用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/diegosouzapw/awesome-omni-skill --skill tinman命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Token-efficient tracking for AI orchestration. CLI-first for status updates (~50 tokens), agent fallback for complex ops (~1KB). Use when: updating task status, querying blockers, creating progress files, validating phases.
AshAi extension guidelines for integrating AI capabilities with Ash Framework. Use when implementing vectorization/embeddings, exposing Ash actions as LLM tools, creating prompt-backed actions, or setting up MCP servers. Covers semantic search, LangChain integration, and structured outputs.
This skill should be used when solving hard questions, complex architectural problems, or debugging issues that benefit from GPT-5 Pro or GPT-5.1 thinking models with large file context. Use when standard Claude analysis needs deeper reasoning or extended context windows.
基于 SOC 职业分类
正在显示 SKILL.md
| name | tinman |
| version | 1.0.0 |
| description | Security auditing and hardening for OpenClaw and system infrastructure. |
| metadata | {"openclaw":{"emoji":"🛡️","category":"security"}} |
Security auditing and hardening for OpenClaw and system infrastructure.
| Level | Description | Response |
|---|---|---|
| S0 | Info | Log only |
| S1 | Low | Notify user |
| S2 | Medium | Alert + recommend fix |
| S3 | High | Immediate action required |
| S4 | Critical | Stop + notify immediately |
| Check | Risk | Action |
|---|---|---|
| Credentials in git | S3 | Add to .gitignore, rotate |
| Token expiration | S2 | Refresh tokens |
| Exposed secrets | S4 | Rotate immediately |
| Uncommitted changes | S1 | Review + commit |
| Check | Risk | Action |
|---|---|---|
| SSH password auth | S2 | Disable, use keys only |
| Open ports | S1 | Review with ss -tlnp |
| Unattended upgrades | S2 | Enable automatic updates |
| Firewall status | S2 | Verify ufw/iptables |
# Check for credentials in git
git log --all --full-history -- .credentials/
# Check file permissions
ls -la ~/.credentials/
# Check SSH config
cat /etc/ssh/sshd_config | grep -E "PasswordAuthentication|PermitRootLogin"
## Security Audit Report
**Date:** 2026-02-20
**Scope:** OpenClaw + System
### Findings
| Level | Issue | Recommendation |
|-------|-------|----------------|
| S2 | Token expires in 3 days | Refresh Google OAuth |
### Actions Taken
- [x] Verified .credentials/ permissions (600)
- [ ] Refresh expiring tokens
{
"name": "daily-security-check",
"schedule": {"kind": "cron", "expr": "0 6 * * *"},
"payload": {
"kind": "agentTurn",
"message": "Run tinman security scan. Check: credential perms, token expiration, git secrets. Report S2+ issues."
},
"sessionTarget": "isolated",
"notify": true
}
If S4 (Critical) detected: