Clawpilot

This is the reference skill for OpenClaw, a self-hosted AI gateway that routes messages from chat platforms (WhatsApp, Telegram, Discord, Slack, iMessage, and others) to AI agents. You'll want this if you're running OpenClaw v2026.2.19 or later and need help with installation, channel setup, security hardening, or troubleshooting openclaw.json configs. It includes bundled scripts for security audits and has staleness checks that pull fresh CVE data before answering, which matters because OpenClaw patched 40+ vulnerabilities in early 2026. The skill enforces a security-first workflow and walks through real command sequences rather than theory. Useful for both initial setup and debugging production gateway issues.

skills.sh installs: 264
GitHub stars: 48
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add kcchien/clawpilot --skill clawpilot --agent claude-code

Installs into .claude/skills of the current project.

Files

OpenClaw Expert Skill

Auto-Update Check (Run First)

Before any other action, run the staleness check:

bash scripts/check_updates.sh

If UP_TO_DATE: Proceed normally.
If STALE: The skill references may be outdated. Before proceeding with the user's task:
1. Fetch the latest 3-5 releases from https://github.com/openclaw/openclaw/releases
2. Fetch https://docs.openclaw.ai/llms.txt for doc changes
3. Search web for recent OpenClaw CVEs or security advisories
4. Compare findings against the version in SKILL.md frontmatter and references/security.md
5. Inform the user of any version gaps or new security issues found
6. If references were updated, run: bash scripts/mark_updated.sh <latest-version>
7. If no updates needed, still mark as checked: bash scripts/mark_updated.sh <current-version>