ClawHub

Workspace Guardian

v1.0.1

Auto-healing e proteção para workspaces OpenClaw. Valida e corrige problemas comuns automaticamente no startup e durante a execução. Usar quando: (1) Workspa...

⭐ 0· 157·0 current·0 all-time
by@elontools

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for elontools/workspace-guardian.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "Workspace Guardian" (elontools/workspace-guardian) from ClawHub.
Skill page: https://clawhub.ai/elontools/workspace-guardian
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Bare skill slug

openclaw skills install workspace-guardian

ClawHub CLI

Package manager switcher

npx clawhub@latest install workspace-guardian
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
The name/description (auto-healing for OpenClaw workspaces) aligns with the included script and docs: creating memory files/directories, validating openclaw.json, checking permissions and local gateway health. The actions requested are coherent with maintaining workspace stability.
ℹ
Instruction Scope
SKILL.md and references instruct reading and validating /data/.openclaw/openclaw.json, creating files, checking gateway health, and (in examples) using sed and restarting the gateway. The shipped script creates files, fixes permissions, and flags config issues but does not automatically replace API keys. The SKILL.md language about 'corrigir e reiniciar gateway' is somewhat vague — the references show example commands that would modify config in-place, so an agent following these instructions could make persistent changes to local config. This is within the claimed purpose but grants the agent discretion to modify sensitive config; the instructions could be clearer about when to prompt for approval.
✓
Install Mechanism
No install spec; the skill is instruction-only with one shell script. Nothing is downloaded or written to disk at install time beyond the included files—this is low-risk and consistent with the skill purpose.
ℹ
Credentials
The skill does not request environment variables or external credentials, but it reads openclaw.json which may contain provider apiKeys and baseUrls (sensitive secrets). Reading and validating those fields is reasonable for a guardian, but users should understand the skill will access local secrets stored in that config file.
✓
Persistence & Privilege
always is false and the skill does not request system-wide persistent installation. It edits/creates files inside the workspace (expected for this purpose) and references restarting the local gateway, which is an appropriate action for a startup health-check script.
Assessment
This skill appears internally consistent and performs local maintenance of an OpenClaw workspace, but it will read and can modify /data/.openclaw/openclaw.json (which may contain API keys). Before installing: (1) review and backup /data/.openclaw/openclaw.json and your workspace, (2) verify the guardian-startup.sh content (it is included) and test it in a staging workspace, (3) ensure you are comfortable with an agent having permission to edit local config and restart the gateway, and (4) if you want manual control, require the agent to ask before applying fixes (do not enable autonomous auto-fix without review).

Like a lobster shell, security has layers — review code before you run it.

latestvk979sxvvh0kb0vnmptzf2vg2kx838vhw
157downloads
0stars
2versions
Updated 1mo ago
v1.0.1
MIT-0
@elontools
latest
Download

Workspace Guardian

Skill de auto-healing para workspaces OpenClaw. Garante que o workspace está saudável e funcional.

Quando rodar

Esta skill é executada automaticamente:

  1. No startup — via HEARTBEAT.md (primeira execução)
  2. Periodicamente — a cada heartbeat, validação leve
  3. Sob demanda — quando o agente detecta erros recorrentes

Startup: Validação e Setup

No primeiro heartbeat após iniciar, executar o script de validação:

bash scripts/guardian-startup.sh

O script valida e corrige:

  • ✅ MEMORY.md existe (cria vazio se não)
  • ✅ memory/ diretório existe
  • ✅ memory/topics/ diretório existe
  • ✅ Permissões corretas nos arquivos
  • ✅ openclaw.json válido (JSON parseable)

Tratamento de Erros LLM

Quando receber erros do tipo:

  • "Only HTTPS URLs are supported" → Verificar e corrigir URLs no config
  • "Edit failed" → Arquivo não existe, criar primeiro com Write
  • "LLM request rejected" → Verificar apiKey e baseUrl no openclaw.json
  • timeout → Retry com backoff exponencial

Procedimento de auto-fix:

  1. Ler openclaw.json
  2. Validar que todas as URLs usam HTTPS
  3. Validar que apiKey está presente e não vazia
  4. Se encontrar problema: corrigir e reiniciar gateway

Validação de Config

Verificar no openclaw.json:

  • models.providers.*.baseUrl → deve começar com https://
  • models.providers.*.apiKey → deve existir e não estar vazia
  • models.providers.*.api → deve ser openai-completions ou anthropic
  • agents.list → deve ter pelo menos 1 agente

Referências

  • Ver references/common-errors.md para lista de erros conhecidos e soluções
  • Ver references/health-checks.md para detalhes dos health checks

Comments

Loading comments...