Ensure accessibility in UI components including semantic HTML, ARIA attributes, keyboard navigation, and WCAG 2.2 AA compliance.
中文简介正在准备中。当前显示原文说明。
Svelte and SvelteKit expert including components, stores, and routing
中文简介正在准备中。当前显示原文说明。
查看安装方法安装前可以查看交给 AI 代理的指令内容。
When reviewing or writing code, apply these guidelines:
When reviewing or writing code, apply these guidelines:
When reviewing or writing code, apply these guidelines:
$:) for reactivity, e.g. bind:valueWhen reviewing or writing code, apply these guidelines:
components/auth-form.svelte).This expert skill consolidates 1 individual skills:
$:) in new code — use Svelte 5 runesload functions for data fetching in SvelteKit$state and $derived runes+error.svelte error boundaries for every route group that can fail| Anti-Pattern | Why It Fails | Correct Approach |
|---|---|---|
| Using Svelte 4 reactive syntax | Legacy patterns conflict with rune-based reactivity | Use $state(), $derived(), and $effect() runes in all new code |
| Global stores for local state | Unnecessary coupling; component state leaks | Use $state rune for component-local reactive state |
| Ignoring SvelteKit routing conventions | Manual routing breaks framework integration | Follow file-based routing; use +page.svelte and +layout.svelte |
Missing +error.svelte handlers | Unhandled route errors produce blank pages | Add +error.svelte to every route group that can fail |
| Skipping accessibility attributes | Screen readers and keyboard users cannot use the UI | Always add ARIA labels and test keyboard navigation |
Before starting:
cat .claude/context/memory/learnings.md
After completing: Record any new patterns or exceptions discovered.
ASSUME INTERRUPTION: Your context may reset. If it's not in memory, it didn't happen.
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Ensure accessibility in UI components including semantic HTML, ARIA attributes, keyboard navigation, and WCAG 2.2 AA compliance.
中文简介正在准备中。当前显示原文说明。
Use when you want to improve response quality through meta-cognitive reasoning. Applies 15+ reasoning methods to reconsider and refine initial outputs.
中文简介正在准备中。当前显示原文说明。
N-round opposing-stance debates for trade-off analysis. Assigns pro/con roles to agents, runs structured debate rounds with quality scoring, and produces a moderator synthesis with confidence-rated recommendation. Generalizable to architecture, technology, security, and design decisions.
中文简介正在准备中。当前显示原文说明。
Force adversarial code review stance that eliminates confirmation bias — reviewer must find issues or re-analyze
中文简介正在准备中。当前显示原文说明。
Creates specialized AI agents on-demand when no existing agent matches a request. Use when the Router cannot find a suitable agent for a task. Enables self-evolution by generating persistent agents.
中文简介正在准备中。当前显示原文说明。
LLM-as-judge evaluation framework with 5-dimension rubric (accuracy, groundedness, coherence, completeness, helpfulness) for scoring AI-generated content quality with weighted composite scores and evidence citations
中文简介正在准备中。当前显示原文说明。