Discovers and invokes agent skills. Use when starting a session or when you need to discover which skill applies to the current task. This is the meta-skill that governs how all other skills are discovered and invoked.

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

Classify germline variants from VCF/BCF files according to the ACMG/AMP 2015 28-criteria evidence framework and generate clinical-grade interpretation reports with per-variant evidence audit trails and ACMG SF v3.2 secondary findings screening.

Use when users need visual direction, interface hierarchy, layout decisions, design specifications, or prototypes before implementing a Web or mini program UI.

Converts PyTorch models (e.g. ResNet, timm, HuggingFace transformers) directly to LiteRT (.tflite) flatbuffer format. Use when converting PyTorch models to TFLite, setting up export environments, or troubleshooting torch-to-litert conversion bugs. Don't use for ONNX exports or converting existing TensorFlow models.

Frontend specialist for React, Next.js, TypeScript with FSD-lite architecture, shadcn/ui, and design system alignment. Use for UI, component, page, layout, CSS, Tailwind, and shadcn work.

Use for advertisements, branded films, and product storytelling that need audience hook logic, benefit framing, desire construction, and concise conversion-oriented visual messaging.

Model software around the business domain using bounded contexts, aggregates, and ubiquitous language. Use when the user mentions "domain modeling", "bounded context", "aggregate root", "ubiquitous language", "anti-corruption layer", "context mapping", "domain events", "strategic design", "the code doesnt match the business", or "how do we split this big system". Also trigger when breaking a monolith into services, defining service boundaries, or aligning code structure with business processes. Covers entities vs value objects, domain events, and context mapping strategies. For architecture layers, see clean-architecture. For complexity, see software-design-philosophy.

Update Chatto Go and frontend dependencies within their compatible version ranges, then run tests.

Control Eight Sleep pods (status, temperature, alarms, schedules).

Use when the user asks to "optimize for AI citations"; improves citation readiness for ChatGPT, Perplexity, AI Overviews, Gemini, and Claude. Not for structural on-page SEO — use on-page-seo-checker; not for net-new drafting — use content-writer. AI引用优化/GEO优化/AI搜索

Design new Claude skills from structured idea specifications. Use when the skill auto-generation pipeline needs to produce a Claude CLI prompt that creates a complete skill directory (SKILL.md, references, scripts, tests) following repository conventions.

Use this skill when you need to write, review, or debug automated tests for applications built on the Jazz framework. This skill provides the correct architectural patterns for simulating local-first synchronization and multi-user environments without resorting to invalid mocking strategies.

Use this skill when designing data schemas, implementing sharing workflows, or auditing access control in Jazz applications. It covers the hierarchy of Groups, Accounts, and CoValues, ensuring data is private by default and shared securely through cascading permissions and invitations.

Curate an Oracle Forms modernization feature by reconciling extracted Oracle evidence, linked screenshots, a running target mockup, its Next.js implementation, existing canonical requirements, and accepted target architecture. Use when a target mockup must be converted or incrementally enriched into a review-ready feature requirement package plus an evidence-backed server-side implementation specification covering UI-to-data mappings, LOVs, validations, detailed decision rows for Delete, Add, Edit, and other operations, Oracle-constraint-to-application-message translations, transactions, tab dependencies, APIs, errors, security, and acceptance scenarios without inventing unsupported physical mappings.

Guides systematic root-cause debugging. Use when tests fail, builds break, behavior doesn't match expectations, or you encounter any unexpected error. Use when you need a systematic approach to finding and fixing the root cause rather than guessing.

Use for frontend architecture boundaries: code ownership, directory roles, file placement, import direction, UI/component extraction, API/data contracts, fetching/query, URL state, mappers/schemas/DTOs, hooks/stores, architecture docs, and tool enforcement. Also use before agent-initiated architecture-enforcement changes in lint, CI, import-boundary checks, or similar automation—even without a user request—and for small UI changes that may leak business rules or external data into lower-level code.

Transforms business analyses into epics, features, and tech-agnostic success criteria. Creates handoff documents for the architect. Use this skill when the user mentions "Requirements", "RE", "Define Features", "Create Epics", "User Stories", "Requirements", "Success Criteria", "NFRs", "ASRs", "Acceptance Criteria", or similar. Also when a BA document exists and the next step is the formalization of requirements.

问数端到端编排（native CLI 版）：从候选 KN 选定知识网络，用 bkn object-type 发现对象类与字段， 由编排层 LLM 生成 SQL，再由 ontology dataview query 执行取数； 最后输出中文结论与口径说明。 当用户需要指标、统计、趋势、SQL 取数或数据查询时使用。

Implement an approved new-project slice and report actual checks. For changes to an existing app use vibe-change.