Loading...
Loading...
Found 33 Skills
Builds features based on Jobs-to-be-Done theory using Bob Moesta's frameworks. Use when designing features, identifying customer jobs, understanding push/pull forces, or uncovering hidden needs beyond stated feature requests.
Implementation guide for new Streamlit features. Use when adding new elements, widgets, or features that span backend, frontend, and protobufs.
Fast Track for Feature Process - When requirements are clear and scope is small, skip the complete design process, write a compact {slug}-design.md, and proceed directly to implementation after one confirmation from the user. What is compressed is divergent discussions and phased reviews, not quality standards - code pointers, acceptance criteria, etc., must not be omitted. Trigger scenarios: User says "quick mode", "fastforward", "cut the steps", "just start working". Not suitable for complex features involving cross-subsystem integration, new terminology sorting, or more than 4 promotion steps - in these cases, proactively inform the user to revert to the complete process.
Enter this sub-process when developing new features — turn the vague idea of "adding X capability" into a closed-loop acceptance process, with solution files archived so that both AI and users can later check what was thought and why decisions were made at that time. Trigger scenarios are focused on new capabilities ("develop new features", "add X", "implement XX") and do not address bugs in existing code. This skill only handles routing, deciding which next step to take among brainstorm / design / fastforward / implement / acceptance based on existing artifacts.
Breaks down feature requests into sequential, implementable tasks with code changes under 50 lines each. Use when planning new features, refactors, or multi-step changes to ensure logical ordering and no broken intermediate states.
Transform code, issues, or context into a detailed prompt/context for another LLM to fix or implement. Use when preparing comprehensive context for external LLM assistance, bug fixes, improvements, or feature implementations. Provides detailed context without implementation suggestions, letting the receiving LLM decide how to implement solutions. Focuses on "what" (problem, requirements, current state) not "how" (implementation approach).
Implement a plan or feature. Use when the user has a defined plan ready to be coded.
Guide feature development with architecture patterns for any tech stack. Covers frontend, backend, full-stack, and automation projects. Use when adding new features, modifying systems, or planning changes.
Creates new OrchardCore modules with proper structure, manifest, startup, and patterns. Use when the user needs to create a new module, add content parts, fields, drivers, handlers, or admin functionality.
Use when starting new feature work to create isolated git worktrees with smart directory selection and safety verification. Keeps main branch clean while developing.
Use when developing a new feature, fixing a bug, or making significant code changes - guides the full cycle from planning through verified commit with expert review
一个全面、结构化的特性开发工作流程，包含代码库探索、架构设计、质量审查和实现等专门阶段。在构建需要以下条件的新特性时使用：（1）在做出更改之前了解现有代码库，（2）通过系统性的提问澄清模糊的需求，（3）在实现之前设计周到的架构，（4）通过多维度的代码审查确保质量。非常适合涉及多个文件、需要架构决策、包含复杂集成或需求有些不明确的功能特性。