Token导航 LogoToken导航

Agent Skill · 研究检索

openclaw-urgent-care(OpenClaw urgent care 搜索)

openclaw-urgent-care 用于记录任务执行中的错误、用户纠正、经验和能力缺口,适合在 OpenClaw 中希望让 Agent 持续沉淀问题、修正和最佳实践时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

openclaw-urgent-care 是研究检索类 Agent Skill,可用宿主为 OpenClaw,通过ClawHub获取,权限为接触敏感数据;许可证为 MIT-0,第三方扫描已通过,按安装量在研究检索类的 73,675 个 Skill 里排第 28,792。

总安装 3,158周安装 129GitHub Stars 公开资料未说明下载 1,011核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
MIT-0
版本
0.1.1

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:openclaw-urgent-care(OpenClaw urgent care 搜索)
来源仓库:https://github.com/scsays/openclaw-urgent-care
安装命令:
openclaw skills install openclaw-urgent-care
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install openclaw-urgent-care

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

用于诊断和恢复 OpenClaw 常见故障,提升系统稳定性。适用于网关离线、工具锁定、提供商错误等场景的排查与修复。通过分析错误日志和用户反馈,生成修正建议和最佳实践。安装命令:openclaw skills install openclaw-urgent-care。

需确认权限范围和维护状态,避免触发敏感操作或文件修改。

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 OpenClaw;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 openclaw skills install openclaw-urgent-care;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要接触敏感数据,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

openclaw-urgent-care 怎么安装?

在终端执行 openclaw skills install openclaw-urgent-care。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

openclaw-urgent-care 支持哪些 AI 工具?

公开资料标注支持 OpenClaw。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

openclaw-urgent-care 需要什么权限?

权限级别是接触敏感数据。该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

openclaw-urgent-care 是免费的吗?

来源标注的许可证是 MIT-0。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

openclaw-urgent-care 用的人多吗?

公开数据是累计安装 3,158 次,近一周安装 129 次,下载 1,011 次。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

openclaw-urgent-care 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 专注 OpenClaw 一种宿主,触发方式和使用习惯不用来回切换。
  • 许可证明确为 MIT-0,商用和分发边界好判断。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 需要接触敏感数据,装到常用环境前要先评估影响面。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 OpenClaw,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。
  • 需要许可证清楚、并且有第三方扫描结果的团队项目。

不太适合

  • 环境里有大量密钥、凭证,不方便给第三方 Skill 读取的人。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
openclaw-urgent-care

OpenClaw urgent care 搜索 · 本页

3,158—接触敏感数据MIT-0通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

name
openclaw-urgent-care
description
>
metadata
openclaw
emoji
🚑
version
0.1.0
author
Andre Bradford / S.C. Says Poetry LLC
tags

OpenClaw Urgent Care

When your OpenClaw setup breaks, use this skill to diagnose what happened and get the shortest safe path to recovery.

When to use this skill

Use when:

  • OpenClaw went silent after an update
  • The gateway is unreachable or keeps crashing
  • Your agent can see messages but can't do anything
  • Commands that used to run automatically are now blocked
  • A Discord channel is routing to the wrong agent
  • Scheduled jobs stopped running
  • A plugin or skill failed to install
  • You want to verify your setup is healthy before making changes

Do NOT use for:

  • Initial OpenClaw installation (use the official docs at openclaw.ai)
  • Multi-agent architecture design
  • Skill development or publishing

Common Failure Modes

1. Gateway Offline

Symptoms: Agent stopped responding. Dashboard unreachable. Discord bot silent.

Quick fix:

openclaw gateway restart

If that doesn't work after an update:

openclaw gateway install
openclaw status

2. Agent Can See Messages But Can't Do Anything (v2026.3.2)

Symptom: Agent responds but can't run tools, execute commands, or take actions.

Cause: The v2026.3.2 update defaulted tools.profile to messages — restricting the agent to message-only mode.

Fix:

  1. Open ~/.openclaw/openclaw.json
  2. Find or add: "tools": { "profile": "full" }
  3. Run: openclaw gateway restart
⚠️ full grants full tool access. Review your security posture before applying.

3. Provider / Billing / Auth Failure

Symptoms: Gateway is up. Agent is silent. Session logs show disabled:billing, usage limits, or authentication_error.

This is NOT a gateway problem. The gateway is fine — the model provider is blocking calls.

For disabled:billing (Anthropic cached penalty):

  1. Find: ~/.openclaw/agents/<agent>/agent/auth-profiles.json
  2. Remove the usageStats.anthropic:default entry
  3. Restart: openclaw gateway restart

For usage cap:

  • Raise the limit in your provider dashboard, or temporarily switch models.

For auth error:

  • Verify and rotate your API key in ~/.openclaw/openclaw.json.

4. Wrong Agent Handling a Channel (Routing / Binding)

Symptom: Discord messages go to the default agent instead of the intended one.

Fix: Check ~/.openclaw/openclaw.json → bindings. Every non-default Discord account needs an explicit binding:

{
  "agentId": "your-agent-name",
  "match": {
    "channel": "discord",
    "accountId": "your-account-id"
  }
}

Then: openclaw gateway restart


5. Channel Connected But Messages Don't Flow

Symptom: Channel shows connected/ready. Agent doesn't respond.

Common causes: @mention required, pairing not approved, allowlist blocking, missing OAuth scope.

Check:

openclaw channels status --probe
openclaw logs --follow

Look for: allowlist blocked, pairing pending, permission denied, missing scope.


6. Commands Require Unexpected Approval (Post-Update)

Symptom: Commands that ran automatically are now waiting for approval or timing out.

Cause: A recent update tightened exec approval defaults.

Check:

openclaw config get | grep -A10 exec

Review ask, security, and host settings. Update to match your intended defaults, then restart.


7. Scheduled Jobs Not Running

Symptom: Morning briefing didn't arrive. Cron jobs silent.

Check:

openclaw cron status
openclaw cron list

Common causes: scheduler disabled after update, wrong delivery accountId, quiet hours active.


8. Plugin / Skill Won't Load

Symptom: A skill fails after an update or fresh install.

Check:

openclaw skills list --failed
openclaw logs --follow

Common causes: missing runtime dependency, package shape changed, security scan blocked install.


9. Gateway Installed But Not Staying Up

Symptom: Service shows as loaded but keeps crashing. Dashboard unreachable. Restart loop.

Check:

openclaw gateway status
openclaw logs --follow
openclaw doctor
lsof -i :18789

Common causes: port 18789 conflict, auth/bind config error, startup config mismatch.


Automated Recovery Tool

The full OpenClaw Urgent Care product automates all of the above:

  • Runs preflight, collection, classification, and AI explanation in one command
  • Covers all 11 failure modes with confidence scoring and evidence
  • Safe auto-fix for gateway restart and tools.profile lockout
  • Works completely offline — local model only, no cloud API needed
  • Writes a full markdown recovery report
# Install once
bash /path/to/openclaw-urgent-care/install.sh

# Then run from anywhere
urgentcare

Available at Claw Mart: shopclawmart.com → Search "OpenClaw Urgent Care"

One-time purchase · All future updates included


Triage Checklist (copy-paste for fast debugging)

# Step 1 — Is the gateway up?
openclaw status

# Step 2 — Any errors in recent sessions?
openclaw logs --follow

# Step 3 — Is config valid?
openclaw config validate

# Step 4 — Gateway restart (safe to run anytime)
openclaw gateway restart

# Step 5 — If still broken after an update
openclaw gateway install
openclaw doctor

*Built by Andre Bradford / S.C. Says Poetry LLC* *Full product: shopclawmart.com → OpenClaw Urgent Care*

平台分布

OpenClaw

96.82%
按下载量换算979

安全审计

VirusTotal

未展示

ClawScan

通过

Static analysis

通过

权限和风险

接触敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills