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.

Compound-target-disease network construction and analysis for drug repurposing, polypharmacology discovery, and multi-target drug design. Uses STRING, BioGRID, ChEMBL, DGIdb, OMIM, OpenTargets. Use for off-target effect prediction, network-based drug repurposing, and identifying molecules with desired multi-target profile.

Metabolomics pathway analysis — metabolite identification (HMDB, KEGG, ChEBI), pathway mapping (Reactome, KEGG, MetaCyc), disease associations, enzyme/gene linkage. Use for metabolite-to-pathway-to-disease connections, BridgeDb-based ID conversion, and integrating metabolomics with gene-level pathway analyses.

Meta-analysis / evidence synthesis — pool effect sizes across studies (odds ratios, risk ratios, hazard ratios, mean differences, correlations, GWAS betas) with fixed- or random-effects models, quantify heterogeneity (Q, I², τ²), and build a forest plot. Use when you have results from MULTIPLE studies and need a single pooled estimate, or to synthesize evidence from a systematic review / multiple GWAS / replicated experiments. Handles the error-prone effect-size + standard-error preparation (converting OR/HR/CI, two-group means±SD, proportions, and correlations into the (effect, SE) the pooling step needs).

AI-driven patient-to-trial matching for precision oncology and rare-disease care. Transforms a patient's molecular profile (mutations, biomarkers, expression) and clinical state into ranked clinical-trial recommendations with evidence tiers. Searches ClinicalTrials.gov, the EU CTIS register (European/EEA trials), AND the ISRCTN registry (UK/international) plus cross-references CIViC, OpenTargets, ChEMBL, and FDA labels. Use for matching patients to trials by genotype, biomarker-driven trial selection, trial-eligibility scoring, and finding trials across the US, Europe, and the UK.

TCGA/GDC cancer genomics analysis — cohort construction, clinical metadata retrieval, somatic mutation frequencies, survival analysis, and multi-omics integration. Use for TCGA-BRCA-style cohort studies, mutation prevalence by cancer type, survival-by-mutation analysis, and pan-cancer driver discovery. Always cancer-type-specific (don't use pan-cancer counts without cohort context).

Propose the mechanism by which a missense variant causes loss-of-function (LoF), synthesizing evidence from 5 independent layers: AlphaMissense pathogenicity, AlphaFold structural context, ESMC sequence likelihood, SAE feature disruption, and DynaMut2 stability ΔΔG. Distinguishes 'structural stability LoF' (mis-folding) from 'direct functional disruption' (catalytic / binding / PTM site damage). Use for coding missense variants where you need a mechanistic causal model, not just a pathogenicity score.

Gene-disease association analysis across DisGeNET, OpenTargets, Monarch, OMIM, GenCC, Orphanet. Cross-references multiple sources for evidence-graded association reports with concordance scoring (5/5 sources agree → strong, 1/5 → weak). Use for 'which diseases is gene X associated with' or 'which genes cause disease Y' queries with quantitative confidence.

Trace drug mechanism of action — primary target → downstream signaling → pathway perturbation → tissue/organ effect → clinical outcome. Uses DrugBank, ChEMBL, KEGG, Reactome, STRING. Use for understanding how a drug works, identifying off-target effects, mechanism-based combination therapy design, and writing mechanism sections of reports.

Install the ToolUniverse Claude Code plugin in one step — provides MCP server with 1000+ scientific tools, 120+ research skills, slash commands, hooks, and the research agent. Use for first-time plugin install, troubleshooting plugin not loading, verifying MCP server connection, listing API key requirements, or configuring auto-update.

在需要圆角矩形纯色背景、描边边框时，优先用 DevWidget（io.github.afkt:DevWidgetX）的 dev.widget.ui.round 包替代 shape / layer-list drawable。流程与核心坑在 SKILL，Round 系列 View、R.styleable.DevWidget 中 app:dev_* 属性及源码对照见 references/reference.md。工作区内优先 Read lib/DevWidget；仅当无该模块时再查上游 GitHub。

将布局与代码中的硬编码 dp、sp 改为引用 @dimen/dp_*、@dimen/sp_* 与 R.dimen.*； 资源名规则为整数部分与一位小数部分用下划线连接（如 12.5 → dp_12_5）。 在用户要求去掉魔法数、统一 dimen、替换 dp/sp 字面量或规范化尺寸引用时使用。

Explore user intent, requirements, and design options through collaborative dialogue before implementation. Use before building new features, components, or systems — whenever the user describes something to build and design decisions are involved. Triggers: "brainstorm", "help me design", "think through the requirements", "头脑风暴", "设计方案", "梳理需求". Not for bug fixes, config changes, or tasks with an obvious implementation path.

HASH error handling patterns using error-stack crate. Use when working with Result types, Report types, defining custom errors, propagating errors with change_context, adding context with attach, implementing Error trait, or documenting error conditions in Rust code.

Use when writing or modifying tests inside MPS `@tests` models — `NodesTestCase` (typesystem, constraints, scopes, dataflow, generator output), `EditorTestCase` (intentions, actions, keystrokes, side-transforms, completion), `MigrationTestCase` (migration scripts), `BTestCase` (plain JUnit on hand-written Java/Kotlin runtime), inline annotations such as `has error` / `has type` / `ScopesTest`, label-based `node<label>` cross-references, caret markers, and running tests via MCP / in MPS. Reach for this skill whenever the task involves authoring or fixing tests in a `tests`-stereotype model, or interpreting failures from one.

Add, update, or delete MPS nodes using JSON blueprints — covers the unified blueprint format, staged construction for large subtrees, validation, and reference repair. Use whenever creating, editing, or restructuring nodes in any MPS model (structure, editor, behavior, generator, application code, etc.).

Use when authoring or debugging MPS TextGen — concept-to-plain-text serialisation for languages whose final output is text (source files, config, scripts, DDL, XML, markdown). Covers `ConceptTextGenDeclaration` roots, `append` / `indent buffer` / `with indent` statements, text layout areas, context objects (e.g. imports sets), attributes, the base text gen component (`LanguageTextGenDeclaration`), binary `write`, `found error`, and the indentation-buffer model. Reach for this skill whenever the task involves editing `<lang>/languageModels/textGen.mps`.

Use when authoring or debugging MPS migration scripts that upgrade user models after a language definition changes — covers jetbrains.mps.lang.migration (MigrationScript class-based, PureMigrationScript declarative, MoveConcept/MoveContainmentLink/MoveReferenceLink/MoveProperty, ordering via OrderDependency, data exchange via putData/getData, RefactoringLog, ConceptMigrationReference) and jetbrains.mps.lang.script Enhancement Scripts (MigrationScript with MigrationScriptPart_Instance, ExtractInterfaceMigration, FactoryMigrationScriptPart, CommentMigrationScriptPart) — when a model needs version-gated upgrade, concept rename or removal, link or property rename, instance-level transformation, or composition of migration steps.

Use when authoring the **non-layout** parts of the MPS editor aspect — what happens when the user types, presses a key, triggers completion, pastes, or invokes a context action. Covers action maps (`CellActionMapDeclaration`), cell keymaps (`CellKeyMapDeclaration`), transformation menus (`TransformationMenu_Default` / `_Named` / `_Contribution`), substitute menus (`SubstituteMenu_Default` / `SubstituteMenu` / contributions), side transforms (LEFT/RIGHT), legacy cell menus, paste wrappers and copy-paste handlers (in the actions language), completion styling, reference presentation, two-step deletion, and the editor selection API. Trigger terms: `actionMap`, `keyMap`, `delete_action_id`, `transformationMenu`, `substituteMenu`, `Ctrl+Space`, `Ctrl+Alt+B`, side transform, paste wrapper, completion styling, `PasteWrappers`, `CopyPasteHandlers`. For the **layout** side (cells, layouts, style sheets) use `mps-aspect-editor` instead.

Use when defining or editing MPS node factories (the "actions" aspect) — `NodeFactories` roots, per-concept `NodeFactory` setup functions that initialize a freshly created node and optionally copy data from a replaced `sampleNode`, plus the actions aspect's `CopyPasteHandlers` and `PasteWrappers` roots. Reach for this skill when a substitution, side transform, completion replacement, or `add new initialized(...)` should preserve fields from the node it is replacing, or when defaults set in a constructor are not enough.