Is the Agent Doctor skill free?

Yes. The skill itself is free from AlekseiUL/openclaw-superagent. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Agent Doctor SkillProof Score?

8.0/10 — installs cleanly 5/5, triggers reliably 4/5, output vs. baseline 7/10, docs & honesty 4/5.

How do I install Agent Doctor?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Agent Doctor with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Agent Doctor

Self-diagnosis and guided repair for OpenClaw agents: memory, crons, gateway, se

by AlekseiUL · AlekseiUL/openclaw-superagent

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 8.0/10
Tested: Jul 25, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Jul 30, 2026 · bd70528

⚠ This skill is no longer available upstream. Our re-check on Aug 10, 2026 couldn't find it any more (repo unreachable/deleted). The test below is what we measured on Jul 25, 2026 and we're leaving it up as a record — but there is nothing left to install, so we've removed the command.

Built a deliberately broken OpenClaw config and ran the skill's seven-point checklist live: it flagged all four planted faults (journal_mode=delete, memorySearch disabled, gateway bind 0.0.0.0, memory-core plugin off), and every remediation one-liner from the body executed verbatim and fixed them with the config staying valid JSON. Encodes real OpenClaw-specific knowledge a bare model would not reliably have; value is fully gated on actually running OpenClaw, and the bundled auto-diagnostic.sh has a set -e bug that aborts after the first failing check.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 4/5
Output vs. baseline 7/10
Docs & honesty 4/5

What Agent Doctor does

Diagnoses an OpenClaw agent across seven categories (memory/WAL, crons, config, files, gateway, system, security) and proposes exact fix commands that are applied only after user confirmation. Triggers on requests like 'self-check', 'health check', or 'diagnose yourself'. Useful mainly for OpenClaw operators, especially after an OpenClaw update.

How to install Agent Doctor

Nothing to install: the source repository no longer has this skill. If the author brings it back, our daily re-check will pick it up and the command will reappear here.

Commands — how to trigger Agent Doctor

/agent-doctor Self-diagnosis and guided repair for OpenClaw agents: memory, crons, gateway, se

It also activates on plain-language prompts like these:

Run a self-check on my OpenClaw agent after the update
Diagnose why my OpenClaw memory and gateway aren't working
Health check my OpenClaw config and fix any WAL issues

Frequently asked questions

Is the Agent Doctor skill free?: Yes. The skill itself is free from AlekseiUL/openclaw-superagent. SkillProof publishes the install command and an independent test verdict at no cost.
Does Agent Doctor work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 25, 2026. Verdict: Tested · Works. Built a deliberately broken OpenClaw config and ran the skill's seven-point checklist live: it flagged all four planted faults (journal_mode=delete, memorySearch disabled, gateway bind 0.0.0.0, memory-core plugin off), and every remediation one-liner from the body executed verbatim and fixed them with the config staying valid JSON. Encodes real OpenClaw-specific knowledge a bare model would not reliably have; value is fully gated on actually running OpenClaw, and the bundled auto-diagnostic.sh has a set -e bug that aborts after the first failing check.
What is the Agent Doctor SkillProof Score?: 8.0/10 — installs cleanly 5/5, triggers reliably 4/5, output vs. baseline 7/10, docs & honesty 4/5.
How do I install Agent Doctor?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Agent Doctor with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.