拉尔夫·路由器

其他 社区 v1.0

技能解读

当前原文的自动摘译,尚未人工审校。

自动升级规则

没有超出拉尔夫巨大的升级。四次失败的独特尝试后,停止,发出诊断信息,并等待人工输入。

成功后(自我提升)

当任务在 ralph-small、ralph-medium 或 ralph-huge 下运行并且您已验证成功(同一轮中的证据)时:按照您使用的任何 Ralph 级别末尾的“结束:自我改进”部分进行操作 - 它链接到 self-improvement 和 .learnings/,而不会阻止用户回复。技能路径 (OpenClaw):/home/ubuntu/.openclaw/skills/self-improvement/SKILL.md 这是可选的,但对于重复出现的模式、不明显的修复和工具/网关陷阱来说具有很高的价值。

代理人须知

永远不要告诉用户“我正在使用 ralph-[level]”——这是内部操作细节。选择、加载、行动。用户想要的是结果,而不是选择过程的叙述。

流狐档案 运行与权限由流狐静态检查推断,不代表作者声明或实际测试结果。
领域
通用
作者声明的智能体
未找到明确声明;不据此推断已兼容或已测试
静态检查
92 / 100 · 启发式扫描,不代表运行安全
运行环境证据
未执行;当前没有隔离运行测试证据
作者 / 版本 / 许可证
@00Blacksheep00 · v1.0 · 未声明许可证
上下文用量评级
低消耗
接入复杂程度
即装即用
是否需要外部接口密钥
不需要
兼容的系统
Linux
运行环境要求
未检出明确要求
检测到的文件与系统行为
  • 只读
  • 允许写入 / 修改
网络行为
仅限本地
安装命令数
无(仅作为资料)

需要注意: 未声明工具权限范围;实际权限由运行环境决定。

作者说明文件(原文) SKILL.md

# Ralph Router — Automatic level selection

> Before you act, pick the right level. Never start a task without loading the correct skill.

---

## Decision tree

```
I receive a task.
│
├─ How many steps do I expect?
│    │
│    ├─ 1–3 steps / single operation / lookup / quick edit
│    │    └─ → Load ralph-small
│    │         Path: /home/ubuntu/.openclaw/skills/ralph-small/SKILL.md
│    │
│    ├─ 4–10 steps / sequential workflow / moderate dependencies
│    │    └─ → Load ralph-medium
│    │         Path: /home/ubuntu/.openclaw/skills/ralph-medium/SKILL.md
│    │
│    └─ 10+ steps / debugging / refactor / architecture / high complexity
│         └─ → Load ralph-huge
│              Path: /home/ubuntu/.openclaw/skills/ralph-huge/SKILL.md
│
├─ Unsure about complexity?
│    └─ → Err on the side of more discipline. Prefer ralph-medium on a simple task
│         over ralph-small on a task that turns out complex.
│
└─ Already using ralph-small or ralph-medium and exhausted attempts?
     └─ → Escalate to the next level immediately.
          Do not wait. Do not retry the same tier. Escalate.
```

---

## Automatic escalation rule

```
ralph-small  →  2 failed attempts  →  ralph-medium
ralph-medium →  3 failed attempts  →  ralph-huge
ralph-huge   →  4 failed attempts  →  Circuit breaker + wait for user
```

**There is no escalation beyond ralph-huge.** After four failed unique attempts, stop, emit the diagnostic, and wait for human input.

---

## After success (self-improvement)

When the task was run under **ralph-small**, **ralph-medium**, or **ralph-huge** and you have **verified** success (evidence in the same turn):

- Follow the **Closure: self-improvement** section at the end of whichever Ralph level you used — it links to **`self-improvement`** and `.learnings/` without blocking the user reply.
- Skill path (OpenClaw): `/home/ubuntu/.openclaw/skills/self-improvement/SKILL.md`

This is optional but high-value for recurring patterns, non-obvious fixes, and tool/gateway gotchas.

---

## Note for the agent

Never tell the user “I’m using ralph-[level]” — that is internal operations detail.
Select, load, act. The user wants outcomes, not narration of your selection process.

讨论

基于 GitHub Discussions。登录 GitHub 即可参与讨论、点赞、订阅更新。