SUSTech-GenAI/StatefulDiscovery

evidence-strength-judge

Invoke after experiment-runner completes an investigation's query bundle. Evaluates all claims in current_investigation.json and produces an investigation-level adjudication. Writes claim_scores.json.

原文语言：英语

experiment-runner

Invoke after investigation-decomposition. Runs all queries in an investigation bundle using shared data preparation. Writes code and results.

原文语言：英语

exploration-strategist

Invoke after main agent writes L2 assessment. Reads epistemic state (L1/L2), patterns, and investigations to recommend next action. Writes strategy_recommendation.json.

原文语言：英语

gseapy

Gene set enrichment analysis (GSEA, Enrichr, over-representation). Invoke when query mentions enrichment, pathway analysis, GO analysis, GSEA, or gene set.

原文语言：英语

investigation-decomposition

Invoke before running experiments for an investigation. Reads current_investigation.json and task_packet.json, writes current_investigation_requirements.json with shared data preparation and per-query requirements.

原文语言：英语

mygene

Gene ID conversion and annotation. Invoke when you need to map between any gene identifier formats.

原文语言：英语

phylogenetics

Phylogenetic analysis: multiple sequence alignment (MAFFT), tree building (IQ-TREE, FastTree), tree metrics (treeness, branch lengths, patristic distances). Invoke when query involves phylogenetic trees, evolutionary analysis, sequence alignment, treeness, or…

原文语言：英语

pydeseq2

Differential expression analysis for RNA-seq count data. Invoke when query mentions DESeq2, differential expression, DE genes, or RNA-seq comparison.

原文语言：英语

pysam

NGS data processing: read/write SAM/BAM/CRAM alignments, VCF/BCF variants, FASTA/FASTQ. Calculate coverage, perform pileup, run samtools/bcftools commands. Invoke when query involves sequencing alignment, variant calling, coverage depth, or read mapping.

原文语言：英语

repro-gate-check

Invoke before final output. Validates that all claims have reproducible evidence (code files exist, experiment records complete). Run the bundled Python script.

原文语言：英语

scanpy

Single-cell RNA-seq analysis pipeline. Invoke for .h5ad data, QC, normalization, PCA/UMAP, clustering, marker genes, cell type annotation.

原文语言：英语

write-claims

Invoke for claims.json final output format reference. Defines the schema for aggregated claims across all investigations.

原文语言：英语

write-experiment

Invoke before writing experiments.jsonl. Provides the exact JSON structure and required fields for experiment records.

原文语言：英语

write-investigation

Invoke for investigations.json and current_investigation.json format reference. Defines the schema for claim investigations and query bundles.

原文语言：英语

write-patterns

Invoke for patterns.json format reference. Defines the schema for tracking unexplained data patterns.

原文语言：英语

write-state

Invoke for epistemic_state.json format reference. Defines the global exploration state schema with L1/L2 uncertainty assessment.

原文语言：英语

gseapy

Gene set enrichment analysis (GSEA, Enrichr, over-representation). Invoke when query mentions enrichment, pathway analysis, GO analysis, GSEA, or gene set.

原文语言：英语

repro-gate-check

Invoke before final output. Validates that all claims have reproducible evidence (code files exist, experiment records complete). Run the bundled Python script.

原文语言：英语