← ClaudeAtlas

datalisted

Search the data catalog, variable dictionary, and data linkages for datasets, variables, or data sources. Use when the user asks about available data, what variables exist, or how datasets connect across projects.
hsigstad/research-kit · ★ 0 · Data & Documents · score 75
Install: claude install-skill hsigstad/research-kit
# Data Catalog Lookup Search across the workspace's data documentation to find datasets, variables, and cross-project data linkages. ## Finding the workspace root The workspace root contains `CLAUDE.md` and subdirectories `projects/`, `pipelines/`, `data_catalog/`, `research/`. If the current working directory is inside a project or pipeline, search upward to find the root. For example, if you're in `projects/deterrence/`, the root is two levels up. Use `git rev-parse --show-toplevel` or search upward for `CLAUDE.md` with `research/rules/workspace.md` alongside it. Store the resolved root as `$ROOT` for the paths below. ## Where to look Search these files in order of relevance: 1. **`$ROOT/data_catalog/DATA_CATALOG.md`** (symlink to sibling repo) — master registry of all raw datasets with provenance, structure, and restrictions 2. **`$ROOT/data_catalog/codebooks/`** (symlink) — detailed codebooks per dataset 3. **`$ROOT/research/meta/variable_dictionary.md`** — shared variable definitions used across projects 4. **`$ROOT/research/meta/data_linkages.md`** — how datasets link across projects (join keys, shared identifiers) 5. **Project-level `docs/data.md`** files — in `$ROOT/projects/*/docs/data.md` 6. **Pipeline `docs/data.md`** and `docs/summary.md` — in `$ROOT/pipelines/*/docs/` ## How to search Based on the user's query: - **"What data do we have on X?"** — Search DATA_CATALOG.md and codebooks for topic matches. Report: dataset name, provider, coverage, key varia