1275 个 · 按相关度排序
Query OmniRoute through A2A, a protocol for communication between agents. Get provider and model recommendations, check remaining quotas, find providers with required features, estimate request costs, and review system health.
中文简介正在准备中。当前显示英语简介。
Find available AI models across configured providers and browse a catalog that includes provider-specific variants. Inspect individual models and create or update aliases, alternative names used to refer to models.
中文简介正在准备中。当前显示英语简介。
Implement or review a managed runtime provider for NemoClaw. Check its required interfaces, activation requirements, saved provider identity, and lifecycle behavior, then report validation evidence and any remaining qualification requirements.
中文简介正在准备中。当前显示英语简介。
Read provider usage, limits, credits, and installation or configuration health through CodexBar. Returns JSON for enabled providers or a selected provider, while hiding secrets and leaving configuration and authentication unchanged.
中文简介正在准备中。当前显示英语简介。
Configure OAuth, the authorization flow used for provider sign-in, with portless development URLs. It guides callback registration and authentication library settings, helping diagnose rejected domains, redirect URL mismatches, and callbacks that point to the wrong address.
中文简介正在准备中。当前显示英语简介。
Turn a Bifrost PR or GitHub issue into API regression tests that catch recurring bugs. Review existing coverage, add cases to the Postman collection, and validate collection processing and provider filtering.
中文简介正在准备中。当前显示英语简介。
Use this when scaffolding a new Terraform provider with the Plugin Framework: workspace layout, go module setup, provider server main.go, and a provider.go with schema and Configure. Also use when a user wants to start building a provider for a new API or asks how to begin a terraform-provider-* project.
中文简介正在准备中。当前显示原文说明。
Customize Ant Design colors, spacing, corners, and typography using design tokens, shared values that control appearance. Configure global styles, individual components, dark mode, and CSS variables through ConfigProvider, and extract computed theme values when needed.
中文简介正在准备中。当前显示英语简介。
Configure HTTP, HTTPS, and SOCKS proxies for requests to external providers. Manage shared or provider-specific rules, test connections, and control proxy rotation to define which intermediary servers handle outgoing requests.
中文简介正在准备中。当前显示英语简介。
Combine all service research reports for a selected date into a local Markdown digest. Add up to five highlights to help maintainers prioritize updates, review proposed changes, and spot research errors.
中文简介正在准备中。当前显示英语简介。
Check AI watermarks through Google, OpenAI, Microsoft, or Meta verification services. The skill links results to file hashes, identifiers used to verify file integrity, and records separate evidence for each configured account and verification route.
中文简介正在准备中。当前显示英语简介。
Audit Kiln’s model list against provider APIs and catalogs to identify removed models and upcoming retirements. Get findings organized by provider, then mark affected entries as deprecated after reviewing and approving the proposed changes.
中文简介正在准备中。当前显示英语简介。
Implement AI chat behavior with useXChat, a React function for managing chat state. Connect Providers that handle API communication, manage messages and errors, regenerate or cancel replies, and support multiple conversations with separate state.
中文简介正在准备中。当前显示英语简介。
Implement AI chat behavior with useXChat, a React function for managing chat state. Connect Providers that handle API communication, manage messages and errors, regenerate or cancel replies, and support multiple conversations with separate state.
中文简介正在准备中。当前显示英语简介。
Configure XRequest for API calls and streaming responses, where data arrives in successive pieces. This skill covers request settings, authentication, debugging, and environment-specific handling of credentials for standalone requests or integration with chat providers.
中文简介正在准备中。当前显示英语简介。
Configure XRequest for AI chat API connections, authentication, and streaming responses that arrive in successive pieces. The skill explains practical request settings, connection checks, and how to keep secret keys on the server when building browser applications.
中文简介正在准备中。当前显示英语简介。
Determines the organization's role (provider, deployer, importer, distributor, or quasi-provider) and assesses Art. 25 quasi-provider risk of the EU AI Act. This skill should be used when the user asks to "determine AI Act roles", "check if we are provider or deployer", "assess quasi-provider status", "check Art. 25 substantial modification", "check value chain responsibilities", or mentions "Betreiber", "Anbieter", "wesentliche Veränderung", or finetuning implications under the AI Act.
中文简介正在准备中。当前显示原文说明。
Use when setting up providers, consuming state, optimizing rebuilds, using ProxyProvider, or migrating from deprecated providers (Provider package).
中文简介正在准备中。当前显示原文说明。
Fix Flutter home feed / main screen stuck on loading spinner after login when using Riverpod StreamProvider that watches GoRouter location changes. Use when: (1) Screen shows BrandedLoadingIndicator or CircularProgressIndicator permanently after successful auth redirect, (2) Widget watches a route-type-gating provider that returns AsyncValue.loading() intermittently, (3) Logs show route location oscillating between stale and current paths during post-login transition (e.g., /welcome/* after /home/0), (4) Provider chain has double-gate: widget gates on pageContext AND data provider also gates on pageContext. Distinct from riverpod-infinite-rebuild-loop (rapid rebuilds) — this causes permanent loading state, not infinite rebuilds.
中文简介正在准备中。当前显示原文说明。
Startup rules for the app shell, layouts, and global providers. Use when editing app/Providers.tsx, app/DeferredSingletonWrapper.tsx / DeferredSingletonCore.tsx, a layout.tsx, StoreProvider, or a global provider; adding startup fetches or mount-time useEffects high in the tree; or reading auth state (isAdmin, isGuest, fingerprintId) client-side.
中文简介正在准备中。当前显示原文说明。
为OpenClaw添加模型服务商，并通过实际回复验证连接。凭据以环境变量或文件引用的形式配置，同时验证设置并报告测试结果。
Monitor AI provider health, response times, usage quotas, and spending alerts in OmniRoute. Inspect circuit breakers, which temporarily block failing providers, and configure whether reaching a budget limit switches models, blocks requests, or issues warnings.
中文简介正在准备中。当前显示英语简介。
Manage AI service connections in OmniRoute through its API. Add, update, remove, and test connections, maintain API keys and sign-in credentials, and inspect usage metrics and connection health.
中文简介正在准备中。当前显示英语简介。
Review estimated spending, token usage, and cache hit ratios across Claude Code, Codex, and Grok using local logs. Filter by time, project, or provider, while keeping currencies separate and identifying models without pricing.
中文简介正在准备中。当前显示英语简介。