scholarlabs-search
Stage 2 of the lit review pipeline: run a Google Scholar Labs deep search from the detailed research question produced by Stage 0, scrape each result's citation (Cite to BibTeX), then parse + enrich into the pipeline schema. The driver signs in to Google with a persistent profile and runs headless via Playwright. Only use this skill when explicitly requested. Do NOT auto-trigger on general literature review or paper search requests.
npx skills add kennethkhoocy/applied-micro-skills --skill scholarlabs-search --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# 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 br
- Quick start
- The flow (validated against the June 2026 UI)
- The Scholar Labs query is distinct from the Undermind brief
- Login & credentials
- CLI
- Graceful degradation
- Output schema
- Testing with windows-mcp (headed)
- Troubleshooting
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 \ 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
What does the scholarlabs-search skill do?
Stage 2 of the lit review pipeline: run a Google Scholar Labs deep search from the detailed research question produced by Stage 0, scrape each result's citation (Cite to BibTeX), then parse + enrich into the pipeline schema. The driver signs in to Google with a persistent profile and runs headless via Playwright. Only use this skill when explicitly requested. Do NOT auto-trigger on general literature review or paper search requests.
How do I install it?
Run `npx skills add kennethkhoocy/applied-micro-skills --skill scholarlabs-search --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From kennethkhoocy/applied-micro-skills, a repository with 54 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.