research-lookup
research-lookup is a Literature review & citations skill for AI agents, published by K-Dense-AI in the scientific-agent-skills repository on GitHub. Skillspace rates research-lookup B (87/100) and it passed the safety scan; a judge model has also reviewed it.
Compile current scholarly evidence for a scientific manuscript or research brief. Use when the user explicitly asks to gather literature, references, background evidence, competing findings, or a manuscript research packet. Uses Parallel Search by default, Parallel Extract for source verification, Parallel Research for explicitly deep/exhaustive work, optional explicit Parallel Chat, and optional Perplexity only when requested or allowed as a failure fallback.
- Grade
- B
- Quality
- 87 / 100
- Safety
- Passed
- GitHub stars
- 30,973
Placed #2 of 6 in the judged category final for Literature review & citations.
Our two independent classifiers differ on this skill's category, so treat the placement as provisional.
This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.
Our review
- Architecture
- 100 / 100
- Maturity
- Packaged: licensed, with a version or references
- Security scan
- No issues found
- License
- MIT
- Adoption
- Adopted by 0 other repositories, in 4 collections
- Scope
- Vendor-specific: built around one product. Research compiled via the Parallel search API products
Judge review
Placed #2 of 6 in the judged category final for Literature review & citations.
- Trigger
85 85 - Instructions
85 85 - Specificity
88 88 - Safety
85 85 - Disclosure
68 68 - Maintenance
72 72
Well-bounded manuscript-evidence pipeline with an explicit multi-pass academic search strategy, retraction-aware extraction, and honest disclosure of which provider each query is sent to.
Not checked yet
- No blind task eval yet
- Sibling files (scripts, references) not fetched; security scan covers SKILL.md only
Also published in 1 other repo
Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.