devtu-code-optimization

Orchestrate the full ToolUniverse self-improvement cycle: discover APIs, create tools, test with researcher personas, fix issues, optimize skills, and push via git. References and dispatches to all other devtu skills. Use when asked to: run the self-improvement loop, do a debug/test round, expand tool coverage, improve tool quality, or evolve ToolUniverse.

Optimize ToolUniverse skills for better report quality, evidence handling, and user experience. Apply patterns like tool verification, foundation data layers, disambiguation-first, evidence grading, quantified completeness, and report-only output. Use when reviewing skills, improving existing skills, or creating new ToolUniverse research skills.

Optimize tool descriptions in ToolUniverse JSON configs for clarity and usability. Reviews descriptions for missing prerequisites, unexpanded abbreviations, unclear parameters, and missing usage guidance. Use when reviewing tool descriptions, improving API documentation, or when user asks to check if tools are easy to understand.

GitHub workflow for ToolUniverse - push code safely by moving temp files, activating pre-commit hooks, running tests, and cleaning staged files. Use when pushing to GitHub, fixing CI failures, or cleaning up before commits.

Fix failing ToolUniverse tools by diagnosing test failures, identifying root causes, implementing fixes, and validating solutions. Use when ToolUniverse tools fail tests, return errors, have schema validation issues, or when asked to debug or fix tools in the ToolUniverse framework.

TOP PRIORITY skill — find and immediately fix or remove every piece of wrong, outdated, or redundant information in ToolUniverse docs. Wrong code, broken links, incorrect counts, and overlapping instructions must be fixed or removed — never left in place. Runs five phases: (D) static method scan, (C) live code execution, (A) automated validation, (B) ToolUniverse audit, (E) less-is-more simplification. Core philosophy: each concept appears exactly once; remove don't add; no emojis; single setup entry point. Use when reviewing docs, before releases, after API changes, or when asked to audit, fix, or simplify documentation.

Create new scientific tools for ToolUniverse framework with proper structure, validation, and testing. Use when users need to add tools to ToolUniverse, implement new API integrations, create tool wrappers for scientific databases/services, expand ToolUniverse capabilities, or follow ToolUniverse contribution guidelines. Supports creating tool classes, JSON configurations, validation, error handling, and test examples.

Automatically discover life science APIs online, create ToolUniverse tools, validate them, and prepare integration PRs. Performs gap analysis to identify missing tool categories, web searches for APIs, automated tool creation using devtu-create-tool patterns, validation with devtu-fix-tool, and git workflow management. Use when expanding ToolUniverse coverage, adding new API integrations, or systematically discovering scientific resources.

Router skill for ToolUniverse tasks. First checks if specialized tooluniverse skills (105+ skills covering disease/drug/target research, gene-disease associations, clinical decision support, genomics, epigenomics, proteomics, comparative genomics, chemical safety, toxicology, systems biology, and more) can solve the problem, then falls back to general strategies for using 2300+ scientific tools. Covers tool discovery, multi-hop queries, comprehensive research workflows, disambiguation, evidence grading, and report generation. Use when users need to research any scientific topic, find biological data, or explore drug/target/disease relationships. ALSO USE for any biology, medicine, chemistry, pharmacology, or life science question — even simple factoid questions like "how many X in protein Y", "what drug interacts with Z", "what gene causes disease W", or "translate this sequence". These questions benefit from database lookups (UniProt, PubMed, ChEMBL, ClinVar, GWAS Catalog, etc.) rather than answering from memory alone. When in doubt about a scientific fact, USE THIS SKILL to verify against real databases.

End-to-end variant-to-mechanism analysis: given a genetic variant (rsID or coordinates), trace its functional impact from regulatory context (GWAS, eQTL, RegulomeDB, ENCODE) through target gene identification (GTEx, OpenTargets L2G) to downstream pathway and disease biology (STRING, Reactome, GO enrichment, disease associations). Produces an evidence-graded mechanistic narrative linking genotype to phenotype. Use when asked "how does this variant cause disease?", "what is the mechanism of rs7903146?", "trace variant to pathway", or "connect this GWAS hit to biology".

Systematic clinical variant interpretation from raw variant calls to ACMG-classified recommendations with structural impact analysis. Aggregates evidence from ClinVar, gnomAD, CIViC, UniProt, and PDB across ACMG criteria. Produces pathogenicity scores (0-100), clinical recommendations, and treatment implications. Use when interpreting genetic variants, classifying variants of uncertain significance (VUS), performing ACMG variant classification, or translating variant calls to clinical actionability.

Comprehensive functional annotation of protein variants — pathogenicity, population frequency, structural context, and clinical significance. Integrates ProtVar (map_variant, get_function, get_population) for protein-level mapping and structural context, ClinVar for clinical classifications, gnomAD for population frequency with ancestry data, CADD for deleteriousness scores, and ClinGen for gene-disease validity. Produces a structured variant annotation report with evidence grading. Use when asked about protein variant impact, missense variant pathogenicity, ProtVar annotation, variant functional context, or combining population and structural evidence for a variant.