agentsclimarketplace

Ganhuo ai ip quality

Skill yuanyuanyuan430/ganhuo-ai-ip-quality/skills/ganhuo-ai-ip-quality

Use this Skill when the user provides IPs, proxy endpoints, proxy export tables, or network environment notes and wants to screen IP quality for ads operations, account operations, Ganhuo AI workflows, or proxy pool triage. Use it to verify exits, classify ASN/ISP and hosting signals, find duplicated or concentrated ranges, rank relative quality, and produce a human-reviewable risk table. Do not use it to evade platform enforcement, bypass bans, promise account safety, scrape unauthorized services, or submit proxy credentials to untrusted public websites.From its SKILL.md

Install
npx -y skills add yuanyuanyuan430/ganhuo-ai-ip-quality --skill ganhuo-ai-ip-quality

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

4.1 KB, ~1.2k tokens by cl100k_base, as published. Nobody here has run it

Ganhuo AI IP Quality

这个 Skill 解决什么问题

ganhuo-ai-ip-quality 专门处理一个运营里很容易被忽略的问题:广告、账号、素材、落地页都在排查,最后才发现网络环境一开始就不干净。

它的目标不是“保证不封号”,而是把 IP 和代理出口变成一张可复核的质量排序表,让团队先筛掉明显不适合继续测试的网络环境,再把剩下的候选 IP 交给人做业务判断。

核心原则:

  • 先验证实际出口,再谈质量;
  • 用多项公开信号交叉判断,不迷信单一查询结果;
  • 明确区分“证据支持”和“需要人工复核”;
  • 不承诺防封、不规避平台风控、不帮助账号滥用;
  • 输出必须能被人、agent、运营表格继续复用。

什么时候使用

当用户提供下面材料时,使用这个 Skill:

  • 单个 IP 或一批 IP;
  • HTTP、HTTPS、SOCKS5 等代理地址;
  • AdsPower、浏览器环境、代理池或供应商导出的表格;
  • 账号登录、广告投放、独立站测试前的网络环境清单;
  • 对“这批 IP 哪个质量更好”的排序需求;
  • 对“为什么这批广告或账号环境异常”的基础排查需求。

如果用户要求保证不封号、绕过封禁、规避平台检测、批量滥用账号,拒绝这些目标,只能提供合规的环境风险筛查和人工复核建议。

必读文件

  • references/ip-quality-playbook.md for the screening workflow.
  • references/ip-quality-output-standard.md for the delivery package.
  • references/ip-quality-risk-rules.md when scoring risk, tiers, and red lines.
  • references/ip-quality-material-notes.md when the user provides proxy credentials, exports, tables, or mixed materials.
  • templates/ip-check-brief.md when the user needs an intake template.

执行流程

  1. 读取输入,识别 IP、代理、目标国家、使用场景、供应商、账号重要性和备注。
  2. 先做安全处理:代理密码只保留给本地连接,不在输出中明文展示,不提交到不可信网页。
  3. 验证连通性和真实出口 IP。能跑网络检测时,用代理访问出口查询服务;不能跑时,说明未实测并转为静态评估。
  4. 查询公开信号:国家/地区、ASN、ISP、组织名、托管/代理/VPN/Tor/移动/住宅等标签。
  5. 检查批量风险:重复出口、同一 /24 或 ASN 过度集中、地区不匹配、供应商描述和实测不一致、出口漂移。
  6. references/ip-quality-risk-rules.md 打分和分层。
  7. references/ip-quality-output-standard.md 返回完整交付包。
  8. 最后做质量检查:证据是否足够、红线是否标出、密码是否脱敏、是否出现防封承诺、是否留下人工复核事项。

默认交付

  1. IP 质量排序表
  2. 风险分层
  3. 证据说明
  4. 人工复核清单
  5. 下一步小规模测试建议
  6. 不确定项和限制说明

质量底线

宁可把结论写成“需要复核”,也不要把证据不足的 IP 写成“安全”。

每个结论必须处在下面四种状态之一:

  • 已通过当前检测或公开查询支持;
  • 用户材料已经明确说明;
  • 标为待复核;
  • 删除或弱化。

永远不要承诺账号安全、广告通过、平台不风控。永远不要把代理密码、账号资料或敏感业务信息写进公开输出。

发布前校验

仓库发布前运行:

python3 scripts/validate_skill.py

What ships with it: 8 files

11.1 KB alongside SKILL.md

templates/

Keep looking

Skills are one crate of 326,149. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.