com um clique
darwin
darwin contém 22 skills coletadas de yejunbin, com cobertura ocupacional por repositório e páginas de detalhe dentro do site.
Skills neste repositório
Fetch and analyze AlphaFold-predicted protein structures from the AlphaFold DB or EBI.
Autonomous experiment loop that tries ideas, measures results, keeps what works, and discards what doesn't. Use when the user asks to optimize a metric, run an experiment loop, improve performance iteratively, or automate benchmarking.
Search, read, and query research papers via the `alpha` CLI (bioRxiv-backed). Use when the user asks about academic papers, wants to find research on a topic, needs to read a specific paper, ask questions about a paper, inspect a paper's code repository, or manage paper annotations.
Evaluate biomarker performance with ROC analysis, AUC, sensitivity, and specificity.
Monitor bioRxiv and medRxiv preprints for a topic, author, or keyword. Use for staying current with emerging biomedical research before peer review.
Search and summarize clinical trials from ClinicalTrials.gov and EU CTR. Use for drug development, competitive intelligence, and evidence synthesis.
Contribute changes to the Darwin repository itself. Use when the task is to add features, fix bugs, update prompts or skills, change install or release behavior, improve docs, or prepare a focused PR against this repo.
Execute research code inside isolated Docker containers for safe replication, experiments, and benchmarks. Use when the user selects Docker as the execution environment or asks to run code safely, in isolation, or in a sandbox.
Calculate drug dosages with renal and hepatic adjustments. Use standard references only. Not for direct patient care.
Look up gene information from HGNC, OMIM, ClinVar, and UniProt. Use for target validation, variant interpretation, and disease-gene associations.
Guide reanalysis of GEO datasets with standard bioinformatics pipelines.
Fit dose-response curves and calculate IC50/EC50 with confidence intervals using 4-parameter logistic regression.
Inspect active background research work including running processes, scheduled follow-ups, and pending tasks. Use when the user asks what's running, checks on background work, or wants to see scheduled jobs.
Guide gene list enrichment analysis using over-representation and GSEA approaches.
Simulate a tough but constructive peer review of an AI research artifact. Use when the user asks for a review, critique, feedback on a paper or draft, or wants to identify weaknesses before submission.
Search PubMed with MeSH terms, structured queries, and filters. Use for peer-reviewed biomedical literature, clinical trials, systematic reviews, and meta-analyses.
Plan or execute a replication of a paper, claim, or benchmark. Use when the user asks to replicate results, reproduce an experiment, verify a claim empirically, or build a replication package.
Check papers for retractions, corrections, and expressions of concern. Use before citing any source in evidence synthesis or systematic reviews.
Guide sequence alignment and BLAST searches for nucleotide and protein sequences.
Search past Darwin session transcripts to recover prior work, conversations, and research context. Use when the user references something from a previous session, asks "what did we do before", or when you suspect relevant past context exists.
Validate statistical methods, check for p-hacking signs, and verify reporting adequacy in biomedical papers.
Set up a recurring research watch on a topic, company, paper area, or product surface. Use when the user asks to monitor a field, track new papers, watch for updates, or set up alerts on a research area.