“spec-driven development”

WHAT - Default development workflow, task lifecycle, DoR, DoD, validation, and evidence model when a project has no explicit override.

You MUST activate this skill when working on Python projects

开发或修改前端页面、交互和样式时使用；复用项目已有组件与主题，按职责组织代码，隔离数据及业务操作，保持正式页面与已获授权原型的一致性。不自动制作原型。

Event-driven — sourcing, CQRS, saga, idempotency, schema registry.

Build, deploy, run, and benchmark Filament binaries on connected Android devices or emulators.

Create, modify and validate Apify Actors with scoped inputs, storage schemas, runtime logic and deployment review.

Design and build LLM-powered projects from ideation through deployment.

WHEN to auto-invoke: Creating API routes, building endpoints, adding route.ts files, implementing REST/GraphQL APIs, adding authentication to APIs, rate…

Use when a task can be isolated into a fresh-context subagent or parallelized safely, and its result needs review against the original requirements.

Build a clearly identified .NET proof of concept or experiment to test technical feasibility.

Turn a big or ambiguous technical task into a spec of independently verifiable slices, implement slice-by-slice with verification gates, and close the spec…

Drive performance optimizations through a disciplined measure-optimize-measure cycle.

Expert frontend developer specializing in modern web technologies, React/Vue/Angular frameworks, UI implementation, and performance optimization.

LLM app development with RAG, prompt engineering, vector databases, and AI agents

Treat project context as a managed artifact alongside code.

This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent…

Implement Monica Blazor and MudBlazor v9 components, pages, themes, CSS isolation, local assets, browser storage, and async component lifecycle.

Architect-posture skill for ongoing work on an existing project.

Use for Rho implementation, package-boundary changes, or authored Rmd test workflows.

A comprehensive skill for Rust development that combines error handling, testing, and logging patterns.

Use when a request is vague, requirements are unclear, or a feature should be specified before planning or coding.

Complete guide for authoring LCP tool sets: binding discovery, AST schema generation, execution contract, host configuration injection, human-in-the-loop…

Use when implementing any feature or bugfix, before writing implementation code

Safely create skills or tools and extend UnrealAgentTools itself using live registry capabilities, source tools/external coding agents, builds, and validation.