Detect and analyze adverse drug event signals using FDA FAERS reports, drug labels, and disproportionality statistics (PRR, ROR, IC). Generates quantitative safety signal scores (0-100) with evidence grading. Use for post-market surveillance, pharmacovigilance, drug safety assessment, regulatory submissions, and detecting rare AE signals not visible in clinical trials.

Validate a variant-effect predictor (AlphaMissense, ESM-C SAE, ESM logits, EVE, conservation scores, or any per-variant numeric score) against experimental deep mutational scanning (DMS) data. Computes per-variant predictor scores, splits variants into neutral vs disruptive groups by DMS effect, runs a Mann-Whitney U test on the predictor scores, and sweeps the stratification thresholds for robustness. Use when you need to know whether a predictor's scores track real functional disruption on a specific protein.

Build AI scientist systems with the ToolUniverse Python SDK for scientific research. Covers the 3 calling patterns (`tu.run` portable dict API, `tu.tools.X` function API, direct class instantiation), tool loading, batch execution, MCP server integration, and embedding-based tool search. Use for SDK programming, custom tool composition, benchmarking pipelines, and integrating ToolUniverse into research workflows.

Phylogenetic analysis — de novo multiple sequence alignment (Clustal Omega/MUSCLE/MAFFT via EBI_msa_align) and neighbour-joining/UPGMA tree building (EBI_build_phylogenetic_tree) from your own sequences, plus tree analysis, treeness, saturation (PhyKIT), parsimony-informative sites, alignment gap analysis, DVMC, long-branch detection, BUSCO orthologs. Uses PhyKIT, Biopython, DendroPy. Use to align a set of sequences, build a tree from sequences or an alignment, or for phylogenetic tree QC, multi-gene phylogenomics, evolutionary-rate analysis, and comparative-genomics studies.

Use when authoring or debugging MPS typesystem — inference rules (`typeof :==: / :<=: / :>=:`), `SubtypingRule`, `ComparisonRule`, `InequationReplacementRule`, `SubstituteTypeRule`, `WhenConcreteStatement` blocks, `NonTypesystemRule` checking rules, `TypesystemQuickFix`, error/warning/info reports with `messageTarget` highlighting and quick-fix wiring (`helginsIntention`), and shared BaseLanguage helpers in the typesystem model. Reach for this skill whenever the task involves editing `<lang>/languageModels/typesystem.mps`.

Use when defining or editing MPS intentions (the Alt+Enter context-action aspect) — adding `IntentionDeclaration` roots, parameterized or surround-with variants, description/isApplicable/execute blocks, child-filter functions, factory-initialized AST splicing, or debugging why an intention is not offered. Lives in the language's `intentions` model and uses `jetbrains.mps.lang.intentions`.

Reviews pull requests against project standards and posts review comments via the gh CLI. Use when reviewing PRs, checking coding standards compliance, or performing approval reviews.

Facade-specific YARD documentation rules for Git::Repository::* topic modules and their facade methods, overriding and extending the general yard-documentation skill. Use when writing or reviewing YARD docs for facade modules under lib/git/repository/.

Command-specific YARD documentation rules for Git::Commands::Base subclasses, overriding and extending the general yard-documentation skill. Use when writing or reviewing YARD docs for command classes.

Scaffolds new and reviews existing Git::Commands::* classes with unit tests, integration tests, and YARD docs using the Base architecture. Use when creating a new command class from scratch, updating an existing command class, or reviewing a command class for correctness.

Translate Chinese rtp2httpd docs into docs/en/ and synchronize English navigation, links, and terminology after source changes.

Write or revise prose for humans. Use for documentation, code comments and API references in any language, UI and error text, reports, explanations, and project communication. Preserve exact meaning while replacing vague, metaphorical, anthropomorphic, hedged, or inflated language with literal statements.

Use the Svelte CLI to check any Svelte component or module that you create, edit, or analyze.

Turn workflows from your MemSearch memory into reusable skills. Use when the user asks to make/create/extract/distill a skill from what they just did or from past work, review skill candidates, install a distilled skill, or 'turn this into a skill'. Manages MemSearch procedural-memory candidates under .memsearch/skill-candidates/, not the host agent's own skills system.

Search and recall relevant memories from past sessions via memsearch. Use when the user's question could benefit from historical context, past decisions, debugging notes, previous conversations, or project knowledge -- especially questions like 'what did I decide about X', 'why did we do Y', or 'have I seen this before'. Also use when you see `[memsearch] Memory available` hints injected via SessionStart or UserPromptSubmit. Typical flow: search for 3-5 chunks, expand the most relevant, optionally deep-drill into original transcripts via the anchor format. Skip when the question is purely about current code state (use Read/Grep), ephemeral (today's task only), or the user has explicitly asked to ignore memory.

Diagnose and configure MemSearch memory behavior. Use when the user asks about MemSearch configuration, plugin summarization, PROJECT.md/USER.md maintenance, memory directories, index health, provider routing, prompt files, or migration/compatibility questions.

Investigate a failure with an unclear cause, repeated unsuccessful fixes, or a cross-component boundary. Use existing reproduction evidence for a localized bug; not a mandatory multi-stage ritual for every edit.

Go test-shape discipline for Compozy. Use when writing or editing *_test.go under cmd or internal after test placement is justified. Do not use for non-Go tests, fixture-only changes, or as a replacement for eng-consolidate-test-suites.

Data-boundary audit for Compozy route loaders, TanStack Query caches, paginated catalogs, filters, ordering, totals, live streams, workspace-scoped reads, and their backend APIs. Use when adding, changing, or debugging those paths. Don't use for presentational-only UI or backend work with no public read-model impact.

Contract co-ship for Compozy wire changes. Use when editing public DTOs, OpenAPI, JSON-RPC extension shapes, generated clients, or handler request/response semantics. Do not use for internal Go refactors or test-only changes that leave the wire contract unchanged.