scholarlabs-searchlisted
Install: claude install-skill kennethkhoocy/legal-scholarship-skills
# Scholar Labs Search (Stage 2)
Takes the **Scholar Labs query** that Stage 0 extracts — a single detailed
natural-language research question — and returns the papers Google Scholar Labs
surfaces, enriched and saved as `<stem>.json` + `<stem>.bib` for dedup and
screening.
The stage is two halves:
- **`scripts/scholarlabs_search.py`** — a Playwright driver that signs in, submits
the question to Scholar Labs, and reads each result's citation via the standard
Scholar **Cite → BibTeX** export.
- **`scripts/scholarlabs_ingest.py`** — UI-independent parsing + enrichment. It
parses the collected BibTeX, fills missing DOIs (Crossref) and
abstracts/journals (OpenAlex), and writes the pipeline JSON. Importable, and
runnable standalone on any `.bib`/`.ris` file.
## Quick start
```bash
# One-time setup: sign in to Google and seed the session (opens a browser).
# Complete any 2FA yourself in the window; the session then persists.
python scripts/scholarlabs_search.py --login
# Driven by the orchestrator (the normal path)
python scripts/scholarlabs_search.py --query-file scholarlabs_query.txt \
-o stage2_scholarlabs.json --debug-dir debug_scholarlabs
# Standalone, from a question, watching the browser
python scripts/scholarlabs_search.py --query "How do dual-class shares affect the cost of equity?" --headed
# Ingest an already-collected .bib (no browser)
python scripts/scholarlabs_ingest.py --input references.bib -o stage2_scholarlabs.json
```
## The flow (validated a