.
DATAHUB_MANAGED — synced from DataHub; read-only here (cannot be authored/edited).ACTIVE_CUSTOM_MANAGED — DataSpoke-owned extractor with a recipe + schedule; runnable.PASSIVE — an external ingestor with a declared scope; observed, not run by DataSpoke.| Intent | Call |
|---|---|
List sources (optionally ?mode=…) | dataspoke-api GET /spoke/ingestion/sources |
| Inspect one source | dataspoke-api GET /spoke/ingestion/sources/{id} |
| Create a source | dataspoke-api POST /spoke/ingestion/sources '<json>' |
| Replace / update | `dataspoke-api PUT |
| Delete a source | dataspoke-api DELETE /spoke/ingestion/sources/{id} |
| Dry-run (connection check, no writes) | dataspoke-api POST '/spoke/ingestion/sources/{id}/method/run?dry_run=true' '{}' |
| Real run | dataspoke-api POST /spoke/ingestion/sources/{id}/method/run '{}' |
| Run / event history | dataspoke-api GET /spoke/ingestion/sources/{id}/event |
| Datasets covered by a source | dataspoke-api GET /spoke/ingestion/sources/{id}/datasets |
| Datasets covered by no source | dataspoke-api GET /spoke/ingestion/unmanaged |
| Available credential refs (Editor+) | dataspoke-api GET /spoke/ingestion/secrets |
| Reverse lookup for a dataset | dataspoke-api GET /spoke/common/data/{urn}/attr/ingestion |
ACTIVE_CUSTOM_MANAGED sources, and show the user the
dry-run result before firing the real run.${secret_name__key} placeholders — never inline a plaintext
secret. Discover available refs with GET /spoke/ingestion/secrets.409 INGESTION_SOURCE_READONLY, 409 INGESTION_RUNNING,
409 INGESTION_RUN_NOT_APPLICABLE) and 403 READ_ONLY_ROLE verbatim — do not work around them.…/event (and …/datasets) to confirm completion and emitted datasets;
newly ingested datasets can lag a couple of minutes in DataHub search.npx claudepluginhub selhorys/dataspoke-baseline --plugin dataspokeManage DataSpoke validation slots and generate validation routines for data pipelines. Register/edit confs, post/query results, and author compute code.
Finds dlt sources and connectors for APIs, databases, or files by classifying requests, searching verified sources, and recommending init commands for data pipelines.
Plans new DataHub connectors by classifying source systems, researching them, and generating a _PLANNING.md blueprint with entity mapping and architecture decisions.