全部能力

Expert-level JavaScript testing skill focused on writing high-quality tests that find bugs, serve as documentation, and prevent regressions. Advocates for…

Comprehensive Svelte development skill covering reactivity runes, components, stores, lifecycle, transitions, and modern Svelte 5 patterns

Turn error logs, screenshots, voice notes, and rough bug reports into crisp, developer-ready GitHub issues with repro steps, impact, and evidence.

浏览器自动化技能，支持101个工具：页面导航、元素交互、内容提取、截图、网络控制、性能监控等

Comprehensive test automation specialist covering unit, integration, and E2E testing strategies. Expert in Jest, Vitest, Playwright, Cypress, pytest, and…

Integrate Firebase AI Logic as the direct Firebase app/client SDK lane for Gemini-powered features. Use when the user needs in-app text/chat/multimodal generation, structured output, streaming, or App Check-aware Firebase app integration without a separate workflow framework. Triggers on: Firebase AI Logic, Gemini in Firebase app, Firebase AI SDK, client-side Gemini, in-app AI feature, mobile/web AI integration, and direct Firebase model integration. Route server-owned flows, tool calling, RAG, evaluation, and reusable backend orchestration to `genkit`, and route project/deploy/operator tasks to `firebase-cli`.

Use this skill when the user wants to review, audit, improve, or plan email sending best practices. This includes deliverability, inbox placement, sender reputation, consent, list hygiene, subject lines, preview text, preference centers, onboarding emails, lifecycle emails, product updates, or deciding between marketing and transactional email. It works for any email stack, but when Loops is involved, use Loops behavior and docs as the source of truth. Trigger on phrases like "email deliverability", "inbox placement", "sender reputation", "double opt-in", "unsubscribe", "subject line review", "preview text", "lifecycle emails", "onboarding emails", "product update email", "transactional vs marketing", or "email sending best practices". Do not prefer this skill for pure API implementation; use the Loops API skill for integration details.

Expert DevOps engineer for CI/CD, IaC, Kubernetes, and deployment automation. Activate on: CI/CD, GitHub Actions, Terraform, Docker, Kubernetes, Helm, ArgoCD,…

通用发布工作流。自动检测版本文件和变更日志。支持 Node.js、Python、Rust、Claude 插件和通用项目。当用户说"发布"、"release"、"新版本"、"bump version"、"push"、"推送"时使用。

Creates mock API servers for testing and development with MSW, json-server, or custom handlers. Use when users request "API mocking", "mock server", "MSW…

Use this skill when working with Agile and Scrum methodologies - sprint planning, retrospectives, velocity tracking, Kanban boards, story point estimation, backlog grooming, or team workflow optimization. Triggers on any task involving sprint ceremonies, agile metrics, user story writing, capacity planning, or continuous improvement processes.

Search, validate, and save cloud drive resources via PanSou aggregation API and local Quark desktop APP integration. This skill should be used when the user…

Configure LLM providers, use fallback models, handle streaming, and manage model settings in PydanticAI. Use when selecting models, implementing resilience, or…

Performance review and testing: evaluate Core Web Vitals, page load times, bundle sizes, runtime performance, resource optimization, and rendering efficiency…

Implement Syncfusion Blazor DataForm component for creating dynamic, data-bound forms with validation and field management. Use this when building forms in…

Turn a PR, diff, merge request, or patch stack into one evidence-first review brief. Use when the main job is deciding approve vs request-changes vs block, naming the highest-risk findings, calling out missing proof for risky paths, and routing Git cleanup, debugging, test-policy, visual-review, or repo-admin work to the right neighboring skill instead of absorbing it.

ClickHouse schema design and optimization. TRIGGERS - ClickHouse schema, compression codecs, MergeTree, ORDER BY tuning, partition key.

Comprehensive MLOps workflows for the complete ML lifecycle - experiment tracking, model registry, deployment patterns, monitoring, A/B testing, and production…

Guides the agent through setting up in-app purchases in Capacitor apps. Covers App Store Connect and Google Play Console product configuration, plugin…

Use when implementing hot reloading with Bun (--hot, --watch), HMR, or automatic code reloading during development. Covers watch mode, hot mode, and HTTP…