Skip to content
Back to skills

215 Name Skill 5f59f25a

BSecurity

Install, configure, and update openclaw-config

  • 9 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added October 11, 2026
ai-agentsgoapidevops

Works with

  • claude code
  • cli
  • api

Security analysis

B85/100
  • highCreates or modifies cron jobs for persistent execution

Pro scans all 2 files and shows the line behind each finding

Scanned October 11, 2026

npx -y skills add tools-only/X-Skills --skill 215-name-skill_5f59f25a --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of 215 Name Skill 5f59f25a?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for 215 Name Skill 5f59f25a
[![Security: B β€” Skills Directory](https://www.skillsdirectory.com/api/skills/tools-only-215-name-skill-5f59f25a/badge)](https://www.skillsdirectory.com/skills/tools-only-215-name-skill-5f59f25a)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: openclaw
version: 0.2.2
description: Install, configure, and update openclaw-config
triggers:
  - openclaw
  - openclaw-config
  - set up openclaw
  - update openclaw
metadata:
  openclaw:
    emoji: "🐾"
---

# OpenClaw Config Skill 🐾

Manages your openclaw-config installation.

**Users say things like:**

- "Set up openclaw-config"
- "Update my openclaw config"
- "Force update openclaw" (overwrites their changes)
- "Check if openclaw has updates"

---

# Setup

Do these steps in order:

1. **Clone repo** to `~/.openclaw-config`

2. **Copy templates** to workspace root (don't overwrite existing): AGENTS.md, SOUL.md,
   USER.md, TOOLS.md, HEARTBEAT.md, IDENTITY.md

3. **Create memory folders:** `memory/people`, `memory/projects`, `memory/topics`,
   `memory/decisions`

4. **Copy skills** to `skills/`

5. **Optional: Add workflows** β€” Ask if they want any workflows:
   - "Do you want the email steward workflow?" β†’ Manages inbox automatically

   If yes:
   - Copy `AGENT.md` from `~/.openclaw-config/workflows/email-steward/` to
     `workflows/email-steward/`
   - Create `workflows/email-steward/logs/` directory
   - The workflow will interview them on first run to create `rules.md`

6. **Configure memory search** β€” Required for semantic search to work. Ask: LM Studio
   (local, free, recommended) or OpenAI?
   - **LM Studio:** Server on port 1234, model
     `lmstudio-community/embedding-gemma-300m-qat`, configure gateway
     memorySearch.remote.baseUrl to `http://127.0.0.1:1234/v1`
   - **OpenAI:** Get their API key, configure gateway memorySearch.remote.baseUrl to
     `https://api.openai.com/v1`, model `text-embedding-3-small`
   - **Verify it works:** Create test file in memory/, index it, search for it, confirm
     it returns results, clean up

7. **Personalization** β€” Ask and replace in templates: `{{USER_NAME}}`,
   `{{ASSISTANT_NAME}}`, `{{TIMEZONE}}`, `{{PRIORITY_1}}`, `{{PRIORITY_2}}`

8. **Optional skills** β€” These are optional. Ask about each one individually, only
   configure if they say yes:
   - "Do you have a Limitless Pendant?" β†’ If yes, get API key from app.limitless.ai β†’
     Settings β†’ Developer
   - "Do you use Fireflies.ai for meeting transcripts?" β†’ If yes, get API key from
     app.fireflies.ai β†’ Integrations β†’ Fireflies API
   - "Do you use Quo for business phone?" β†’ If yes, get API key from my.quo.com β†’
     Settings β†’ API
   - "Do you want Parallel.ai for web search? (better results than built-in)" β†’ If yes,
     get API key from platform.parallel.ai

   Skip any they don't use. Don't assume they want all of them.

9. **Health check setup** β€” Ask: "Do you want automated health monitoring? It runs
   hourly via cron (Claude Code + Sonnet) to check your gateway and services, fix minor
   issues, and notify you of problems."

   If yes:
   - Ask: "Who should be notified if there's a problem?" β†’ `mkdir -p ~/.openclaw` then
     write their answer to `~/.openclaw/health-check-admin` (just the name, one line)
   - Resolve the claude CLI path with `which claude` β€” use the full path in the cron job
   - Install the cron job (substitute CLAUDE_PATH with the resolved path):
     ```
     0 0,7-23 * * * test -f "$HOME/.openclaw-config/devops/health-check.md" && flock -n "$HOME/.openclaw/health-check.lock" CLAUDE_PATH -p "Run health check" --model sonnet --append-system-prompt-file "$HOME/.openclaw-config/devops/health-check.md" --dangerously-skip-permissions --max-budget-usd 5.00 >> "$HOME/.openclaw/health-check.log" 2>&1
     ```
   - Verify: `crontab -l | grep health-check`
   - Do a test run: execute the claude command once and verify it produces output
   - Tell them: runs hourly 7 AM–midnight, logs at `~/.openclaw/health-check.log`

10. **Track version** in `.openclaw/installed-version`

11. **Summary** β€” Tell them what's configured

---

# Update

Compare `.openclaw/installed-version` with `~/.openclaw-config/VERSION`.

If newer: pull, update skills (safe to overwrite), update templates only if user hasn't
modified them, update version file, report changes.

If user wants to force/overwrite: backup to `.openclaw/backup/` first.

**Workflows:** Only update AGENT.md (the algorithm). Never touch rules.md,
agent_notes.md, or logs/ β€” those belong to the user.

---

# Status

Show installed version and skill versions. Fetch remote VERSION, report if updates
available.

Files in this skill

  • README.md764 B
  • skill.md4.3 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.