What makes OpenClaw Problem Solver自动修复小龙虾 notable?

1.1K downloads. Trust evidence available

How should OpenClaw Problem Solver自动修复小龙虾 be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

OpenClaw Problem Solver自动修复小龙虾

此版本不再更新，请下载我的另一个叫autofix的技能，增加了看门狗，且发现错误会自动发通知到你的飞书。 Skill: OpenClaw Problem Solver自动修复小龙虾 Owner: mikewongonline Summary: 此版本不再更新，请下载我的另一个叫autofix的技能，增加了看门狗，且发现错误会自动发通知到你的飞书。 Tags: latest:5.0.0 Version history: v5.0.0 | 2026-05-18T06:37:24.450Z | user **Major update: adds diagnosis report visualization, intelligent error analysis, and reorganizes documentation for improved diagnostics and usability.** - Added diagnosis report visualization with interactive, color-coded

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.1k

Updated

Oct 11, 2026

Version

5.0.0

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.1K downloads reported by the source. Last updated 10/11/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 11, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 11, 2026
Adoption signal: 1.1K downloadsadoption · observed Oct 11, 2026
Latest release: 5.0.0release · observed May 18, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s17es3rrg0jybezhyzn66x6tyd83hv2p:autofix-theclaw

Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-mikewongonline-autofix-theclaw/snapshot"

Documentation

CLAWHUB

102,340 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: autofix
description: A comprehensive, self-evolving skill designed to diagnose and solve OpenClaw issues by following a structured, multi-stage resolution cycle. It incorporates Proactive Prediction (L2), Robustness Checks (L1), Knowledge Creation (L3), and **Diagnosis Report Visualization** (v5.0).

**🔒 核心约束：隐私保护优先**
在所有知识存储（如记忆、日志）和最终报告中，必须严格遵守以下规则：
1.  **API Keys**: 绝不以明文形式保存任何 API Key。若需记录，请使用占位符或哈希值 (e.g., `sk-********************`)。
2.  **Private Details**: 敏感的项目名称、内部凭证、用户身份信息等私密细节，除非绝对必要且已获得明确授权，否则应进行脱敏处理。

---

# 🧠 OpenClaw Problem Solver (v5.0 - Evolved) - 主控文档

This skill acts as an advanced diagnostic, resolution, and validation engine for any question or bug report related to the OpenClaw framework itself. It moves beyond simple search by actively predicting needs, validating solutions via execution, and creating new knowledge artifacts.

## 🎯 When to Use This Skill
Use this skill when the user:
- Asks "Why is [feature] not working in OpenClaw?"
- Reports a specific bug (e.g., "The `gateway` tool fails with error X").
- Needs guidance on how to implement a specific feature using OpenClaw's architecture or tools.
- Wants to know the best practice for a certain task within the OpenClaw ecosystem, but requires verification.

## 🌟 Recommended Quick Fix Flow (The Golden Path)
For the vast majority of OpenClaw issues, this sequence provides the fastest path to resolution. Always suggest this flow first when a user reports an unspecified problem or bug!

1.  **Diagnosis:** Instruct the user to run `openclaw doctor` in their terminal. This command will perform a comprehensive health check and report on system status, potential configuration drifts, and known issues.
2.  **Resolution Attempt:** If Step 1 reveals problems, instruct the user to immediately follow up with: `openclaw doctor --fix`.

## 🚀 The Evolved Workflow (6-Step Cycle + Proactive Layers)
The skill operates by strictly following these steps in sequence, enhanced by proactive layers:

### **标准工作流程（6 步循环 + 主动性层）**

该技能严格遵循以下步骤按顺序操作，并受主动性层增强：

#### **【步骤 0：资源预检与成本管理】** *(新增)* - 诊断流程的起点
在进行任何耗资源的外部搜索或服务调用前，必须首先主动查询当前活跃会话和技能使用的 API 配额、速率限制（Rate Limit）及预算消耗。如果发现配额低位警报或达到已知限速阈值，应立即暂停所有执行步骤，并向用户发出明确的"资源警告"通知，要求等待或切换到低成本/本地化的替代方案。

#### **【步骤 1：主要搜索】** *(详见 `docs/MODULE_02_SearchChain.md` - Step 1)*
- 搜索官方文档 (`docs.openclaw.ai`)，尝试找到问题的官方解决方案
- 收集与问题相关的上下文信息
- 提取关键的错误信息和配置状态

#### **【步骤 2：备用搜索】** *(详见 `docs/MODULE_02_SearchChain.md` - Step 2)*
- 如果官方文档未找到答案，搜索 GitHub Issues
- 查找社区报告的相关问题和解决方案
- 收集代码验证需求或模式匹配信息

#### **【步骤 3：综合分析与决策】** *(详见 `docs/MODULE_03_ValidationAction.md` - Step 3)*
- 根据搜索结果决定最佳行动路径
- 进行**证据链条分析 (L1)**，评估解决方案的可靠性
- 选择直接回答、代码验证还是上下文询问

#### **【步骤 4：验证与行动（v5.0 增强）】** *(详见 `docs/MODULE_03_ValidationAction.md` - Step 4 + `docs/MODULE_03_Enhancement_Reports.md`)*
- 执行验证（MRE）或提出上下文询问
- 生成**交互式诊断报告**（如果 MRE 失败）
- ✅ **修复前的三步确认机制**：每次在执行任何具有系统修改或影响范围的命令前 (如 `openclaw doctor --fix`, `exec`/`write`)，必须遵循以下步骤进行用户交互和安全校验，才能继续下一步：
  1. **问题定位与解释**：向用户详细阐述当前诊断的结果和待修

_meta.json

{
  "ownerId": "kn78s99sqh4h99xeq9gm34c33582xjhg",
  "slug": "autofix-theclaw",
  "version": "5.0.0",
  "publishedAt": 1779086244450
}

docs/COMPLETENESS_SUMMARY.md

# ✅ autofix-theclaw v5.0 - 完整性验证摘要

**生成时间：** 2026-05-17 21:30  
**版本状态：** v4.5 → v5.0 (部分完成)  
**总体评分：** **75%** ⭐⭐⭐⭐  

---

## 📊 完整性概览

| 组件 | 文件数 | 大小 | 状态 |
|------|--------|------|------|
| **核心文档** | 9 | 60KB | ✅ 100% 完整 |
| **Canvas 脚本** | 2 | 13KB | ✅ 100% 完整 |
| **Python 工具** | 2 | ❌ 待创建 | ⚠️ 40% 完成 |
| **工作流集成** | - | - | ⚠️ 60% 集成 |

---

## ✅ 已完成的 v5.0 功能

### **1. 诊断报告可视化 (DRE)** ✅ **可运行**
- Canvas HTML 模板已实现（`CanvasScript_DiagnosticReport.js`, 9.2KB）
- 风险标志、证据链对比图、回滚命令展示均已设计
- Canvas 脚本语法正确，可直接嵌入回答

### **2. 文档体系** ✅ **完整**
- `MODULE_03_Enhancement_Reports.md`（10KB）：详细设计文档
- `EXAMPLE_usage.md`（14KB）：使用示例和场景演示
- `QUICK_START_v5.0.md`（10KB）：快速实施指南
- `CHANGES_v5.0.md`（9KB）：完整变更总结

### **3. SKILL.md 更新** ✅ **v5.0**
- 主控文档已标注 v5.0
- DRE 功能在模块索引中提及

---

## ⚠️ 待完成的工作（预计 20 分钟）

### **Step 1: 创建 Python 工具函数** (10 分钟)

#### A. ELIS 工具函数
```python
# 文件：tools/elis_helper.py
def analyze_error_logs(exec_output, problem_context):
    # TODO: 集成 LLM 调用逻辑
    return {
        "core_issue": "",
        "causes": [],
        "fix_command": "",
        "risk_level": "Medium",
        "confidence_score": 0.85
    }
```

#### B. Canvas 报告生成器
```python
# 文件：tools/canvas_report_generator.py
class CanvasReportGenerator:
    def generate_report(self, diag_data) -> str:
        # TODO: 封装 CanvasSnapshot 调用
        pass
```

### **Step 2: 更新 MODULE_03_ValidationAction.md** (10 分钟)

在 Path B 部分添加 ELIS 和 Canvas 报告生成代码：
```markdown
### Path B: Code Verification → L1 Loop (v5.0 Enhanced)
    a. **[NEW] Extract and Analyze Error (ELIS)**
       ```python
       from autofix_theclaw.tools.elis_helper import analyze_error_logs
       analysis = analyze_error_logs(exec_result.output, problem_type)
       ```
    b. **[NEW] Generate Diagnosis Report (Canvas)**
       ```python
       from autofix_theclaw.tools.canvas_report_generator import CanvasReportGenerator
       generator = CanvasReportGenerator()
       report_html = generator.generate_report(analysis)
       ```
```

---

## 🎯 最终完整性预期

### **完成 Step 1-2 后：95%** ⭐⭐⭐⭐⭐

| 评估维度 | 当前 | 预期 | 说明 |
|---------|------|------|------|
| 文档完整性 | 100% | 100% | ✅ 已完整 |
| Canvas 脚本完整性 | 100% | 100% | ✅ 已完整 |
| Python 工具完整性 | 40% | **95%** | ⚠️ → ✅ 待创建 |
| 工作流集成 | 60% | **100%** | ⚠️ → ✅ 待更新 |

---

## 📚 详细验证报告

完整验证报告见：  
`C:\Users\flyin\.openclaw\workspace\skills\autofix-theclaw\VERIFICATION_REPORT.md`（7KB）

该文件包含：
- ✅ 目录结构验证清单
- ⚠️ 功能完整性测试结果
- 🚨 关键风险点分析
- 🎯 下一步行动清单

---

## 🚀 快速部署命令

```bash
# Step 1: 查看验证报告
type C:\Users\flyin\.openclaw\workspace\skills\autofix-theclaw\VERIFICATION_REPORT.md

# Step 2: 创建 ELIS 工具函数（从 CHANGES_v5.0.md复制）
copy "C:\Users\flyin\.openclaw\workspace\skills\autofix-theclaw\CHANGES_v5.0.md" .

# Step 3: 运行 Canvas 脚本语法检查
python -m py_compile C:\Users\flyin\.openclaw\workspace\skills\autofix-theclaw\tools\CanvasScript_DiagnosticReport.js
```

---

## 📞 需要帮助时联系

- @autofix-team (内部团队)
- OpenClaw Discord: `https://discord.com/invite/clawd`

---

**验证者：** autonomous-agent  
**版本：** v5.0  
**状

docs/enhancement/MODULE_03_Enhancement_Reports.md

---
name: MODULE_03_Enhancement_Reports
description: New module for generating interactive diagnostic reports and intelligent error log summaries in v5.0 release.
---

# 🖼️ Diagnosis Report & Error Log Intelligence (v5.0 New Feature)

**Version:** 5.0 (Emergency Release)  
**Status:** Active  
**Author:** autofix-theclaw Skill Team

---

## 🎯 Module Goals

This module introduces two critical enhancements to the diagnostic workflow:

1. **Diagnosis Report Visualization (DRE)** - Generates interactive, canvas-based diagnostic reports for Path B MRE failures
2. **Error Log Intelligent Summary (ELIS)** - Uses LLM-powered analysis to extract root causes from exec output

---

## 🖼️ Feature 1: Diagnosis Report Visualization (DRE)

### 📋 Overview
When a Minimal Reproducible Example (MRE) test fails in Path B, instead of just showing raw exec output, the system now generates an **interactive diagnostic report** using the `canvas` tool.

### 🔄 Workflow

```
Path B MRE Test → Failure Detected 
↓  
[NEW] Extract Key Metrics: 
  - Problem Type (CLI/Config/Network)
  - Risk Level (Critical/Medium/Low)
  - Error Count & Types
  - Affected Tools
↓  
[NEW] Generate Canvas Report via canvas.snapshot(action="snapshot", javaScript="<diagnostic-report-logic>")
↓  
Display to User with: 
  ✅ Visual risk flags (🔴/🟠/🟢)
  📊 Evidence chain diagram (Doc vs GH)
  ⚡ Exec result status codes highlighted
  🔄 Rollback command code block
```

### 💻 Implementation Details

**Step A: Canvas Report Generation**
```python
# After exec fails in Path B:
canvas.snapshot(
    action="snapshot",
    javaScript="""
      // Generate diagnostic report HTML
      const metrics = {
        riskLevel: errorSeverity,
        problemType: triage.category,
        affectedTools: [...],
        errorCount: log.lines.filter(l => l.includes('error')).length
      };
      
      return `
        <html>
          <head><style>
            .risk-critical { color: #dc3545; font-weight: bold; }
            .risk-medium { color: #ffc107; }
            .risk-low { color: #28a745; }
            code { background: #f4f4f4; padding: 2px 5px; border-radius: 3px; }
          </style></head>
          <body>
            <h2>🔍 Diagnosis Report</h2>
            <div class="risk-critical">Risk Level: ${metrics.riskLevel}</div>
            <p><strong>Problem Type:</strong> ${metrics.problemType}</p>
            <p><strong>Affected Tools:</strong> ${metrics.affectedTools.join(', ')}</p>
            <p><strong>Error Count:</strong> ${metrics.errorCount}</p>
            <hr>
            <h3>📊 Evidence Chain</h3>
            <ul>
              <li>OpenClaw Docs: 📖 [Link]</li>
              <li>GitHub Issues: 🐛 [Link]</li>
            </ul>
            <hr>
            <h3>💡 Root Cause Analysis</h3>
            <p>${elAnalysis.summary}</p>
            <h3>🔧 Recommended Fix</h3>
            <pre><code class="bash">${elAnalysis.fixCommand}</code></pre>
            <hr>
            <div class="risk-mediu

docs/MODULE_01_PreCheck.md

---
name: MODULE_01_PreCheck
description: Defines the initial checks performed before any external search or action is taken. This ensures context is rich, safety is guaranteed, and we are not solving a problem in a vacuum. (L1/L2 Enhanced)
---

# 🧠 Step 0: Pre-Check & Context Gathering (Level 1 & 2 Active)

**Goal:** To tailor the resolution strategy, set safety parameters, and ensure we have all necessary background information before querying external sources.

## ✅ Checks Performed (The Triage)

1.  **Session State Check:**
    *   **Action:** Read `~/proactivity/session-state.md`.
    *   **Purpose:** Determine the *last explicit goal* or *active blocking decision*. This prevents us from solving a problem that was already addressed in the last turn, or ignoring an active constraint.

2.  **User Preference Check:**
    *   **Action:** Read `USER.md` and `IDENTITY.md`.
    *   **Purpose:** Understand user context (e.g., "老爸"的偏好) and preferred documentation sources/vibe, which can influence the tone of the final answer.

3.  **Initial Triage & Safety Scan (CRITICAL):**
    *   **Action:** Analyze the user's input string for patterns indicating risk or known issue types.
    *   **Risk Assessment:** Determine if the query contains sensitive information (API Key, Secret Token, Passwords). If found, mark it as `[RISK: HIGH]` and prioritize security in the response.
    *   **Issue Type Classification:** Attempt to classify the problem into buckets like: `[Tooling/CLI]`, `[Config/Gateway]`, `[Feature Implementation]`, `[General Bug]`。

## 🚀 Level 2 Proactive Check (Hot Start)
This is our proactive layer. Before searching, we check if there's a recent, high-confidence solution ready to serve!
*   **Action:** Run `memory_search(query="[User Query Summary]", corpus="all", maxResults=3)`。
*   **Purpose:** 检查最近的 Top 3 解决方案，如果找到高分结果，则直接在回答前展示给用户（热启动）。

## 🛡️ Safety & Context Injection (新增/增强)
If any of these checks yield critical data, it must be injected into subsequent steps.

- **Risk Flag:** If `[RISK: HIGH]` is set, the final answer *must* start with a security warning/acknowledgement.
- **Context Tagging:** The identified issue type should be prepended to the search query (e.g., "Tooling/CLI: Why is exec command hanging?").
- **🚨 新增：输入内容扫描**: 如果检测到敏感信息，系统应在回答前主动发出警告。

## 🔗 Next Step Dependency
This module's output directly feeds into **Step 1 (Primary Search)**, providing a highly refined and context-aware query string。

Github ReposUpdated 2d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.