Python Testing
edp43273-glitch
使用pytest的Python测试策略,包括TDD方法、夹具、模拟、参数化和覆盖率要求。
An agent skill is a folder of instructions, scripts and resources that an agent loads on demand. Unlike an MCP server it runs no process of its own, which makes it cheaper in context and simpler to audit.
Showing 625–648 of 935
edp43273-glitch
使用pytest的Python测试策略,包括TDD方法、夹具、模拟、参数化和覆盖率要求。
edp43273-glitch
Spring Boot架构模式、REST API设计、分层服务、数据访问、缓存、异步处理和日志记录。用于Java Spring Boot后端工作。
edp43273-glitch
SwiftUI 架构模式,使用 @Observable 进行状态管理,视图组合,导航,性能优化,以及现代 iOS/macOS UI 最佳实践。
edp43273-glitch
Vite build tool patterns including config, plugins, HMR, env variables, proxy setup, SSR, library mode, dependency pre-bundling, and build optimization. Activate when working with vite.config.ts, Vite plugins, or Vite-based projects.
edp43273-glitch
Multi-agent orchestration using dmux (tmux pane manager for AI agents). Patterns for parallel agent workflows across Claude Code, Codex, OpenCode, and other harnesses. Use when running multiple agent sessions in parallel or coordinating multi-agent development workflows.
edp43273-glitch
Formal evaluation framework for Claude Code sessions implementing eval-driven development (EDD) principles
edp43273-glitch
Frontend development patterns for React, Next.js, state management, performance optimization, and UI best practices.
edp43273-glitch
Translate PRD intent, roadmap asks, or product discussions into an implementation-ready capability plan that exposes constraints, invariants, interfaces, and unresolved decisions before multi-service work starts. Use when the user needs an ECC-native PRD-to-SRS lane instead of vague planning prose.
edp43273-glitch
Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.
edp43273-glitch
Use this skill when writing new features, fixing bugs, or refactoring code. Enforces test-driven development with 80%+ coverage including unit, integration, and E2E tests.
ajquintal
Write conversion copy in Tony's voice for one asset — a sales-page section, an email, or an ad — on the hook → problem → mechanism → offer → CTA skeleton (Hormozi value equation + Brunson hook/story/offer). DRAFTS ONLY, never sent or published. Use when you need copy that converts for a specific asset and goal. Triggers: "write copy", "sales page", "write the email", "ad copy", "landing page copy"
corticalstack
Use when implementing infrastructure as code with Terraform on Azure. Invoke for module development (create reusable modules, manage module versioning), state management (Azure Blob backend, import existing resources, resolve state conflicts), provider configuration, multi-environment workflows, and infrastructure testing.
burgebj
Reverse-engineer design systems, tokens, and components from live products or screenshots
burgebj
OpenClaw instance administration — manage hosts across macOS, Ubuntu/Debian, Docker, OCI, and Proxmox
burgebj
Auto-detect work context (Dev vs Knowledge) — use to tailor workflows based on current task type
burgebj
GitHub Copilot CLI as optional zero-cost provider via copilot -p programmatic mode
burgebj
Project remaining workflow cost from per-phase averages — warns on budget ceiling overruns
burgebj
Trace codepaths in diffs, map against tests, auto-generate missing coverage — use before shipping PRs
burgebj
Structured multi-provider AI debates between Claude and available advisors — use for critical decisions
burgebj
Debug issues methodically — use when stuck on errors, test failures, or unexpected behavior
burgebj
Environment diagnostics — check providers, auth, config, hooks, scheduler, and more
burgebj
Track project blockers, bugs, and gaps across sessions — use when issues pile up or need triage
burgebj
Run tasks in a loop until goals are met — use for iterative refinement, polling, or convergence
burgebj
Decompose large tasks across parallel agents — use for migrations, multi-file refactors, or batch work