xrk-llm — for Claude Code xrk-llm, XRK-AGT, community, for Claude Code, ide skills, *_llm.yaml, *_compat_llm.yaml, commonconfig, openai, azure_openai

v1.0.0

关于此技能

适用场景: Ideal for AI agents that need 工厂:src/factory/llm/llmfactory.js. 本地化技能摘要: xrk-llm helps AI agents handle repository-specific developer workflows with documented implementation details.

功能特性

工厂:src/factory/llm/LLMFactory.js
OpenAI Chat 协议工具:src/utils/llm/openai-chat-utils.js
v3 网关:core/system-Core/http/ai.js(POST /api/v3/chat/completions)
Provider 选择规则(对外约定)
v3 请求体里的 model: 填 provider key (例如 openai、azure openai、ollama-local)。

# 核心主题

sunflowermm sunflowermm
[131]
[12]
更新于: 4/29/2026

Killer-Skills Review

Decision support comes first. Repository text comes second.

Reference-Only Page Review Score: 8/11

This page remains useful for teams, but Killer-Skills treats it as reference material instead of a primary organic landing page.

Original recommendation layer Concrete use-case guidance Explicit limitations and caution
Review Score
8/11
Quality Score
49
Canonical Locale
zh
Detected Body Locale
zh

适用场景: Ideal for AI agents that need 工厂:src/factory/llm/llmfactory.js. 本地化技能摘要: xrk-llm helps AI agents handle repository-specific developer workflows with documented implementation details.

核心价值

推荐说明: xrk-llm helps agents 工厂:src/factory/llm/llmfactory.js. xrk-llm helps AI agents handle repository-specific developer workflows with documented implementation details.

适用 Agent 类型

适用场景: Ideal for AI agents that need 工厂:src/factory/llm/llmfactory.js.

赋予的主要能力 · xrk-llm

适用任务: Applying 工厂:src/factory/llm/LLMFactory.js
适用任务: Applying OpenAI Chat 协议工具:src/utils/llm/openai-chat-utils.js
适用任务: Applying v3 网关:core/system-Core/http/ai.js(POST /api/v3/chat/completions)

! 使用限制与门槛

  • 限制说明: Requires repository-specific context from the skill documentation
  • 限制说明: Works best when the underlying tools and dependencies are already configured

Why this page is reference-only

  • - Current locale does not satisfy the locale-governance contract.
  • - The underlying skill quality score is below the review floor.

Source Boundary

The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.

评审后的下一步

先决定动作,再继续看上游仓库材料

Killer-Skills 的主价值不应该停在“帮你打开仓库说明”,而是先帮你判断这项技能是否值得安装、是否应该回到可信集合复核,以及是否已经进入工作流落地阶段。

实验室 Demo

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

常见问题与安装步骤

以下问题与步骤与页面结构化数据保持一致,便于搜索引擎理解页面内容。

? FAQ

xrk-llm 是什么?

适用场景: Ideal for AI agents that need 工厂:src/factory/llm/llmfactory.js. 本地化技能摘要: xrk-llm helps AI agents handle repository-specific developer workflows with documented implementation details.

如何安装 xrk-llm?

运行命令:npx killer-skills add sunflowermm/XRK-AGT/xrk-llm。支持 Cursor、Windsurf、VS Code、Claude Code 等 19+ IDE/Agent。

xrk-llm 适用于哪些场景?

典型场景包括:适用任务: Applying 工厂:src/factory/llm/LLMFactory.js、适用任务: Applying OpenAI Chat 协议工具:src/utils/llm/openai-chat-utils.js、适用任务: Applying v3 网关:core/system-Core/http/ai.js(POST /api/v3/chat/completions)。

xrk-llm 支持哪些 IDE 或 Agent?

该技能兼容 Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer。可使用 Killer-Skills CLI 一条命令通用安装。

xrk-llm 有哪些限制?

限制说明: Requires repository-specific context from the skill documentation;限制说明: Works best when the underlying tools and dependencies are already configured。

安装步骤

  1. 1. 打开终端

    在你的项目目录中打开终端或命令行。

  2. 2. 执行安装命令

    运行:npx killer-skills add sunflowermm/XRK-AGT/xrk-llm。CLI 会自动识别 IDE 或 AI Agent 并完成配置。

  3. 3. 开始使用技能

    xrk-llm 已启用,可立即在当前项目中调用。

! 参考页模式

此页面仍可作为安装与查阅参考,但 Killer-Skills 不再把它视为主要可索引落地页。请优先阅读上方评审结论,再决定是否继续查看上游仓库说明。

Upstream Repository Material

The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.

Upstream Source

xrk-llm

安装 xrk-llm,这是一款面向AI agent workflows and automation的 AI Agent Skill。查看评审结论、使用场景与安装路径。

SKILL.md
Readonly
Upstream Repository Material
The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.
Supporting Evidence

你是什么

你是 XRK-AGT 的 LLM 工厂与多运营商配置专家。你必须以“配置驱动”为第一原则:不建议硬编码,优先调整 *_llm.yaml*_compat_llm.yaml,并确保 commonconfig schema 字段与客户端实现一致。

关键入口

  • 工厂:src/factory/llm/LLMFactory.js
  • OpenAI Chat 协议工具:src/utils/llm/openai-chat-utils.js
  • v3 网关:core/system-Core/http/ai.jsPOST /api/v3/chat/completions

Provider 选择规则(对外约定)

  • v3 请求体里的 model填 provider key(例如 openaiazure_openaiollama-local)。
  • 真实模型名:写在 provider 配置 YAML 的 model/chatModel(或 Azure 的 deployment)。

配置文件地图

官方 provider(单一配置文件)

  • OpenAI:data/server_bots/{port}/openai_llm.yaml
  • Azure OpenAI:data/server_bots/{port}/azure_openai_llm.yaml
  • Gemini:data/server_bots/{port}/gemini_llm.yaml
  • (若启用)Anthropic:data/server_bots/{port}/anthropic_llm.yaml

兼容 provider(providers[] 多运营商聚合)

  • OpenAI Chat:data/server_bots/{port}/openai_compat_llm.yaml
  • OpenAI Responses:data/server_bots/{port}/openai_responses_compat_llm.yaml
  • New API:data/server_bots/{port}/newapi_compat_llm.yaml
  • CherryIN:data/server_bots/{port}/cherryin_compat_llm.yaml
  • Ollama:data/server_bots/{port}/ollama_compat_llm.yaml
  • Gemini:data/server_bots/{port}/gemini_compat_llm.yaml
  • Anthropic:data/server_bots/{port}/anthropic_compat_llm.yaml
  • Azure OpenAI:data/server_bots/{port}/azure_openai_compat_llm.yaml

Schema(前端表单字段来源)

对应文件:core/system-Core/commonconfig/*.js
原则:YAML 字段必须能在 schema 里找到;schema 提供的字段必须被代码消费。

排障清单(必须按顺序)

  1. provider key 是否存在LLMFactory.listProviders() / GET /api/v3/models
  2. v3 的 model 是否填对:应该是 provider key,不是真实模型名
  3. 端点拼接是否正确baseUrl + path(或 Azure deployment + api-version、Ollama /api/chat、Gemini :generateContent
    • OpenAI/兼容 Chat 协议:默认约定 baseUrl 已包含版本前缀(如 /v1),path 只写资源路径(如 /chat/completions/responses
  4. 认证方式是否匹配
    • OpenAI 官方:Authorization: Bearer
    • Azure:api-key
    • Anthropic:x-api-key + anthropic-version
    • Gemini:query key=...
    • 兼容网关:用 authMode(bearer/api-key/header)配置
  5. 流式开关:provider 配置 enableStream 是否禁用
  6. 工具注入(MCP)enableTools + streams 白名单(由请求体 workflow 整理出来)

文档来源(需要时引用)

  • docs/factory.md
  • docs/aistream.md(streams 白名单、MCP 注入与子服务端关系)
  • core/system-Core/http/ai.js(v3 行为权威实现)

权威入口

  • 项目概览:PROJECT_OVERVIEW.md
  • 代码入口:src/core/ 对应子目录
  • 相关文档:docs/ 下对应主题文档

适用场景

  • 需要定位该子系统的实现路径与配置入口。
  • 需要快速给出改动落点与兼容性注意事项。

非适用场景

  • 不用于替代其他子系统的实现说明。
  • 不在缺少证据时臆造路径或字段。

执行步骤

  1. 先确认需求属于该技能的职责边界。
  2. 再给出代码路径、配置路径与关键字段。
  3. 最后补充风险点、验证步骤与回归范围。

常见陷阱

  • 只给概念,不给具体文件路径。
  • 文档与代码冲突时未标注以代码为准。
  • 忽略配置、Schema 与消费代码的一致性。

相关技能

寻找 xrk-llm 的替代方案 (Alternative) 或可搭配使用的同类 community Skill?探索以下相关开源技能。

查看全部

openclaw-release-maintainer

Logo of openclaw
openclaw

本地化技能摘要: 🦞 # OpenClaw Release Maintainer Use this skill for release and publish-time workflow. It covers ai, assistant, crustacean workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

333.8k
0
AI

widget-generator

Logo of f
f

本地化技能摘要: Generate customizable widget plugins for the prompts.chat feed system # Widget Generator Skill This skill guides creation of widget plugins for prompts.chat . It covers ai, artificial-intelligence, awesome-list workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf

149.6k
0
AI

flags

Logo of vercel
vercel

本地化技能摘要: The React Framework # Feature Flags Use this skill when adding or changing framework feature flags in Next.js internals. It covers blog, browser, compiler workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

138.4k
0
浏览器

pr-review

Logo of pytorch
pytorch

本地化技能摘要: Usage Modes No Argument If the user invokes /pr-review with no arguments, do not perform a review . It covers autograd, deep-learning, gpu workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

98.6k
0
开发者工具