name: 4d-compression-core version: 1.0.2 description: "把长内容压缩成结构化向量——节省 60-80% Token,保留核心信息" metadata: { "openclaw": { "emoji": "🌀", "requires": { "bins": ["jq", "awk"] }, "triggers": ["压缩", "4d",...
中文简介正在准备中。当前显示原文说明。
Network-wide ad and tracker blocking at the DNS level. A Pi-hole alternative that runs directly on your machine as an OpenClaw skill. No separate hardware needed.
中文简介正在准备中。当前显示原文说明。
查看安装方法安装前可以查看交给 AI 代理的指令内容。
Network-wide ad and tracker blocking at the DNS level. A Pi-hole alternative that runs directly on your machine as an OpenClaw skill. No separate hardware needed.
Runs a DNS sinkhole server that blocks ads, trackers, malware, and telemetry domains across your entire network. Any device that uses this machine as its DNS server gets ad-free browsing automatically — phones, tablets, smart TVs, laptops, IoT devices, everything.
Blocks 189,000+ ad and tracker domains using the same blocklists as Pi-hole (Steven Black, AdAway, EasyList, EasyPrivacy, Anti-Malware). Blocks both IPv4 (A) and IPv6 (AAAA) queries.
Works great for: Banner ads on websites, tracking pixels, third-party ad networks (Doubleclick, Amazon Ads, Criteo, Rubicon, etc.), in-app ads, telemetry/analytics trackers, malware domains.
Won't block: YouTube ads, Twitch ads, or any ads served from the same domain as the content itself. These platforms serve ads from their own CDN (e.g. googlevideo.com for YouTube), so blocking the domain would break the entire service. This is a fundamental limitation of ALL DNS-level blockers including Pi-hole. For YouTube ads, use a browser extension like uBlock Origin.
The skill runs a DNS server on this machine. When a device queries a domain:
All queries are logged with stats (total queries, blocked percentage, top blocked domains).
cd /path/to/skills/adblock/scripts
bash setup.sh
This will:
The user will need to enter their sudo password once during setup.
Alternative (manual start without systemd):
sudo node dns-server.js
This is the critical step. The DNS server does nothing until devices point to it.
Find this machine's local IP address:
hostname -I | awk '{print $1}'
Then configure devices to use that IP as their DNS server:
Router (blocks entire network):
Individual devices:
nmcli con mod "Wi-Fi" ipv4.dns "MACHINE_IP"# Should return 0.0.0.0 (blocked)
nslookup ads.google.com MACHINE_IP
# Should return a real IP (allowed)
nslookup google.com MACHINE_IP
Or check the API: curl http://localhost:8053/stats
When the user asks about ad blocking, use these:
curl -s http://localhost:8053/stats | python3 -m json.tool
Report: total queries, blocked queries, block percentage, top blocked domains.
If something is broken because it's being blocked:
curl -s -X POST http://localhost:8053/whitelist/add -H "Content-Type: application/json" -d '{"domain":"example.com"}'
curl -s -X POST http://localhost:8053/blacklist/add -H "Content-Type: application/json" -d '{"domain":"annoying-site.com"}'
curl -s "http://localhost:8053/check?domain=ads.google.com"
Blocklists auto-update every 24 hours. To force an update:
curl -s -X POST http://localhost:8053/update
curl -s http://localhost:8053/whitelist
The setup.sh script handles this automatically. If you need to manage it manually:
sudo systemctl start adblock-dns # Start
sudo systemctl stop adblock-dns # Stop
sudo systemctl restart adblock-dns # Restart
sudo systemctl status adblock-dns # Check status
journalctl -u adblock-dns -f # View logs
# Remove completely
sudo systemctl disable adblock-dns
sudo rm /etc/systemd/system/adblock-dns.service
sudo systemctl daemon-reload
Edit data/config.json:
{
"upstream": "1.1.1.1", // Upstream DNS (Cloudflare, Google 8.8.8.8, etc.)
"port": 53, // DNS port (53 = standard, needs sudo)
"apiPort": 8053 // Stats API port
}
data/blocklist.txt - Compiled blocklist (auto-generated)data/whitelist.txt - Whitelisted domains (one per line)data/custom-blacklist.txt - Extra domains to block (one per line)data/stats.json - Query statisticsdata/config.json - Server configuration还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
name: 4d-compression-core version: 1.0.2 description: "把长内容压缩成结构化向量——节省 60-80% Token,保留核心信息" metadata: { "openclaw": { "emoji": "🌀", "requires": { "bins": ["jq", "awk"] }, "triggers": ["压缩", "4d",...
中文简介正在准备中。当前显示原文说明。
Use cheap, TEE-verified AI models from the 0G Compute Network as OpenClaw providers. Discover available models and compare pricing vs OpenRouter, verify provider integrity via hardware attestation (Intel TDX), manage your 0G wallet and sub-accounts, and configure models in OpenClaw with one workflow. Supports DeepSeek, GLM-5, Qwen, and other models available on the 0G marketplace.
中文简介正在准备中。当前显示原文说明。
Send and receive P2P messages using disposable numbers and PINs. No servers, no accounts. Use for human notifications, approval flows, and agent-to-agent communication.
中文简介正在准备中。当前显示原文说明。
Query historical crypto market data from 0xArchive across Hyperliquid, Lighter.xyz, and HIP-3. Covers orderbooks, trades, candles, funding rates, open interest, liquidations, and data quality. Use when the user asks about crypto market data, orderbooks, trades, funding rates, or historical prices on Hyperliquid, Lighter.xyz, or HIP-3.
中文简介正在准备中。当前显示原文说明。
Find and complete paid tasks on the 0xWork decentralized marketplace (Base chain, USDC escrow). Use when: the agent wants to earn money/USDC by doing work, discover available tasks, claim a bounty, submit deliverables, check earnings or wallet balance, or set up as a 0xWork worker. Task categories: Writing, Research, Social, Creative, Code, Data. NOT for: posting tasks (use the website), managing the 0xWork platform, or frontend development.
中文简介正在准备中。当前显示原文说明。
Patterns and practices that dramatically accelerate development velocity. Covers parallel execution, automation, feedback loops, workflow optimization, and anti-pattern avoidance. Use when starting projects, planning sprints, optimizing workflows, or onboarding developers.
中文简介正在准备中。当前显示原文说明。