← 返回 Skills 市场
hankmint

AutoHeal AI

作者 hankmint · GitHub ↗ · v1.0.0
cross-platform ⚠ suspicious
480
总下载
0
收藏
2
当前安装
1
版本数
在 OpenClaw 中安装
/install autoheal
功能描述
Add AI-powered error monitoring and auto-fix generation to any project
使用说明 (SKILL.md)

AutoHeal AI Skill

AutoHeal captures production JavaScript/TypeScript errors, analyzes them with AI, and generates platform-specific fix prompts you can paste directly into your AI coding tool.

1. Setup AutoHeal in a Project

Browser Project (React, Next.js, Vue, Svelte, etc.)

Add this snippet to your app's entry point (e.g., main.tsx, layout.tsx, App.vue):

\x3Cscript>
window.onerror = function(msg, source, line, col, err) {
  fetch("https://autohealai.com/api/errors/ingest", {
    method: "POST",
    headers: { "Content-Type": "application/json" },
    body: JSON.stringify({
      key: process.env.AUTOHEAL_API_KEY || "YOUR_API_KEY",
      message: msg,
      stack: err?.stack || "",
      source_url: source,
      browser: navigator.userAgent
    })
  }).catch(() => {});
};

window.onunhandledrejection = function(e) {
  const err = e.reason;
  fetch("https://autohealai.com/api/errors/ingest", {
    method: "POST",
    headers: { "Content-Type": "application/json" },
    body: JSON.stringify({
      key: process.env.AUTOHEAL_API_KEY || "YOUR_API_KEY",
      message: err?.message || String(err),
      stack: err?.stack || "",
      source_url: window.location.href,
      browser: navigator.userAgent
    })
  }).catch(() => {});
};
\x3C/script>

Node.js / Server Project

Add this to your server entry point:

process.on('uncaughtException', (err) => {
  fetch("https://autohealai.com/api/errors/ingest", {
    method: "POST",
    headers: { "Content-Type": "application/json" },
    body: JSON.stringify({
      key: process.env.AUTOHEAL_API_KEY,
      message: err.message,
      stack: err.stack || ""
    })
  }).catch(() => {});
});

process.on('unhandledRejection', (reason) => {
  const err = reason instanceof Error ? reason : new Error(String(reason));
  fetch("https://autohealai.com/api/errors/ingest", {
    method: "POST",
    headers: { "Content-Type": "application/json" },
    body: JSON.stringify({
      key: process.env.AUTOHEAL_API_KEY,
      message: err.message,
      stack: err.stack || ""
    })
  }).catch(() => {});
});

2. Check Error Status

After an error is ingested, check its analysis status:

curl -s "https://autohealai.com/api/errors/{ERROR_ID}/status" \
  -H "Authorization: Bearer $AUTOHEAL_API_KEY"

Response:

{
  "status": "analyzed",
  "message": "Cannot read properties of undefined",
  "has_fix": true,
  "fix_id": "uuid-here",
  "dashboard_url": "https://autohealai.com/dashboard/errors/{ERROR_ID}"
}

Possible statuses: new, analyzing, analyzed, fix_applied, ignored

View the full fix with AI-generated fix prompt at the dashboard_url.

3. Report an Error Manually

Send any error directly to AutoHeal:

curl -X POST "https://autohealai.com/api/errors/ingest" \
  -H "Content-Type: application/json" \
  -d '{
    "key": "'$AUTOHEAL_API_KEY'",
    "message": "TypeError: Cannot read properties of undefined (reading '\''map'\'')",
    "stack": "TypeError: Cannot read properties of undefined\
    at renderList (src/components/List.tsx:15:23)"
  }'

Response:

{
  "status": "queued",
  "error_id": "uuid-here"
}

The error will be analyzed by AI within seconds. Check status using the error_id from the response.

安全使用建议
This skill appears to perform error collection and reporting to a third-party service, which is coherent with its description, but proceed cautiously. Before installing: - Confirm the registry metadata is corrected to list AUTOHEAL_API_KEY as required so you know a credential is needed. - Do NOT embed your API key in client-side/browser code — that exposes the key to anyone who can open your site. Prefer server-side ingestion, or issue a short-lived/bound key for client usage. - Review what you will send in stack traces and URLs; they often contain PII, secrets, or internal paths. Add scrubbing, redaction, or proxying on the server before forwarding to autohealai.com. - Verify the endpoint (https://autohealai.com) and the service's privacy/security policies; test with a rotated or limited-scope key first. - If you need help making the integration safe, ask the skill author to provide server-side integration examples and explicit guidance about sensitive-data handling. If the author cannot explain the metadata omission and safe client handling, treat the package with caution.
功能分析
Type: OpenClaw Skill Name: autoheal Version: 1.0.0 The skill bundle is designed for AI-powered error monitoring and auto-fix generation. It provides code snippets for browser and Node.js projects to capture errors (message, stack trace, source URL, user agent) and send them to `https://autohealai.com/api/errors/ingest`. The `scripts/check-errors.sh` utility interacts with the same API to check error status. All observed network calls and data collection are consistent with the stated purpose of an error monitoring service, requiring an `AUTOHEAL_API_KEY`. There is no evidence of intentional malicious behavior, such as exfiltrating unrelated sensitive data, installing backdoors, or prompt injection attempts against the AI agent.
能力评估
Purpose & Capability
The skill's stated purpose (capture JS/TS errors and send them to an AutoHeal service) matches the included instructions and scripts. However, registry metadata incorrectly lists no required environment variables while SKILL.md and scripts require AUTOHEAL_API_KEY. This metadata mismatch is an incoherence that could mislead users about credential requirements.
Instruction Scope
Runtime instructions instruct sending error messages, stacks, source URLs, and a key to https://autohealai.com/api/errors/ingest. The browser snippet encourages (and appears to expect) putting the API key into client-side code (uses process.env in a browser context and falls back to a literal key), which would expose the key to end users. The instructions do not warn about potentially sensitive or PII-containing data in stack traces or page URLs nor do they recommend server-side proxying or scrubbing before transmission.
Install Mechanism
This is an instruction-only skill with no install spec and no remote downloads; included code is a small local shell script. There is no installer that fetches remote code or creates binaries, so installation risk is low.
Credentials
The skill legitimately needs a single API key (AUTOHEAL_API_KEY) to call the third-party service, which is proportionate to the stated purpose. However, the registry metadata omits this requirement (contradiction). More importantly, the provided browser instructions would effectively leak that credential if embedded client-side; the skill also instructs sending stack traces and page URLs to an external domain, which can contain secrets or PII. These data-exfiltration risks are not justified or mitigated in the docs.
Persistence & Privilege
The skill does not request always:true, does not modify other skills, and does not request system-wide configuration changes. It has normal, limited presence (instruction-only and a helper script).
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install autoheal
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /autoheal 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
Initial release of the AutoHeal skill. - Adds AI-powered error monitoring for JavaScript/TypeScript projects. - Automatically captures and reports errors from both browser and Node.js/server environments. - Provides cURL endpoints to check error analysis status and view AI-generated fixes. - Supports manual error reporting via API. - Requires an `AUTOHEAL_API_KEY` for authentication.
元数据
Slug autoheal
版本 1.0.0
许可证
累计安装 2
当前安装数 2
历史版本数 1
常见问题

AutoHeal AI 是什么?

Add AI-powered error monitoring and auto-fix generation to any project. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 480 次。

如何安装 AutoHeal AI?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install autoheal」即可一键安装,无需额外配置。

AutoHeal AI 是免费的吗?

是的,AutoHeal AI 完全免费(开源免费),可自由下载、安装和使用。

AutoHeal AI 支持哪些平台?

AutoHeal AI 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 AutoHeal AI?

由 hankmint(@hankmint)开发并维护,当前版本 v1.0.0。

💬 留言讨论