Direct REST API access to UniProt for protein search, entry retrieval, and identifier mapping; use when you need programmatic UniProtKB queries or cross-database ID conversion.

Medicinal chemistry screening filters for compound prioritization; use when you need to apply drug-likeness rules, PAINS/structural alerts, and complexity metrics to triage or optimize libraries.

Direct access to KEGG via the REST API for academic-only pathway/gene/compound/drug queries; use when you need precise HTTP-level control or targeted KEGG ID mapping.

Query the ClinicalTrials.gov API v2 to search for clinical trials, retrieve detailed study protocols, and analyze recruitment status; use when you need to find trials by condition/drug, export results, or verify study details by NCT ID.

Programmatically query public single-cell study metadata from the Broad Institute Single Cell Portal REST API when you need to search and filter datasets by organism, tissue, disease, or cell type without an API key.

Conduct comprehensive, systematic literature reviews using multiple academic databases (PubMed, arXiv, bioRxiv, Semantic Scholar, etc.). Creates professionally formatted markdown documents and PDFs with verified citations in multiple citation styles.

Generates submission-ready Elsevier/SCI Highlights from manuscript text or extracted PDF/DOCX/TXT content. Use when a user needs 3-5 concise, evidence-grounded highlight bullets for a research paper, review, meta-analysis, case report, or bioinformatics manuscript.

Compares multiple study-route options for the same biomedical research question and recommends one primary plan, while explicitly explaining why alternative routes are secondary, premature, weaker, or dependency-heavy. Always use this skill when the user already has a reasonably defined question but is unsure which main study route should anchor the project. Focus on plan comparison, route selection, dependency awareness, and primary-plan justification rather than full protocol drafting.

Extends a mechanistic or association-level biomedical finding into a staged validation pathway that moves from descriptive evidence toward stronger functional support, mechanistic specificity, and clinical relevance. Use this skill when a user has a pathway, biomarker, cell-state, target, mechanism, or association finding and needs to decide what should be validated next, in what order, and which evidence layers are necessary versus optional. Do not default to maximal validation stacks. Build a structured validation ladder with a primary route, stronger upgrade route, and optional extensions.

Extracts concrete unmet clinical needs from guidelines, reviews, real-world studies, and clinical-practice evidence. Use this skill when a user wants to turn broad medical research value into specific clinical pain points such as weak early detection, poor risk stratification, treatment-response heterogeneity, monitoring gaps, diagnostic delay, undertreatment, overtreatment, or implementation failure. Always ground unmet-need claims in retrieved evidence and distinguish true care gaps from generic statements of importance.

Matches your study to appropriate journals based on topic, design, and evidence strength. Use when deciding where to submit a manuscript, comparing journal options by impact factor vs scope fit vs method tolerance, or finding a realistic submission target after a rejection. Also triggers on "where should I submit this paper", "which journal is best for my study", "find journals for my manuscript", "is this a good fit for [journal]", or "I need a journal with IF around X".

CRITICAL: Use for ownership/borrow/lifetime issues. Triggers: E0382, E0597, E0506, E0507, E0515, E0716, E0106, value moved, borrowed value does not live long enough, cannot move out of, use of moved value, ownership, borrow, lifetime, 'a, 'static, move, clone, Copy, 所有权, 借用, 生命周期

Scaffold a production-ready Litestar 2.x application with class-based controllers, DTOs, guards, SQLAlchemy plugin, and auto-generated OpenAPI docs.

Cross-reference recently shipped tickets against your help center and changelog to detect outdated articles, missing documentation, and undocumented features. Suggests updates and writes draft copy where possible. Use after each release or on a weekly cadence.

Read lost deals and churned accounts from your CRM, extract reasons clustered by theme (missing features, pricing, competitors, UX), and write a prioritized weekly analysis with product improvement recommendations. Use before roadmap planning or to build the case for prioritizing retention work.

Fetch GitHub issues, spawn sub-agents to implement fixes and open PRs, then monitor and address PR review comments. Usage: /gh-issues [owner/repo] [--label bug] [--limit 5] [--milestone v1.0] [--assignee @me] [--fork user/repo] [--watch] [--interval 5] [--reviews-only] [--cron] [--dry-run] [--model glm-5] [--notify-channel -1002381931352]

Claude Codeスキル（SKILL.md）の設計・作成・バリデーション・レビュー。 Anthropic公式ガイド(2026-03)準拠。新規スキル作成、既存スキルの改善、 description品質チェック、トリガーテスト設計に使用。 「スキル作って」「スキル設計」「SKILL.md作成」「スキルレビュー」で起動。 Do NOT use for: スキルの実行・呼び出し（それは各スキル自体が行う）。

Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".

Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".

Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".