# workspace-health

Adopt this skill: https://proskills.md/skills/other/leostehlik-openclaw-health

Page: https://proskills.md/skills/other/leostehlik-openclaw-health
This document is the public skill bundle for that page. It contains SKILL.md and every helper file the catalog carries. No login is required.

## File: SKILL.md
size: 2539
upstream: https://github.com/leostehlik/openclaw-health/blob/HEAD/SKILL.md

```text
---
name: workspace-health
description: Audits an OpenClaw workspace for configuration health, signal quality, and security issues. Use when asked to run a health check, audit the workspace, review agent config quality, or check if AGENTS.md, SOUL.md, memory files, or skills are in good shape. Checks for: bloated bootstrap files, stale memory, skill description quality, prompt injection risks in skills, critical rules coverage, and context hygiene issues. OpenClaw equivalent of claude-health.
---

# Workspace Health

Audit an OpenClaw workspace across five layers. Detect what to fix and in what order.

Read `references/checks.md` for the full list of checks per layer.

## Layers

1. **Bootstrap files** — AGENTS.md, SOUL.md, TOOLS.md, USER.md, IDENTITY.md
2. **Memory** — MEMORY.md index, memory/*.md files, open-items.md
3. **Skills** — SKILL.md quality, descriptions, security
4. **Cron jobs** — prompt quality, timeouts, silent failure patterns
5. **Process discipline** — open items, daily log hygiene, session close habits

## How to Run

1. Detect workspace root (default: `/Users/leos/.openclaw/workspace`)
2. Read all bootstrap files
3. Read all memory/*.md files and MEMORY.md
4. Read all skills/*/SKILL.md files
5. List cron jobs via cron tool
6. Run all checks from `references/checks.md`
7. Output prioritised report

## Output Format

Group findings into three levels:

**Critical - Fix now**
- Security issues in skills (prompt injection, hardcoded secrets, destructive commands)
- Open items that are blocking or overdue
- Cron jobs with silent failure patterns
- Bootstrap files with dangerous or conflicting instructions

**Structural - Fix soon**
- AGENTS.md signal-to-noise ratio declining (prose bloat, outdated sections)
- MEMORY.md index out of sync with actual memory files
- Skills with bloated descriptions (>200 tokens) or unclear triggers
- Memory files not updated in >14 days despite active sessions
- Critical rules only covered in one layer (should be in AGENTS.md + SOUL.md + relevant skill)

**Incremental - Nice to have**
- Open items with no assigned owner or date
- Skills that could benefit from references/ files to reduce SKILL.md size
- Daily log gaps
- Stale entries in memory files (>90 days, no longer relevant)

## Run Periodically

This health check is most useful when run:
- After a busy sprint or session cluster
- Before briefing a new agent on complex work
- When you notice agent behaviour degrading (forgetting things, ignoring rules)
- Monthly as routine maintenance
```

## File: README.md
upstream: https://github.com/leostehlik/openclaw-health/blob/HEAD/README.md

````text
# workspace-health

Audit your OpenClaw workspace configuration health across all layers.

Detects bloated bootstrap files, stale memory, skill security issues, silent-failure cron patterns, and process discipline gaps. Outputs a prioritised report: fix now, fix soon, nice to have.

OpenClaw equivalent of [claude-health](https://github.com/tw93/claude-health).

---

## What it checks

| Layer | Checks |
|-------|--------|
| Bootstrap files | Signal-to-noise, prose bloat, critical rules coverage, security, contradictions |
| Memory files | MEMORY.md index sync, staleness, open-items hygiene, daily log gaps |
| Skills | Description token count, trigger clarity, content quality, security (injection, credentials, destructive commands) |
| Cron jobs | Prompt quality, silent failure patterns, staleness, missing fallbacks |
| Process discipline | Session close habits, agent brief quality, memory maintenance |

---

## Installation

### OpenClaw

Add your workspace skills directory to `openclaw.json`:

```json
{
  "skills": {
    "load": {
      "extraDirs": ["/path/to/your/skills"]
    }
  }
}
```

Clone into that directory:

```bash
git clone https://github.com/LeoStehlik/workspace-health.git /path/to/your/skills/workspace-health
```

The skill triggers automatically when you ask for a health check, workspace audit, or config review.

---

## Usage

Just ask:

```
Run a health check on my workspace
```

Or invoke directly:

```
/workspace-health
```

---

## Output

Findings are grouped by priority:

**Critical - Fix now**
Skill security issues, blocking open items, cron silent failures, dangerous bootstrap instructions

**Structural - Fix soon**
AGENTS.md prose bloat, MEMORY.md out of sync, skill description quality, stale memory entries

**Incremental - Nice to have**
Open items hygiene, daily log gaps, skill organisation improvements

---

## When to run

- After a busy sprint or session cluster
- Before briefing a new agent on complex work
- When agent behaviour starts degrading (forgetting rules, ignoring context)
- Monthly as routine maintenance

---

## Inspiration

Inspired by [claude-health](https://github.com/tw93/claude-health) by tw93. Built as our own implementation for the OpenClaw workspace structure.

---

## License

MIT - see [LICENSE](LICENSE)
````
