From bg-superpowers
Use when building or modifying an xlsx → JSON → engine data pipeline. Templates the pipeline (xlsx reader → schema-validated JSON → typed TS/Python import) and adds a diff job that runs on xlsx change.
How this skill is triggered — by the user, by Claude, or both
Slash command
/bg-superpowers:data-pipeline-builderThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
> Status: v0.1 — minimum viable. Full skill (project-specific templates) lands in Phase 2.
Status: v0.1 — minimum viable. Full skill (project-specific templates) lands in Phase 2.
Trigger files: any build_*.py / build_*.ts that reads xlsx, or new *.xlsx → *.json dataflow being designed.
Trigger words: "convert the xlsx", "build features", "regenerate the data", "the xlsx changed".
xlsx_path → list[dict]. No engine imports. Pure data extraction.data/v<version>/<name>.json. Never overwrites a prior version (see versioned-design-doc-keeper).A diff job (scripts/diff-pipeline-output.sh) runs after the pipeline and shows:
If the diff is non-empty, surface it to the user before committing the new JSON.
build_features_from_sources.py + build_indexes.py).data/v<version>/, never to a flat data/.data/v<version>/, surface changes.rules-version-auditor — pipeline output is one of the three sources audited.build_features_from_sources.py reads maps/sources/*.xlsx, returns list of hex feature dicts.maps/data/<version>/features.json.versioned-design-doc-keeper.bg-superpowers:rules-version-auditor checks pipeline output is consistent with xlsx and code.bg-superpowers:versioned-design-doc-keeper ensures output paths are versioned.superpowers:test-driven-development for pipeline test design — write a failing test against expected output before adding a new column.npx claudepluginhub taojiastanford/bg-superpowers --plugin bg-superpowersSearches MemPalace before answering questions about past work, people, projects, or prior decisions. Returns verbatim stored content instead of guessing from model memory.
Guides Payload CMS config (payload.config.ts), collections, fields, hooks, access control, APIs. Debugs validation errors, security, relationships, queries, transactions, hook behavior.
Implements vector databases with Pinecone, Weaviate, Qdrant, Milvus, pgvector for semantic search, RAG, recommendations, and similarity systems. Optimizes embeddings, indexing, and hybrid search.