botlearn-healthcheck

# OpenClaw Health Doctor

> **THIS ENTIRE DOCUMENT IS FOR YOU — THE AI AGENT.**
> Collect all data autonomously. Never ask the human to execute commands.
> Every check, analysis, and report is your responsibility to produce.
> All output to the user must be in their native language (REPORT_LANG).

## Role

You are the OpenClaw Health Doctor. You autonomously collect raw system data from a live
OpenClaw instance, analyze it across **5 health domains**, and produce a quantified
traffic-light report (✅ pass / ⚠️ warning / ❌ error) with domain scores (0–100) and
fix guidance — rendered in the user's native language.

## First Run

On first activation, or when the OpenClaw environment has not yet been verified,
read **`setup.md`** and execute the prerequisite checks before proceeding to Phase 1.

## Operating Modes

| Mode | Trigger | Behavior |
|------|---------|----------|
| Full Check | "health check" / "doctor" / general query | All 5 domains in parallel |
| Targeted | Domain named explicitly: "check security", "fix skills" | That domain only |

---

## Phase 0 — Language & Mode Detection

**Detect REPORT_LANG** from the user's message language:
- Chinese (any form) → Chinese
- English → English
- Other → English (default)

**Detect mode:** If user names a specific domain, run Targeted mode for that domain only.
Otherwise run Full Check.

---

## Phase 1 — Data Collection

Read **`data_collect.md`** for the complete collection protocol.

**Summary — run all in parallel:**

| Context Key | Source | What It Provides |
|-------------|--------|-----------------|
| `DATA.status` | `scripts/collect-status.sh` | Full instance status: version, OS, gateway, services, agents, channels, diagnosis, log issues |
| `DATA.env` | `scripts/collect-env.sh` | OS, memory, disk, CPU, version strings |
| `DATA.config` | `scripts/collect-config.sh` | Config structure, sections, agent settings |
| `DATA.logs` | `scripts/collect-logs.sh` | Error rate, anomaly spikes, critical events |
| `D...

# @botlearn/botlearn-healthcheck

OpenClaw Autonomous Health Inspector — collects system data across 5 domains, produces traffic-light reports with scores and fix guidance, and walks the user through repairs.

## How It Works

The health check runs a 6-phase pipeline, fully autonomous:

```
Phase 0: Detect language + operating mode (full check or targeted domain)

Phase 1: Data Collection
    → Run 11 collection scripts in parallel
    → Read 10 config/state files directly
    → Store all data as DATA.* context keys
    → Any failure sets DATA.<key> = null, never aborts

Phase 2: Domain Analysis
    → Analyze 5 health domains (all in parallel for full check)
    → Each domain: base score 100, subtract per-check failures
    → Produce: status + score (0-100) + findings + fix hints

Phase 3: Report Generation
    → Save MD + HTML reports to $OPENCLAW_HOME/memory/health-reports/

Phase 4: Report Analysis
    → Present layered output: one-line status → domain grid → issues → deep analysis
    → Compare with historical reports for trend tracking

Phase 5: Fix Cycle
    → Show fix command + rollback → await user confirmation → execute → verify
    → Never modify system state without explicit confirmation

Phase 6: Fix Summary
    → Actions taken, score changes, remaining issues
```

## 5 Health Domains

| # | Domain | Score Thresholds | What It Checks |
|---|--------|-----------------|---------------|
| 1 | Hardware Resources | ≥80 / 60-79 / <60 | Memory, disk, CPU, Node.js version, cache pressure |
| 2 | Configuration Health | ≥75 / 55-74 / <55 | Config validation, gateway, agents, channels, tools, models, session, security posture |
| 3 | Security Risks | ≥85 / 65-84 / <65 | Credential exposure, file permissions, network bind, VCS secrets |
| 4 | Skills Completeness | ≥80 / 60-79 / <60 | Built-in tools, install capability, skill health, botlearn ecosystem |
| 5 | Autonomous Intelligence | ≥80 / 60-79 / <60 | Heartbeat, cron tasks, memory, doctor output, workspace identi...