xrk-llm
Skill140 starsChanged 8 months agoMITView on GitHub
当你需要配置/新增/排查 LLM 提供商(OpenAI/Azure/Gemini/Anthropic/Ollama/各类兼容网关)时使用;确保 YAML/Schema/代码一致。
In this repository43 other files it gives its agents.
- AGENTS.mdAGENTS.md
- docs/agents.mdAGENTS.md
- .cursor/rules/vibe-learn-craft.mdcCursor rule
- .cursor/rules/xrk-core-code.mdcCursor rule
- .cursor/rules/xrk-dev-requirements.mdcCursor rule
- .cursor/rules/xrk-infrastructure.mdcCursor rule
- .cursor/rules/xrk-project.mdcCursor rule
- .cursor/rules/xrk-third-party-plugins.mdcCursor rule
- accessibility-complianceSkill
- design-system-patternsSkill
- fronted-designSkill
- immersive-short-videoSkill
- interaction-designSkill
- mobile-android-designSkill
- mobile-ios-designSkill
- react-native-designSkill
- responsive-designSkill
- ui-ux-pro-maxSkill
- visual-design-foundationsSkill
- web-component-designSkill
- xrk-agent-runtimeSkill
- xrk-ai-workflowSkill
- xrk-app-devSkill
- xrk-authSkill
- xrk-coding-styleSkill
- xrk-configSkill
- xrk-crawlSkill
- xrk-dockerSkill
- xrk-docsSkill
- xrk-github-researchSkill
- xrk-http-apiSkill
- xrk-infrastructureSkill
- xrk-mcpSkill
- xrk-node-runtimeSkill
- xrk-pluginsSkill
- xrk-project-overviewSkill
- xrk-rendererSkill
- xrk-runtime-utilSkill
- xrk-subserverSkill
- xrk-system-coreSkill
- xrk-taskerSkill
- xrk-v3-apiSkill
- xrk-www-compatSkill
The file
Files
读者:Coding Agent(工厂与配置三同步)。办事助手勿读本文件。
入口
docs/factory.md、src/factory/llm/LLMFactory.js、core/system-Core/http/ai.js、docs/harness-module-loop.md
外仓吸收三准则(必须同时满足)
- 本项目没有(无等价能力,不是「差一点」)
- 本产品有必要(QQ/多通道 AgentRuntime 真刚需,不是酷炫)
- 对方做得明显更好(可移植且更稳/更对)
不满足则不学、不融。
出站 / tool 环
slash/recipe → messages → contextWindow trim → harness continueTurn(MCP)
无 MCP 的 /v1 · 流式单次 → LLMFactory chat/chatStream(不执行工具)并行:policies + security.toolScan(approval 默认关)+ SystemContext 指纹。
群聊入口:plugin/ai.js → ChatStream.process({ mergeWorkflows });见 docs/agent-context.md。
已吸收(过三准则)
| 能力 | 来源 | 落点 |
| Agent loop / session 压缩 | XRK-Harness | @xrkseek/harness · harness-module-loop |
| Policy + 威胁扫描 + 可选审批 | opencode/goose | runtime-policy · security.* |
| Recipe / slash | goose | recipes/ · slash-commands |
| apply_edit / verify / PageRank map | aider | tools MCP |
| triggers microagents | OpenHands | trigger-microagents |
| aux / variants / reasoning budget / 重试 | goose/cline/opencode | 既有 LLM 工厂(单次补全) |
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

