chat-customizations-editor(聊天定制编辑器)
io.github.microsoft/vscode/chat-customizations-editor
在开发 Chat Customizations 编辑器时使用——即用于管理 agents、技能、指令、hooks、提示词、MCP 服务器与插件的管理界面。
共 6,205 个资源
io.github.microsoft/vscode/chat-customizations-editor
在开发 Chat Customizations 编辑器时使用——即用于管理 agents、技能、指令、hooks、提示词、MCP 服务器与插件的管理界面。
io.github.google/skills/google-mobile-ads-validate
为 iOS、Android 或 Unity 项目校验其 Google Mobile Ads(GMA)SDK 集成。用于对集成了 GMA SDK 的应用做全面上线前审计,或校验单个 GMA SDK 集成检查项,如校验广告单元 ID 与广告形式、SKAdNetwork ID、聚合适配器 SDK 版本兼容性或广告预加载。
io.github.google/skills/gke-workload-security
为 Google Kubernetes Engine(GKE)应用与命名空间审计、配置并加固工作负载级安全控制。涵盖运行集群安全审计(audit_cluster.sh)、配置 Workload Identity Federation(扮演、KSA/GSA 绑定与 Pod 设置)、强制网络策略(默认拒绝与 Dataplane V2 日志)、在 GKE Sandbox(gVisor)内隔离高风险 Pod、强制 Pod Security Standard(restricted 标签),以及经由 CSI 挂载 Secret Manager 密钥(SecretProviderClass)。用于审计集群安全态势、隔离命名空间、应用 Pod 安全标准、设置 Workload Identity,或配置网络策略与密钥卷挂载时。不用于集群级控制平面安全、RBAC 加固、Binary Authorization、Shielded Nodes 或平台级 GKE 附加组件启用(改用 gke-platform-security)。
io.github.openai/codex/openai-docs
用于 Codex 模型/定价、定时任务、skills、设置、安装、排障、定制、自动化与自我知识——包括指代 Codex 的“you”“your”“this app”“this coding agent”——以及 OpenAI API/产品与 ChatGPT Work 的问题。也用于模型选型/迁移、prompt 撰写、SDK、Responses、Realtime、agents、evals 以及 Chat/Work/Codex 的对比。仅提到 Codex 的普通应用/软件任务不适用。
io.github.garrytan/gstack/setup-browser-cookies
把真实 Chromium 浏览器中的 cookie 导入到无头浏览会话。(gstack)
io.github.higress-group/higress/nginx-to-higress-migration
在 Kubernetes 环境中从 ingress-nginx 迁移到 Higress。适用于(1)分析现有 ingress-nginx 配置(2)读取 nginx Ingress 资源与 ConfigMap(3)通过 helm 安装 Higress 并正确设置 ingressClass(4)识别不受支持的 nginx annotation(5)为 nginx snippets/高级特性生成 WASM 插件(6)构建自定义插件并推送到镜像仓库。支持完整迁移工作流,含兼容性分析。
io.github.supabase/supabase/studio-queries
Supabase Studio 数据获取的 React Query 规范。在 apps/studio/data/ 下编写或评审 query hook、mutation hook 或 query key 时使用,包括为新接口或资源加首个 fetch 或 mutation。涵盖 queryOptions 模式、keys.ts 结构、mutation hook 模板与命令式 fetch。
io.github.docling-project/docling/docling
用 Docling 理解任意受支持格式文档的内容——PDF(原生数字或扫描件)、DOCX、PPTX、XLSX、HTML、Markdown、AsciiDoc、CSV、图片、音频与 XML——把它们统一转换为 DoclingDocument(Markdown 或结构化 JSON)。当你需要读取、解析、转换、提取或切分无法直接阅读的文档时使用,例如“这份 PDF 里有什么”“转成 markdown”“提取表格”“为 RAG 切块”“读这份扫描文档”“解析这个 DOCX/PPTX”。涵盖 docling CLI、Python SDK(DocumentConverter 与 PipelineOptions)、远程 Service Client(自托管或托管的 docling-serve),以及用于最小依赖体积的 docling-slim install extras。
io.github.ruvnet/ruflo/ruvllm-runtime
Tell apart and check the RuVLLM packages — the WASM add-on behind ruvllm_* tools, the @ruvector/ruvllm 4.1 native runtime and the GPU-loop harness. Use when ruvllm_status shows a backend unavailable or an install resolved the broken 4.0.x.
io.github.ruvnet/ruflo/vector-setup
First-run setup for ruvector@0.3.13 — installs ONNX/Brain/SONA add-ons, registers the MCP server, and verifies the install via `doctor`
io.github.getsentry/sentry/generate-snapshot-tests
Generate visual snapshot test files for Sentry frontend React components. Use for testing appearance changes such as colors, spacing, typography, CSS min/max sizing, responsive layout, and visual variants, or when asked to "generate snapshot tests", "create visual snapshots", "add visual regression tests", or "snapshot this component". Accepts an optional component path or name via $ARGUMENTS.
io.github.getsentry/sentry/react-testing
使用 Jest 与 React Testing Library 为 Sentry 前端编写和审查 React/TypeScript 测试。在 static/ 中新增或编辑测试(*.spec.tsx)、编写组件/hook 测试、用 MockApiClient 模拟 API 响应、测试路由或网络请求,或被要求“write a frontend test”“add a React test”“test this component”“fix a flaky RTL test”时使用。
io.github.code-yeongyu/oh-my-openagent/frontend
构建、样式化并打磨 Web UI/UX。适用于任何前端、页面、组件、样式、布局、动画或视觉质量任务,或当被要求让界面呈现特定观感与手感时。
io.github.code-yeongyu/oh-my-openagent/refactor
以恰当的拆解方式引导重构、清理或重组。当用户要求重构、简化、抽取或现代化代码时使用。
io.github.berriai/litellm/rust-python-boundary
Decide where Python-shaped input becomes typed Rust in litellm-rust. Use when reading config.yaml values, os.environ/ references, REDIS_* or other environment layering, get_secret fallbacks, or kwargs and objects handed over from Python, when coercing text to a bool, int or float the way Python does, or when adding a dependency on litellm-python-compat
io.github.NousResearch/hermes-agent/inspecting-hermes-desktop-dom
Read the live Hermes desktop DOM/CSS over CDP.
io.github.ruvnet/ruflo/fast-code-edits
Local, millisecond code edits with no LLM call: deterministic codemods (hooks_codemod) and snippet merges into large files (hooks_fast-apply, agent-booster). Use when: mechanical transforms across many files (var-to-const, remove-console, add-logging), or merging a rewritten function into a big file. Skip when: the change needs reasoning (types, error handling, refactors).
io.github.microsoft/playwright/playwright-dev
讲解如何开发 Playwright——添加 API、MCP 工具、CLI 命令与引入 vendor 依赖。
io.github.pytorch/pytorch/pr-review
Review PyTorch pull requests for code quality, security, and backward compatibility. Use when reviewing PRs, when asked to review code changes, or when the user mentions "review PR", "code review", or "check this PR".
io.github.cheaper-inference/OmniRoute/omni-models
Query available AI models across all configured providers. List models, resolve model aliases, and browse the full model catalog including provider-specific variants.
io.github.cheaper-inference/OmniRoute/omni-cli-tools
Manage CLI tool integrations exposed via the API. List, configure, and invoke CLI tool plugins that extend OmniRoute's automation surface.
io.github.cheaper-inference/OmniRoute/ponytail
External agent skill (MIT, github.com/DietrichGebert/ponytail). Forces the laziest solution that actually works: question whether the task needs to exist at all (YAGNI), reuse what is already in the codebase, reach for the standard library before custom code, native platform features before dependencies, one line before fifty. Climb the ladder on every coding task — writing, adding, refactoring, fixing, reviewing, or designing code, and choosing libraries or dependencies. Supports intensity levels: lite, full (default), ultra. Never cut validation, error handling, security, or accessibility.
io.github.cheaper-inference/OmniRoute/config-codex-cli
Step-by-step agent workflow to configure the OpenAI Codex CLI on any machine (Linux, macOS, Windows) to use OmniRoute as an OpenAI-compatible backend. Detects OS and shell, writes config.toml and 7 named profiles, sets environment variables, and verifies the setup.
io.github.cheaper-inference/OmniRoute/cli-mcp
Inspect the MCP server status, list registered tools and scopes, run tool invocations, and manage MCP audit logs from the CLI.