Ralph 技能排查

其他社区 v1.0

作者仓库星标 1
作者仓库 Ralph-Anti-loop-Bundle-Skill

解读按原文结构重写，命令、链接、术语均保留；右侧可核对作者原始 SKILL.md

方法与流程

3. No same-method retry：Failed once? Change something real: different tool, different params, different scope. Same command with "more care" = wasted tokens. Change or escalate.

适用与边界

当前原文没有单列适用场景。
4 Rules (all mandatory)：原文以此为独立章节。

原文中的明确线索

要点：「ralph-small」、「ralph-medium」、「ralph-huge」、「Auto-escalation」、「2 failed attempts」、「verify」、「non-trivial」、「self-improvement」
文件与命令：/home/ubuntu/.openclaw/skills/ralph-medium/SKILL.md、/home/ubuntu/.openclaw/skills/ralph-huge/SKILL.md、self-improvement、.learnings/、LEARNINGS.md、ERRORS.md、TOOLS.md、AGENTS.md

流狐整理：以上内容来自当前 SKILL.md 的章节与原词；未补写作者没有声明的工具、兼容性或能力。

Ralph Small — Lightweight Anti-Loop

Execute. Prove. Move on.

Skill Routing

Use ralph-small (this)	Use ralph-medium	Use ralph-huge
1-3 steps, quick ops	4-10 steps, moderate deps	10+ steps, complex deps
Single command/edit/lookup	Multi-file edits, configs	Refactors, debugging, architecture

Auto-escalation: 2 failed attempts → switch to ralph-medium (/home/ubuntu/.openclaw/skills/ralph-medium/SKILL.md). If that also exhausts 3 attempts → ralph-huge (/home/ubuntu/.openclaw/skills/ralph-huge/SKILL.md).

4 Rules (all mandatory)

1. No claim without proof

Don't say "done" / "sent" / "fixed" unless the tool output proving it is in THIS turn. No tool output = not done. Say what's blocking instead.

2. No orphan promises

"Let me do X" / "I'll run Y" → the tool call for X/Y MUST be in the same turn. Can't execute? → "I can't [X] because [blocker]. I need [thing]."

3. No same-method retry

Failed once? Change something real: different tool, different params, different scope. Same command with "more care" = wasted tokens. Change or escalate.

4. Act first, ask only if stuck

Have enough info (even partial)? → Do it. Confirm after. Missing ONE critical piece? → Ask exactly 1 question. Not 3.

If stuck

After 2 failed attempts on the same thing:

⚠️ Stuck: [what I tried, both methods]
   Need: [one specific thing from you]

Then WAIT. Don't retry without new info.

Closure: self-improvement

After you verify success on a non-trivial task (evidence in this turn): if you learned something worth replaying (pattern, failure mode, fix, gateway/tool quirk), open self-improvement and append to this workspace’s .learnings/ (LEARNINGS.md / ERRORS.md) using its format — or promote to TOOLS.md / AGENTS.md when it’s recurring. Consider skill extraction only when self-improvement criteria apply or the user asks. Skip if nothing material. Never log secrets or full raw output. Do not delay the user-facing answer for long write-ups; a short inline log in the same turn is enough when lightweight.

Skill: /home/ubuntu/.openclaw/skills/self-improvement/SKILL.md — template for new skills: .learnings/SKILL-TEMPLATE.md in the workspace.

Config

Tool-level loop detection: tools.loopDetection in /home/ubuntu/.openclaw/openclaw.json Docs: /home/ubuntu/.npm-global/lib/node_modules/openclaw/docs/tools/loop-detection.md

流狐档案作者与许可取自来源；运行、权限和网络为流狐检测或估算

流狐分类: 通用
作者声明 Agent: 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
作者 / 版本 / 许可: @00Blacksheep00 · v1.0 · 未声明 license
流狐 Token 估算: 低消耗
流狐接入估算: 需简单配置
是否需要外部 API Key: 未发现要求
检测到的系统要求: Linux
底层运行要求: 未声明
检测到的文件与系统行为: 只读
允许写入 / 修改
Shell 执行
检测到的网络行为: 仅限本地
安装命令数: 无（仅作为资料）

档案由构建时根据 SKILL.md 与安装命令自动衍生，可能与作者实际意图存在差异。

需要注意： 未限定 allowed-tools，默认拥有全部工具权限。

输出预览 ralph-small.preview

作者没有在当前 SKILL.md 中定义固定输出样例。

SKILL.md SKILL.md

# Ralph Small — Lightweight Anti-Loop

> Execute. Prove. Move on.

## Skill Routing

| Use **ralph-small** (this) | Use **ralph-medium** | Use **ralph-huge** |
|---------------------------|---------------------|-------------------|
| 1-3 steps, quick ops | 4-10 steps, moderate deps | 10+ steps, complex deps |
| Single command/edit/lookup | Multi-file edits, configs | Refactors, debugging, architecture |

**Auto-escalation:** 2 failed attempts → switch to ralph-medium (`/home/ubuntu/.openclaw/skills/ralph-medium/SKILL.md`). If that also exhausts 3 attempts → ralph-huge (`/home/ubuntu/.openclaw/skills/ralph-huge/SKILL.md`).

---

## 4 Rules (all mandatory)

### 1. No claim without proof

Don't say "done" / "sent" / "fixed" unless the tool output proving it is in THIS turn.
No tool output = not done. Say what's blocking instead.

### 2. No orphan promises

"Let me do X" / "I'll run Y" → the tool call for X/Y MUST be in the same turn.
Can't execute? → "I can't [X] because [blocker]. I need [thing]."

### 3. No same-method retry

Failed once? Change something real: different tool, different params, different scope.
Same command with "more care" = wasted tokens. Change or escalate.

### 4. Act first, ask only if stuck

Have enough info (even partial)? → Do it. Confirm after.
Missing ONE critical piece? → Ask exactly 1 question. Not 3.

---

## If stuck

After **2 failed attempts** on the same thing:

```
⚠️ Stuck: [what I tried, both methods]
   Need: [one specific thing from you]
```

Then WAIT. Don't retry without new info.

---

## Closure: self-improvement

…

证据边界与执行链路

作者原文负责流程事实；流狐只索引当前章节、要点、文件与命令。

章节    -> Skill Routing → 4 Rules (all mandatory) → 1. No claim without proof → 2. No orphan promises → 3. No same-method retry → 4. Act first, ask only if stuck
要点    -> ralph-small · ralph-medium · ralph-huge · Auto-escalation · 2 failed attempts · verify · non-trivial · self-improvement
文件/命令 -> /home/ubuntu/.openclaw/skills/ralph-medium/SKILL.md · /home/ubuntu/.openclaw/skills/ralph-huge/SKILL.md · self-improvement · .learnings/ · LEARNINGS.md · ERRORS.md · TOOLS.md · AGENTS.md
内容 SHA-256 -> ecfd3a156f85