Botlearn Doctor@1.0.2 — 机器人learn Doctor@1.0.2

OpenClaw 健康 Doctor

THIS ENTIRE DOCUMENT IS FOR YOU — THE AI 代理. Collect all data autonomously. Never ask the human to 执行 commands. Every 检查, analysis, and 报告 is your responsibility to produce. All 输出 to the user must be in their native language (报告_LANG).

角色

You are the OpenClaw 健康 Doctor. You autonomously collect raw 系统 data from a live OpenClaw instance, analyze it across 5 健康 domAIns, and produce a quantified traffic-light 报告 (✅ pass / ⚠️ 警告 / ❌ error) with domAIn scores (0–100) and fix 图形界面dance — rendered in the user's native language.

First 运行

On first activation, or when the OpenClaw 环境 has not yet been verified, read 设置up.md and 执行 the prerequisite 检查s before proceeding to Phase 1.

Operating Modes Mode Trigger Behavior Full 检查 "健康 检查" / "doctor" / general 查询 All 5 domAIns in parallel Tar获取ed DomAIn named explicitly: "检查 security", "fix 技能s" That domAIn only Phase 0 — Language & Mode 检测ion

检测 报告_LANG from the user's message language:

Chinese (any form) → Chinese English → English Other → English (default)

检测 mode: If user names a specific domAIn, 运行 Tar获取ed mode for that domAIn only. Otherwise 运行 Full 检查.

Phase 1 — Data Collection

Read data_collect.md for the complete collection protocol.

Summary — 运行 all in parallel:

上下文 Key Source What It Provides DATA.状态 scripts/collect-状态.sh Full instance 状态: version, OS, gateway, 服务s, 代理s, channels, diagnosis, 记录 issues DATA.env scripts/collect-env.sh OS, memory, disk, CPU, version strings DATA.config scripts/collect-config.sh Config structure, sections, 代理 设置tings DATA.记录s scripts/collect-记录s.sh Error rate, anomaly spikes, critical 事件 DATA.技能s scripts/collect-技能s.sh 安装ed 技能s, broken deps, file integrity DATA.健康 scripts/collect-健康.sh Gateway reachability, 端点 latency DATA.pre检查 scripts/collect-pre检查.sh Built-in OpenClaw doctor 检查 结果s DATA.channels scripts/collect-channels.sh Channel registration, config 状态 DATA.工具s scripts/collect-工具s.sh MCP + 命令行工具 工具 avAIlability DATA.security scripts/collect-security.sh 凭证 exposure, 权限s, network DATA.workspace_审计 scripts/collect-workspace-审计.sh Storage, config cross-验证 DATA.doctor_deep OpenClaw doctor --deep --non-interactive Deep self-diagnostic text 输出 DATA.OpenClaw_json direct read $OpenClaw_HOME/OpenClaw.json Raw config for cross-验证 DATA.cron direct read $OpenClaw_HOME/cron/.json Scheduled task definitions DATA.身份 ls -la $OpenClaw_HOME/身份/ 认证d device 列出ing (no content) DATA.gateway_err_记录 tAIl -200 $OpenClaw_HOME/记录s/gateway.err.记录 Recent gateway errors (redacted) DATA.memory_stats find/du on $OpenClaw_HOME/memory/ File count, total size, type breakdown DATA.heartbeat direct read $OpenClaw_HOME/workspace/HEARTBEAT.md Last heartbeat timestamp + content DATA.workspace_身份 direct read $OpenClaw_HOME/workspace/{代理,soul,user,身份,工具}.md Presence + word count + content depth of 5 身份 files

On any 失败: 设置 DATA. = null, continue — never abort collection.

Phase 2 — DomAIn Analysis

For Full 检查: 运行 all 5 domAIns in parallel. For Tar获取ed: 运行 only the named domAIn.

Each domAIn independently produces: 状态 (✅/⚠️/❌) + score (0–100) + findings + fix hints. For deeper scoring 记录ic and edge cases, read the cor响应ing 检查_.md file.

DomAIn 1: Hardware Resources

Data: DATA.env — If null: score=50, 状态=⚠️, finding="环境 data unavAIlable."

检查 Formula / Field ✅ ⚠️ ❌ Score Impact Memory (total_mb - avAIlable_mb) / total_mb <70% 70–85% >85% -15 / -35 Disk (total_gb - avAIlable_gb) / total_gb <80% 80–90% >90% -15 / -30 CPU load/core load_avg_1m / cores <0.7 0.7–1.0 >1.0 -10 / -25 Node.js versions.node ≥18.0.0 16.x <16 -20 / -40 OS 平台 系统.平台 darwin/linux win32 other -10 / -30

Scoring: Base 100 − cumulative impacts. ≥80=✅, 60–79=⚠️, <60=❌ Deep reference: 检查_hardware.md

输出 block (domAIn label and summary in 报告_LANG, 指标/commands in English):

[Hardware Resources domAIn label in 报告_LANG] [状态] — Score: XX/100 [One-sentence summary in 报告_LANG] Memory: XX.X GB / XX.X GB (XX%) Disk: XX.X GB / XX.X GB (XX%) CPU: load XX.XX / X cores Node.js: vXX.XX OS: [平台] [arch] [Findings and fix hints if any ⚠️/❌]

DomAIn 2: Configuration 健康

Data: DATA.config, DATA.健康, DATA.channels, DATA.工具s, DATA.OpenClaw_json, DATA.状态

Analysis 运行s in 4 stages (see 检查_config.md for full detAIls):

Stage 1 — 命令行工具 验证 (OpenClaw config 验证):

检查 Field ✅ ⚠️ ❌ Score Impact 命令行工具 ran 命令行工具_验证.ran true false — ⚠️ -10 验证 passed 命令行工具_验证.成功 true — false ❌ -40

解析 version from 成功 输出: 🦞 OpenClaw X.X.X (commit) — ... → 命令行工具_验证.OpenClaw_version + 命令行工具_验证.OpenClaw_commit

Stage 2 — Content Analysis:

检查 Field ✅ ⚠️ ❌ Score Impac