Real Skill packageSource verifiedClawHub registry

geo-cn

GEO-CN v2.0.4 (AI Native) — 面向中国市场的生成式引擎优化执行技能。以「直接问 AI」为地面真值、分层证据审计为引擎，诊断→优化→监测三阶段闭环。覆盖豆包、文心一言、DeepSeek、Kimi、元宝，及百科/知乎/抖音/小红书/B站/地图生态。

Identity and source

Publisher attributionxpregistry owner unverified by skillvetai
Functional categoryAwaiting category reviewreview pending · 0% rule confidence
Package forminstruction bundle6 recorded files
Canonical sourceClawHub registryclawhub:xp1001:geo-cn
Open canonical source ↗

Platform declarations

These states come from the source or distribution context. None of the entries below are SkillVetAI compatibility test results.

OpenClawnative officialProvenance: registry distribution

Independent structural checks

These checks parse the fixed package against dated platform rules. They do not execute the Skill or verify task behavior.

Claude Codepasses structure
Checker 0.1.0 · agent-skills-2026-08-13+claude-code-docs-2026-08-13 · 9/20/2026.claude/skills/geo-cn

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

OpenAI Codexpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+codex-docs-2026-08-13 · 9/20/2026.agents/skills/geo-cn

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

OpenClawpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+openclaw-docs-2026-08-13 · 9/20/2026skills/geo-cn

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

Installation and inspection

This command is recorded from the source ecosystem and resolves the registry's latest release. The fixed release shown on this page should be inspected before adoption.

clawhub install @xp1001/geo-cn
clawhub inspect @xp1001/geo-cn --version 2.0.4

Security evidence

SkillVetAI static result: no findings detected

This automated, non-executing scan is bound to this release hash. It is not a safety certification and may contain false positives or false negatives.

Status
completed
Coverage
full text content
Files
6 / 6 inspected as text
Checked
9/20/2026, 4:09:55 PM
Scanner
0.1.3
Policy
1.0.3
1 inferred permission indicators
  • network access — automatically inferred
3 dependency and API indicators
  • api: chat.baidu.com
  • api: clawhub.ai
  • api: github.com
External clawhub result: clean

This is registry-supplied evidence for the recorded release, not an independent SkillVetAI scan. Check the canonical source for the full report, scanner versions, scope, and current moderation state.

Evidence checked
9/20/2026, 2:31:50 PM
Release binding
Matches this record
  • vt: clean
  • skillspector: suspicious
  • llm: clean

Recorded files

The catalog stores hashes and an inventory summary for change detection. It does not republish the package contents.

Package content hashsha256:7c9d9aeef965b7274837d88d304c46fd89d1770de1daa613b6496f78aa4a9fc5
Show up to 6 recorded paths
  • _meta.json
  • CHANGELOG.md
  • README.md
  • skill-card.md
  • SKILL.md
  • SKILL.v1.md

Source changelog

GEO-CN v2.0.4 变更说明（自 v1.0.1 升级） 一句话总结 从「用搜索引擎结果推断品牌状态」的静态 SOP，重构为「直接问 AI 测量引用」的 AI Native 诊断引擎——诊断→优化→监测全程可测量、可复现、可存档追踪。 为什么必须升级 v1.x 在实战首跑中暴露结构性缺陷：8 个诊断维度误判 3 个（官网漏检、知乎计数失真、社媒矩阵漏盘）。根因是用“搜索引擎可见性”这个代理指标，去推断“品牌资产”和“AI 引用”两个不同的问题。v2.0 按实战验证过的执行引擎重写了协议。 v2.0.0 核心重构 新增第零步：AI 平台实测——直接在 AI 平台问客户的“金钱问题”，以「AI 引用率」为北极星指标，诊断从推断变为测量 分层证据审计：L1-L5 证据阶梯（关键词检索→site: 定向→直连/API→浏览器渲染→客户确认）+ 负证据硬规则：搜到 ≠ 不存在被禁绝，任何 ❌ 判定需两级证据，无法核实一律记 ❓待核查 客户实体档案（强制门禁）：最小可行档案三项即可开工（品牌名/地域/行业），其余字段由审计回填；新增跨平台一致性校验（名称变体、数据口径、POI 名称冲突——AI 实体识别的关键信号） 封闭平台分治协议：抖音/小红书等封闭生态禁止用搜索引擎下结论（实测会产生误关联），改用短链解析+浏览器渲染等实测路径 实测验证的平台数据获取路径速查：B站开放API、知乎主页直读、小红书/抖音分享短链解析、百度地图POI公开接口 存档 v2 格式：实体档案+记录数组，支持勘误类型，向后兼容 v1.x 旧存档 模块 A-E（百科/FAQ/知乎/新闻稿/平台优化）领域知识完整保留，文件自包含 v2.0.1 — 冷启动压测修复（10 项） 最小可行档案消除门禁死锁；新增自主运行模式（客户不在场可完整执行）；AI 实测平台重分组（百度AI搜索为免登录自动化首选）；答案完成判定（流式渲染防误判）；测量污染规避（独立会话+答案区定位）；引用稳定性规范（监测对比关键问题测 2 次取多数）；高德/腾讯路径修正；自查表模板；预检探针具体化。 v2.0.2 — 小白友好化 三级问询…