research-lookup
Originally fromk-dense-ai/claude-scientific-skills
Installation
SKILL.md
Research Information Lookup
Real-time research lookup that routes each query to the backend best suited to it, then saves the result so every citation can be traced later.
The three backends
| Backend | Speed | Use it for | How to call |
|---|---|---|---|
parallel-cli search (default) |
2–10 s | Almost everything: general research, market/industry data, technical lookups, current events, fact-checking, comparisons | parallel-cli search (direct) |
| Perplexity sonar-pro-search | 5–15 s | Scholarly paper searches where peer-reviewed database coverage matters (find papers, DOIs, systematic reviews) | scripts/research_lookup.py --force-backend perplexity |
Parallel Chat API (core model) |
60 s–5 min | Deep, exhaustive multi-source synthesis — only when the user explicitly asks for "deep research" | scripts/research_lookup.py --force-backend parallel |
Naming caution — there are two different "Parallel" things.
parallel-cli searchis the fast web-search CLI (the default). The "Parallel Chat API (coremodel)" is a separate, slow deep-research endpoint reached only throughresearch_lookup.py.--force-backend parallelselects the slow Chat API, not the fast CLI. Don't conflate them.
Default to parallel-cli search. It is fast and cheap and handles the large majority of research needs. Reach for the other two only when the query specifically calls for scholarly paper coverage (Perplexity) or exhaustive synthesis (Chat API).