Research Lookup
This is a research lookup tool with intelligent routing across three backends: parallel-cli for fast web search (the default for most queries), Parallel Chat API for deep multi-source synthesis when you need exhaustive research, and Perplexity sonar-pro for academic paper searches. It auto-detects keywords like "peer-reviewed" or "find papers" to pick the right backend, and for scientific queries it runs dual searches to catch both academic and general sources. The routing logic is transparent and you can force a specific backend if needed. Saves you from manually juggling different search tools depending on whether you're chasing down a DOI or just need current market data.
- skills.sh installs
- 2.1K
- GitHub stars
- 56.6K
- last updated
- Aug 21, 2026
Install
$ npx -y skills add k-dense-ai/scientific-agent-skills --skill research-lookup --agent claude-codeInstalls into .claude/skills of the current project.
Files
Research Lookup
Compile the external evidence needed to plan and write a high-quality scientific
manuscript. The default academic workflow targets 60 verified, unique references
and produces a manuscript-ready research packet rather than a loose list of links.
Here verified_references counts successful retrieval of nonempty Extract excerpts,
excluding flagged retractions. It does not establish bibliographic identity, claim
support, peer review, or absence of corrections; those require source review.
Scope and boundaries
Use this skill when the user explicitly wants:
- literature and background research for a manuscript
- many high-quality academic references
- evidence supporting or contradicting a scientific claim
- a structured evidence matrix or claim-to-source map
- current studies, methods precedent, mechanisms, limitations, or research gaps
Do not activate it for casual factual questions that do not need research, private or unpublished material, or a claim that can be answered from user-provided files. Query text is sent to Parallel. It is sent to OpenRouter only when Perplexity is explicitly selected or the user enables that fallback.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageDetails
- Repository
- github.com/k-dense-ai/scientific-agent-skills
- Categories
- AI & Agent Building, Data Science & ML, Automation & Workflows
- First seen
- Jun 3, 2026
More from k-dense-ai/scientific-agent-skills
All 137- Timesfm Forecasting2.1K
- Geopandas2.1K
- Stable Baselines32.1K
- Consciousness Council2.1K
- Simpy2.1K
- Pymoo2.1K
- Scikit Bio2.1K
- Geomaster2.1K
- What If Oracle2.1K
- Hypogenic2.1K
- Bioservices2.1K
- Anndata2.1K
- Clinical Reports2K
- Clinical Decision Support2K
- Gget2K
- Rdkit2K
- Modal2K
- Scanpy2K
- Astropy2K
- Cellxgene Census2K
- Pydicom2K
- Datamol2K
- Deeptools2K
- Deepchem2K
Recommended
More AI & Agent Building
timesfm-forecastingk-dense-ai/scientific-agent-skillsZero-shot time series forecasting with Google's TimesFM foundation model. Use for any univariate time series (sales, sensors, energy, vitals, weather) without t2.1Kskills.sh installsconsciousness-councilk-dense-ai/scientific-agent-skillsRun a multi-perspective Mind Council deliberation on any question, decision, or creative challenge. Use this skill whenever the user wants diverse viewpoints, n2.1Kskills.sh installs
pudlcatalyst-cooperative/agent-skillsExplore and understand PUDL energy data: discover which tables exist, look up column meanings and usage warnings, and load Parquet files from S3 or a local dire2.1Kskills.sh installssimpyk-dense-ai/scientific-agent-skillsBuild, inspect, test, and analyze bounded process-based discrete-event simulations with SimPy, including events, resources, interrupts, monitoring, replications2.1Kskills.sh installs
risk-management0xhubed/agent-trading-arenaRisk management rules learned from competition outcomes. Use when sizing positions or setting stop-losses.2.1Kskills.sh installspymook-dense-ai/scientific-agent-skillsMulti-objective optimization framework. NSGA-II, NSGA-III, MOEA/D, Pareto fronts, constraint handling, benchmarks (ZDT, DTLZ), for engineering design and optimi2.1Kskills.sh installs