oc-doctor
Runs a comprehensive 11-section health check on local OpenClaw installations. Diagnoses configuration errors, session bloat, model drift, cron issues, security misconfigurations, gateway problems, and system instruction token budget. Generates a structured report with CRITICAL/WARNING/INFO findings and offers interactive one-click fixes. Use when: "openclaw doctor", "claw doctor", "claw health check", "openclaw diagnose", or troubleshooting OpenClaw.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/bryant24hao/oc-doctorWhat This Skill Does
oc-doctor is the definitive diagnostic utility for OpenClaw local installations. It automates the maintenance of your environment by performing a rigorous 11-section health check. The tool scans your configuration files, session directories, and cron job schedules to identify inconsistencies, security holes, and performance bottlenecks. By executing a deep analysis of your local state, it detects critical issues like configuration drifts, obsolete legacy files, and insecure gateway settings that could expose your agent to unauthorized access. The skill produces a human-readable report categorized by CRITICAL, WARNING, and INFO levels, and provides interactive, one-click solutions to resolve identified errors. Whether you are debugging a stalled session or optimizing your token budget, oc-doctor ensures your OpenClaw agent remains performant, secure, and fully operational.
Installation
You can install the skill directly via the OpenClaw command-line interface. Run the following command in your terminal:
clawhub install openclaw/skills/skills/bryant24hao/oc-doctor
Ensure that you have jq installed on your system before running the doctor utility, as it is a mandatory dependency for parsing the configuration reports.
Use Cases
- Post-Update Verification: Run the doctor after updating your OpenClaw version to ensure all configuration schemas match the latest requirements.
- Performance Bottleneck Resolution: If your agent response time is lagging, use the doctor to diagnose session bloat and identify cron job conflicts.
- Security Auditing: Regularly check your Telegram and Feishu channel configurations to ensure your
requireMentionandgroupPolicysettings are not inadvertently exposing your agent. - Automated Cleanup: Use the doctor to identify and remove legacy configuration files (
*.bak*) that clutter your environment.
Example Prompts
- "openclaw doctor: run a full diagnostic on my current installation."
- "claw health check - are there any critical security issues with my channel configuration?"
- "claw diagnose: why is my agent using too many tokens for system instructions?"
Tips & Limitations
- Context Awareness: The tool automatically detects your
OPENCLAW_HOMEdirectory, so you do not need to manually configure environment variables. - Multilingual Support: The tool intelligently detects your language based on your workspace files and interaction history, providing localized reports.
- Safety Note: While the skill offers 'one-click fixes,' always review the proposed changes for complex configuration files. The doctor does not delete active session data without explicit user confirmation during the interactive fix phase.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-bryant24hao-oc-doctor": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: file-read, file-write, code-execution
Related Skills
macos-calendar-assistant
Manage macOS Calendar with OpenClaw in IM-first workflows (Telegram/Discord/Feishu/iMessage/Slack), including screenshot-to-schedule extraction, idempotent create/update, move/extend/reschedule, reminders, conflict checks, daily review sync, and duplicate cleanup. Use when users ask to add/edit/move/postpone events, parse schedule screenshots/chat messages, adjust weekly plans into daily execution, or keep calendar and review notes in sync.
skill-publisher
End-to-end workflow for publishing agent skills to GitHub, ClawdHub, and skills.sh. Handles repo creation, topic tagging, ClawdHub publish, skills.sh index request, and installation verification. Use when: "publish skill", "上架 skill", "发布技能", "submit to skills.sh", "submit to clawhub", "skill 上架流程".