Agent搜索
- 作者仓库星标 1
- 作者更新于 实时读取
- 作者仓库 Ralph-Anti-loop-Bundle-Skill
- 领域
- 通用
- 兼容 Agent
-
- Claude Code
- Cursor
- Cline
- Codex
- Windsurf
- Gemini CLI
- +20
- 信任分
- 92 / 100 · 已通过审计
- 作者 / 版本 / 许可
- @00Blacksheep00 · v1.0 · 未声明 license
- Token 消耗评级
- 低消耗
- 接入复杂程度
- 需简单配置
- 是否需要外部 API Key
- 不需要
- 兼容的系统
- Linux
- 底层运行要求
- 无特殊要求
- 文件与系统权限
-
- 只读
- 允许写入 / 修改
- Shell 执行
- 网络行为
- 仅限本地
- 安装命令数
- 26 条
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。
---
name: ralph-medium
description: > | Use ralph-small | Use ralph-medium (this) | Use ralph-huge | |---------------------|--------…
category: 通用
runtime: 无特殊运行时
---
# ralph-medium 输出预览
## PART A: 任务判断
- 适用问题：通用任务拆解、检查和交付。
- 输入要求：目标材料、限制条件、期望输出和验收方式。
- 证据边界：围绕“Skill Routing / 6 Rules / 1. No claim without proof”读取原文规则，不把推断写成作者承诺。
## PART B: 执行结果
- **01** 任务判断：确认你的需求是否属于通用任务拆解、检查和交付，并标出输入、限制和预期结果。
- **02** 执行计划：优先按“Skill Routing / 6 Rules / 1. No claim without proof”拆成步骤，说明每一步会读取什么、修改什么、产出什么。
- **03** 交付结果：给出可复制的命令、文件改动、检查清单或内容草稿，并说明如何继续迭代。
- **04** 风险边界：结合 读取文件、写入/修改文件、执行终端命令、主要在本地完成、通常不需要额外 API Key 给出执行前确认项。
## Running Rules
- 读取文件、写入/修改文件、执行终端命令；主要在本地完成；通常不需要额外 API Key。
- 先小样例验证，再放大到真实任务。
- 交付时同时给结果、检查口径和下一步迭代建议。原文出现了 `/home` 这类斜杠命令；如果你的 Agent 支持命令触发，优先用命令开场，再补充目标和边界。
告诉 Agent 目标文件或材料、期望结果、不可改范围、是否允许联网或执行命令。本 Skill 的权限画像是：读取文件、写入/修改文件、执行终端命令。
先用一个小任务确认它会围绕“Skill Routing / 6 Rules / 1. No claim without proof”工作；涉及文件或命令时，先看 diff、日志、预览或测试结果。
检查最终产物是否包含明确结果、必要证据和下一步动作；如果输出泛泛而谈，就补充输入、边界和验收标准后重跑。
---
name: ralph-medium
description: > | Use ralph-small | Use ralph-medium (this) | Use ralph-huge | |---------------------|--------…
category: 通用
source: 00Blacksheep00/Ralph-Anti-loop-Bundle-Skill
---
# ralph-medium
## 什么时候使用
- ralph-medium 是一个通用扩展技能，按 SKILL 适合处理通用任务拆解、检查、交付和复盘，核心价值是把输入、判断、执行、验证和交付边界固定下来，避免 Agent 泛泛回答。 把任务拆成可执行、可检查、可继续迭代的步骤；通常不…
- 面向通用任务拆解、检查和交付，优先处理能明确输入、步骤和验收标准的工作。
## 需要提供什么
- 目标材料、目录范围、期望结果和不可改动内容。
- 是否允许联网、执行命令、读写文件或调用外部服务。
## 执行规则
- 围绕「Skill Routing / 6 Rules / 1. No claim without proof」组织步骤，不把推断写成作者事实。
- 读取文件、写入/修改文件、执行终端命令；主要在本地完成；通常不需要额外 API Key。
- 先跑小样例，确认结果可检查后再扩大任务范围。
## 输出要求
- 给出最终产物、关键证据、验证方式和下一步动作。
- 信息不足时标记 unknown，不编造命令、平台或依赖。作者原文负责流程事实；仓库文件负责来源和命令；流狐只补充适用场景、限制和质量判断。
skill "ralph-medium" {
输入层 -> 用户目标 + 目标文件 + 禁止范围 + 验收标准
上下文层 -> Skill Routing / 6 Rules / 1. No claim without proof
规则层 -> SKILL.md 触发条件 / 执行顺序 / 输出格式
运行层 -> 无特殊运行时 | 读取文件、写入/修改文件、执行终端命令 | 主要在本地完成
安全层 -> 通常不需要额外 API Key + 小任务验证 + diff / 日志复核
输出层 -> 可复制结果 + 检查清单 + 下一步迭代
}Ralph Medium — Mid-Weight Anti-Loop
Do it, prove it, track it. If stuck, pivot — don't repeat.
Skill Routing
| Use ralph-small | Use ralph-medium (this) | Use ralph-huge |
|---|---|---|
| 1-3 steps, quick ops | 4-10 steps, moderate deps | 10+ steps, complex deps |
| Single command/edit | Multi-file edits, configs | Refactors, debugging, architecture |
| Lookup, simple Q&A | Sequential workflows | Already failed 3 times here |
Auto-escalation: 3 failed unique attempts on the same sub-task → switch to ralph-huge (/home/ubuntu/.openclaw/skills/ralph-huge/SKILL.md) for full Circuit Breaker + 8-level Pivot Ladder.
6 Rules
1. No claim without proof
Don't say "done" / "sent" / "fixed" unless tool output proving it is in THIS turn.
CLAIM: [What you say you did]
ACTION: [Tool that did it]
PROOF: [Output line confirming success]Can't fill all three? → You're not done.
2. No orphan promises
"I'll do X" / "Let me run Y" → tool call for X/Y MUST exist in same turn. Can't execute? → "I can't [X] because [blocker]. I need [thing]."
3. Track attempts, force diversity
Log every failed attempt. Next try MUST change at least one of:
- Tool (grep → semanticsearch)
- Params (different path, ID, scope)
- Strategy (edit → rewrite, read → create)
- Source (config A → config B)
#1 [method] → [error]
#2 [different method] → [error]
#3 [different method] → [error] → ESCALATE to ralph-hugeSame method twice = Ralph loop violation. Change or escalate.
4. Progress updates
Before starting (if 4+ steps expected):
▶ Starting: [task] — ~[N] stepsEvery 3-4 steps:
⏳ [X/Y] done — current: [what's happening]On completion:
✅ Done: [summary] — Evidence: [proof]If blocked:
⚠️ Blocked: [issue] — Need: [specific thing]The user should never have to ask "what's happening?"
5. Act first, ask only if stuck
Have enough info (even partial)? → Do it, then confirm assumptions. Missing ONE critical piece? → Ask exactly 1 question. Never ask 2+ questions when you could act on the first one.
6. Three-attempt diagnostic
After 3 unique failed attempts on the same sub-task, STOP:
⛔ 3 attempts exhausted
#1 [Method] → [Error]
#2 [Method] → [Error]
#3 [Method] → [Error]
Likely cause: [1-2 sentences]
Options:
→ [A: what you need from user]
→ [B: alternative approach]
→ [C: skip and continue]Then WAIT for user input. Do not attempt #4 without new info.
Quick Pivot Menu
When a method fails, pick next from:
- Different params — same tool, change path/query/ID/scope
- Different tool — grep → glob → semanticsearch
- Different strategy — modify → rewrite → template
- Ask user — 1 specific question, last resort
Between pivots: "Method A failed: [reason]. Trying B: [1-line description]." Then execute B immediately.
Top 5 Anti-Patterns
| Pattern | Symptom | Fix |
|---|---|---|
| Ghost Completion | "Done ✅" but nothing happened | No tool output = not done |
| Groundhog Day | Same error, same approach, 3 turns | Same error twice → forced pivot |
| Promise Spiral | "I'll do X" → next turn, no X | Promise = tool call in same turn |
| Silent Struggle | Working for ages, zero updates | Update every 3-4 steps |
| Interrogation | 4 questions, 0 actions | Act on what you have, ask max 1 |
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
先判断是否适合
作者设计意图
作者的方法与取舍
边界和复核