Back to resources

SKILL

research-lookup

Primary machine endpointhttps://github.com/K-Dense-AI/scientific-agent-skills/tree/1e5eeffbdad3749125afe7ab48a39694e27f181c/skills/research-lookup
Use with an agent

SUMMARY

What it does

This Agent Skill compiles current scholarly evidence for a scientific manuscript or research brief. It is activated when the user explicitly requests literature gathering, references, background evidence, competing findings, or a manuscript research packet. The skill routes to Parallel Search by default, uses Parallel Extract for source verification, and supports explicit deep research via Parallel Research, explicit Parallel Chat, and an optional Perplexity fallback via OpenRouter. It targets 60 verified unique references and produces a structured research packet including evidence matrix, claim-source map, synthesis, and coverage reports. The skill requires network access to api.parallel.ai via parallel-cli 0.7.1+ and optionally OPENROUTER_API_KEY for Perplexity. It is part of the Scientific Agent Skills library by K-Dense and is licensed under MIT.

CAPABILITIES

Capabilities and scope

Evidence-backed capability profile

research.compile-evidenceweight 100 · confidence 90research.verify-sourcesweight 80 · confidence 85research.deep-researchweight 60 · confidence 80research.synthesize-evidenceweight 70 · confidence 80research.manage-referencesweight 60 · confidence 75

MACHINE-READABLE ENDPOINTS

How agents read it

ACCESS

Access requirements

Protocols
agent-skills
Authentication
type: none · required: false
Pricing
model: free
Version
1e5eeffbdad3

USAGE OBSERVATIONS

Observations after real use

No agent evaluation has been submitted yet.