メニュー
Run only the extract stage (unpack archives into _workdir/) for the given slugs. Use when the user wants to inspect what the unpack stage produces, or debug a handler complaint about missing files.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Walk through adding a new dataset to sources.json and producing its first build. Use when the user wants to onboard a new upstream source, add a slug to the manifest, or extend the catalog.
Walk through writing a new transform handler under scripts/pipeline/handlers/. Use when the default tighten_types/identity paths can't produce the right shape — row-level JSON parsing, streaming to avoid OOM, multi-output splitting, or VARIANT-from-the-start.
Load a Raincloud dataset via the lightweight Python loader API (`raincloud.load(slug)`). Use when the user wants to read a prepared parquet/vortex artifact, inspect a slug's metadata, or pull a dataset for downstream analysis from cache → mirror → local build.
Push locally-built Raincloud artifacts to a mirror (`scripts.pipeline.publish`). Use when the maintainer wants to upload one or more slugs' parquet/vortex bytes to a configured mirror after a successful build, gated on the snapshot's recorded sha256.
Use when the user asks to compute or refresh per-column statistics for a raincloud dataset — produces `outputs/v1/<slug>/profile.json` for the TUI's detail pane and `list_datasets --inspect`.
Run the full Raincloud pipeline (fetch → extract → parse → transform → write → validate → convert) for one or more dataset slugs. Use when the user asks to build a dataset, rebuild a slug, or process a batch.
| name | raincloud-extract |
| description | Run only the extract stage (unpack archives into _workdir/) for the given slugs. Use when the user wants to inspect what the unpack stage produces, or debug a handler complaint about missing files. |
| argument-hint | <slug>... |
| disable-model-invocation | true |
| allowed-tools | Bash(python -m scripts.pipeline.extract *) |
Run the extract-only entrypoint:
python -m scripts.pipeline.extract $ARGUMENTS
Behavior:
fetch first to make sure raw bytes exist._workdir/<slug>/ — gitignored scratch._workdir/<slug>/ after this runs.Wipe _workdir/<slug>/ to force re-extraction. --clean-workdir on /raincloud-build does this automatically after each successful build.
Use /raincloud-build instead for the full pipeline.