duclm1x1
duclm1x1/Dive-Ai
相关职业SOC
基于 SOC 职业分类
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/duclm1x1/Dive-Ai --skill meshguard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。
Persistent memory system for AI agents following Model Context Protocol (MCP). Use for storing long-term memories across sessions, semantic search of past knowledge, building knowledge graphs, auto-injecting context, deduplicating memories, syncing to cloud storage. Essential for agents that need to remember decisions, solutions, preferences, and learned patterns over time.
Persistent memory system for AI agents following Model Context Protocol (MCP). Use for storing long-term memories across sessions, semantic search of past knowledge, building knowledge graphs, auto-injecting context, deduplicating memories, syncing to cloud storage. Essential for agents that need to remember decisions, solutions, preferences, and learned patterns over time.
Master REST and GraphQL API design principles to build intuitive, scalable, and maintainable APIs that delight developers. Use when designing new APIs, reviewing API specifications, or establishing API design standards.
正在显示 SKILL.md
基于 SOC 职业分类
| name | meshguard |
| description | Manage MeshGuard AI agent governance - agents, policies, audit logs, and monitoring. |
| metadata | {"clawdbot":{"requires":{"bins":["curl","jq"]}}} |
AI agent governance platform. Manage agents, policies, audit logs, and monitor your MeshGuard instance.
First-time setup — run the wizard:
bash skills/meshguard/scripts/meshguard-setup.sh
This saves config to ~/.meshguard/config (URL, API key, admin token).
| Variable | Description |
|---|---|
MESHGUARD_URL | Gateway URL (default: https://dashboard.meshguard.app) |
MESHGUARD_API_KEY | API key for authenticated requests |
MESHGUARD_ADMIN_TOKEN | Admin token for org management & signup |
Config file ~/.meshguard/config is sourced automatically by the CLI.
All commands go through the wrapper script:
bash skills/meshguard/scripts/meshguard-cli.sh <command> [args...]
meshguard-cli.sh status
Returns gateway health, version, and connectivity.
meshguard-cli.sh agents list # List all agents in org
meshguard-cli.sh agents create <name> --tier <tier> # Create agent (tier: free|pro|enterprise)
meshguard-cli.sh agents get <agent-id> # Get agent details
meshguard-cli.sh agents delete <agent-id> # Delete agent
meshguard-cli.sh policies list # List all policies
meshguard-cli.sh policies create <yaml-file> # Create policy from YAML file
meshguard-cli.sh policies get <policy-id> # Get policy details
meshguard-cli.sh policies delete <policy-id> # Delete policy
Policy YAML format:
name: rate-limit-policy
description: Limit agent calls to 100/min
rules:
- type: rate_limit
max_requests: 100
window_seconds: 60
- type: content_filter
block_categories: [pii, credentials]
meshguard-cli.sh audit query # Recent audit events
meshguard-cli.sh audit query --agent <name> # Filter by agent
meshguard-cli.sh audit query --action <action> # Filter by action type
meshguard-cli.sh audit query --limit 50 # Limit results
meshguard-cli.sh audit query --agent X --action Y --limit N # Combined filters
Actions: agent.create, agent.delete, policy.create, policy.update, policy.delete, auth.login, auth.revoke
meshguard-cli.sh signup --name "Acme Corp" --email admin@acme.com
Creates a new org and returns API credentials. Requires MESHGUARD_ADMIN_TOKEN.
Onboard a new agent with policy:
meshguard-cli.sh agents create my-agent --tier promeshguard-cli.sh policies create policy.yamlmeshguard-cli.sh agents listInvestigate agent activity:
meshguard-cli.sh audit query --agent my-agent --limit 20meshguard-cli.sh agents get <id>See skills/meshguard/references/api-reference.md for full endpoint documentation.