菜单
Run only the fetch stage (download raw bytes) for the given slugs. Use when the user wants to prime the cache, debug fetch logic, or download upstream bytes without running the full pipeline.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
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-fetch |
| description | Run only the fetch stage (download raw bytes) for the given slugs. Use when the user wants to prime the cache, debug fetch logic, or download upstream bytes without running the full pipeline. |
| argument-hint | <slug>... |
| disable-model-invocation | true |
| allowed-tools | Bash(python -m scripts.pipeline.fetch *) |
Run the fetch-only entrypoint:
python -m scripts.pipeline.fetch $ARGUMENTS
Behavior:
outputs/raw_downloads/<slug>/ (unversioned cache — same upstream bytes serve any schema_version).expected_bytes / expected_sha256 from the spec. Delete outputs/raw_downloads/<slug>/ to force re-fetch.For Kaggle entries with requires_interactive_accept: true, a 403 surfaces as an error pointing at the URL the user must click through in a browser (signed into Kaggle) before retrying. See SKILLS.md "Adding a Kaggle dataset gated behind ToS acceptance" and /raincloud-add-kaggle-tos.
Use /raincloud-build instead when you want the full pipeline, not just the download step. Useful standalone for cache priming or debugging fetch logic.