← 返回 Skills 市场

API Health Monitor

Name: API Health Monitor
Author: toller892

作者 toller892 · GitHub ↗ · v1.0.1 · MIT-0

cross-platform ✓ 安全检测通过

总下载

当前安装

版本数

在 OpenClaw 中安装

/install api-health-monitor

功能描述

Parses recent OpenClaw session logs for LLM API errors and returns a structured health report.

使用说明 (SKILL.md)

api-health-monitor

Scans ~/.openclaw/agents/main/sessions/ for recent LLM API error patterns (500 errors, token failures, cooldowns, service_busy) and produces a JSON health report.

Usage

const { checkApiHealth } = require('./skills/api-health-monitor');
const report = await checkApiHealth();
// { healthy: bool, errors: [...], recommendation: string }

Report Shape

Field	Type	Description
`healthy`	boolean	`true` if no errors found
`errors`	array	`[{ type, message, count, lastSeen }]`
`recommendation`	string	Suggested action based on findings

安全使用建议

This skill appears to do exactly what it says: read recent files in ~/.openclaw/agents/main/sessions/ and report LLM API error patterns. Before installing or enabling it broadly: (1) Inspect a few session files manually to see if they contain sensitive data (API keys, tokens, private user content). (2) Run the skill in a sandbox or on a copy of logs first so you can confirm its output does not leak secrets. (3) If you allow autonomous invocation, be aware the skill can be run by agents and may surface sensitive log contents — consider restricting when/which agents can invoke it. (4) If you need safer behavior, request or modify the code to redact known secrets or limit returned message length/content.

功能分析

Type: OpenClaw Skill Name: api-health-monitor Version: 1.0.1 The skill is a utility for monitoring LLM API health by parsing local session logs within the application's own data directory (~/.openclaw). The logic in index.js is limited to reading log files, matching regex patterns for common API errors (e.g., 429 rate limits, 500 server errors), and returning a structured report; it contains no network activity, external dependencies, or suspicious execution patterns.

能力评估

✓ Purpose & Capability

Name/description, SKILL.md, and index.js all target ~/.openclaw/agents/main/sessions/ and search for LLM API error patterns. The declared requirements (none) are consistent with the simple local-log-parsing task. Minor metadata inconsistencies: package.json version (1.0.0) differs from registry metadata (1.0.1) and the SKILL.md example path is a generic require path, but these are bookkeeping issues not functional mismatches.

ℹ Instruction Scope

Instructions and runtime code exclusively read files under the session directory and produce a JSON report; they do not call external endpoints or access unrelated system paths. Note: reading session logs can surface sensitive data (user content, API keys, tokens) because the code returns message snippets and file basenames without redaction; SKILL.md does not warn about this privacy sensitivity.

✓ Install Mechanism

No install spec or remote downloads; the skill is instruction-only but includes a local index.js and package.json (no external dependencies). Nothing in the manifest installs third-party code from remote URLs or writes unexpected binaries.

✓ Credentials

No environment variables or credentials are required. The code uses HOME/USERPROFILE only to locate the expected sessions directory, which is proportional to the stated purpose.

✓ Persistence & Privilege

always is false and the skill does not request persistent system-wide configuration or modify other skills. Autonomous invocation is allowed (platform default); combined with the skill's access to session logs, this is a privacy consideration but not a coherence/security mismatch on its own.

如何使用

确保已安装 OpenClaw（本地或 Docker 部署）
在对话框中输入安装命令：/install api-health-monitor
安装完成后，直接呼叫该 Skill 的名称或使用 /api-health-monitor 触发
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

v1.0.1

Fix: Resolve version conflict, initial publish retry

v1.0.0

Initial release

元数据

Slug api-health-monitor

版本 1.0.1

许可证 MIT-0

累计安装 1

当前安装数 0

历史版本数 2

常见问题