What makes GEO Growth Orchestrator notable?

1.3K downloads. Trust evidence available

How should GEO Growth Orchestrator be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

GEO Growth Orchestrator

Unified GEO growth workflow for brand knowledge base building, LLM visibility audits, Doubao/DeepSeek readiness review, AI-GEO content asset generation, plat...

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.3k

Updated

Oct 10, 2026

Version

1.0.6

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.3K downloads reported by the source. Last updated 10/10/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 10, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 10, 2026
Adoption signal: 1.3K downloadsadoption · observed Oct 10, 2026
Latest release: 1.0.6release · observed Jun 15, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s172qdnna7e9rmecem8tckdtd1845fvv:geo-growth-orchestrator

Install using `clawhub skill install s172qdnna7e9rmecem8tckdtd1845fvv:geo-growth-orchestrator` in an isolated environment before connecting it to live workloads.
No published capability contract is available yet, so validate auth and request/response behavior manually.
Review the upstream CLAWHUB listing at https://clawhub.ai/ljseeking/geo-growth-orchestrator before using production credentials.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-ljseeking-geo-growth-orchestrator/snapshot"

Documentation

CLAWHUB

160,000 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: powermatrix-geo-growth-orchestrator
description: Unified GEO growth workflow for brand knowledge base building, LLM visibility audits, Doubao/DeepSeek readiness review, AI-GEO content asset generation, platform draft planning for Zhihu/Toutiao/CSDN/Juejin, client delivery reports, internal QA, and 7/14/30 day retests. Use when Codex needs to analyze or improve a brand's AI search visibility, generate GEO reports, diagnose model mentions/citations/rankings, create GEO-friendly content tasks, or consolidate GEO platform workflows into one human-reviewed delivery package.
---

# PowerMatrix GEO Growth Orchestrator

This skill is now the unified GEO workflow. It can run as one self-contained skill instead of requiring separate Doubao audit, DeepSeek audit, AI-GEO content, and platform draft skills.

Use the old neighboring skills only as optional references when the user explicitly asks to inspect or preserve their original behavior. Do not require the user to understand or invoke multiple GEO skills.

## Core Promise

Turn brand materials into a human-reviewed GEO delivery package:

1. Resolve the brand entity and aliases.
2. Build or validate the brand knowledge base.
3. Plan and record LLM probes for Doubao, DeepSeek, generic LLMs, or user-provided model answers.
4. Score visibility, mentions, citations, ranking position, answer quality, factual accuracy, localization, and conversion usefulness.
5. Identify content gaps and commercial impact.
6. Generate GEO-friendly content tasks and reusable content assets.
7. Adapt tasks for Zhihu, Toutiao, CSDN, Juejin, Xiaohongshu, Douyin, or manual publishing.
8. Produce client-facing and internal QA reports.
9. Create a 7 / 14 / 30 day retest plan.

## Required First Moves

1. Identify the task type:
- `audit_only`: visibility diagnosis and report.
- `content_only`: content assets and platform drafts.
- `full_workflow`: audit, gap analysis, assets, drafts, delivery report, retest plan.
- `debug_existing_report`: investigate mismatch between model output and report.
2. Normalize the brand entity:
- Extract `brand_name`.
- Extract `company_name` if present.
- Build `brand_aliases`, including abbreviations, city + brand, brand + service, legal name, common short name, old names, pinyin/English names, and likely spelling variants.
- Keep category keywords separate from brand aliases.
3. Decide evidence level before making claims:
- `verified_live_check`: live model/API/platform check with query, answer, time, and raw evidence.
- `manual_check`: user-provided screenshot, copied answer, or manual summary with time/source.
- `inferred_estimate`: reasoning from brand materials only.
- `unverified_assumption`: weak assumption for planning only.
4. If there is no live or manual evidence, do not state rankings, scores, model citations, or "not mentioned" as fact. Output a check plan or mark findings as inferred.

## Inputs

Minimum natural-language input is acceptable. Pre

README.md

# PowerMatrix GEO Growth Orchestrator

PowerMatrix GEO Growth Orchestrator 是一个企业 AI 内容增长工作流 Skill。它把品牌母库、GEO 可见度检测、内容缺口分析、GEO 内容生成和多平台草稿助手串联起来，让企业从“一堆资料”走到“一批可人工审核发布的内容草稿、客户成果报告和内部审计报告”。

它不是某一个平台的写作助手，而是总控层：负责判断先做什么、调用什么能力、输出哪些中间结果、哪些内容需要人工确认。

## 适合什么场景

- 企业希望提升品牌在 AI 搜索、问答模型和内容平台中的可见度。
- 市场团队需要把官网、产品介绍、FAQ、案例整理成可复用内容资产。
- 内容运营需要一次性生成知乎、CSDN、掘金、今日头条等平台的草稿任务。
- AI / GEO 服务交付顾问需要一个标准交付流程，避免每次从零组织材料。
- PowerMatrix 内部团队需要把品牌母库、检测报告、内容包和复盘建议串成闭环。

## 用户如何开始

用户只需要提供四类信息：

1. 企业资料：公司介绍、产品服务、官网、FAQ、案例、联系方式、禁用说法。
2. 目标关键词：希望被 AI 和平台内容覆盖的搜索词。
3. 目标平台：例如知乎、CSDN、掘金、今日头条。
4. 任务目标：例如品牌可见度提升、AI 搜索覆盖、获客内容生成。

如果已经有品牌母库或 GEO 检测报告，可以直接提供，工作流会优先复用。

## 第一次使用需要准备什么资料

建议至少准备：

- 品牌名称、公司简介、产品和服务说明。
- 目标客户、典型场景、客户痛点。
- 核心卖点和证据来源。
- 常见问题和标准回答。
- 官网、产品页、案例页、联系方式。
- 品牌语气、禁用词、禁用承诺、合规边界。

资料不完整也可以开始，但缺失信息会被标记为 `待确认`，不会由系统编造。

## 一次完整工作流会输出什么

这个 Skill 有两类输出：

1. 客户成果报告：用于商务交付、客户沟通、复盘会议。
2. 内部审计报告：用于交付团队检查事实、合规、风险和证据等级。

对客户展示时，优先使用：

- `client_delivery_report.md`：客户可见成果报告。
- `content_asset_summary.md`：客户可读的内容资产摘要。
- `publish_plan_client.md`：客户版发布计划。

内部复盘时，使用：

- `internal_audit_report.md`：内部审计报告。
- `brand_profile.json`：标准品牌资料。
- `geo_audit_report.json`：关键词和模型维度的可见度检测结果。
- `content_gap_report.json`：内容缺口和优先补齐项。
- `content_tasks.json`：可执行的内容任务清单。
- `platform_drafts.json`：知乎、CSDN、掘金、今日头条等平台草稿。
- `publish_plan.json`：内部发布计划。

建议输出目录：

```text
geo_orchestrator_v2/
├── final_report.md
├── summary.md
├── client_delivery_report.md
├── internal_audit_report.md
├── content_asset_summary.md
├── publish_plan_client.md
├── raw_answers/
│   └── {model}/{probe_id}.md
├── model_scores/
│   └── {model}.json
├── dual_model_comparison.json
├── content_recommendations.json
├── geo_action_priorities.json
├── brand_profile.json
├── geo_audit_report.json
├── content_gap_report.json
├── content_tasks.json
├── platform_drafts.json
└── publish_plan.json
```

## OpenClaw 中的默认输出模式

默认 `output_mode` 是 `full_report`。除非用户明确要求“只要摘要”，否则 OpenClaw 执行完成后必须在聊天窗口输出完整 `final_report.md` 正文。

禁止只回复：

- “报告已生成，请查看目录”
- “已保存到本地文件”
- 只有 3 到 5 行执行摘要

如果使用脚本生成客户交付级双模型评估报告，推荐运行：

```bash
python3 scripts/generate_full_report.py examples/spanish_olive_oil_input.json --output-dir geo_orchestrator_v2
```

这个脚本会同时：

- 保存 `final_report.md`
- 保存 `summary.md`
- 保存每个模型每个探针的原始回答
- 保存每个模型评分 JSON
- 保存双模型对比 JSON
- 保存内容生产建议 JSON
- 保存 GEO 行动优先级 JSON
- 默认把完整 `final_report.md` 打印到当前对话输出

## 和单个平台 Draft Assistant 的区别

单个平台 Draft Assistant 负责把已有素材改写成某个平台的草稿。例如知乎助手偏问答和观点，CSDN 助手偏技术教程，掘金助手偏开发者实践，今日头条助手偏通俗商业场景。

本 Orchestrator 负责更上游的编排：

- 判断是否已有品牌母库。
- 规划 DeepSeek、豆包、通用环境的 GEO 检测。
- 从检测结果中找内容缺口。
- 把内容缺口拆成不同平台的内容任务。
- 汇总草稿、发布计划和复盘建议。

## 如何识别相邻 Skill

当前 `Skills/` 目录下的各个 Skill 是平行文件夹，不是本 Skill 的子目录。Orchestrator 通过 `registry/geo_skill_registry.json` 识别相邻能力，所有路径都使用相对于本目录的 `../` 形式，例如：

- `../AI-geo-content-generator`
- `../geo-analysis-doubao`
- `../deepseek-geo-audit-skill`
- `../zhihu-geo-draft-assistant`
- `../toutiao-geo-draft-assistant`
- `../csdn-geo-draft-publisher`
- `../juejin-geo-draft-publisher`
- `../GEO tool-deepseek`

Registr

videos/powermatrix-geo-not-volume/README.md

# PowerMatrix GEO 30s Video

This folder contains a HyperFrames-style 9:16 composition for:

《GEO 不是以量取胜》

## Files

- DESIGN.md - visual system used by the composition
- index.html - HyperFrames source composition, 1080 x 1920, 30 seconds
- script.md - timed script, subtitles, and voiceover text

## Local Review

Open index.html?preview=1 in a browser to use the built-in lightweight preview mode. The source still keeps HyperFrames data-composition, data-start, data-duration, data-track-index, and window.__timelines structure for later CLI rendering.

## Render Note

The HyperFrames CLI could not be fetched in this environment because npm DNS resolution failed. Once the CLI is available, run from this folder:

~~~bash
npx hyperframes lint
npx hyperframes inspect --samples 15 --at 1.5,5.5,11.5,19,26.5
npx hyperframes preview --port 3017
npx hyperframes render --output powermatrix-geo-not-volume.mp4 --quality standard
~~~

_meta.json

{
  "ownerId": "kn73cb2q9jxf7f610j0m0bwdbn8452jk",
  "slug": "geo-growth-orchestrator",
  "version": "1.0.6",
  "publishedAt": 1781544516709
}

references/entity-evidence-rules.md

# Entity, Evidence, Mention, Citation, And Ranking Rules

Use this reference whenever the task involves model visibility, "mentioned/not mentioned" disputes, citation/source ranking, or audit scoring.

## Entity Normalization

Build separate lists:

- `brand_aliases`: names that refer to the target entity.
- `category_keywords`: business/category/search terms.
- `competitor_aliases`: names that refer to competitors or alternatives.
- `channel_terms`: platforms, stores, regions, distributors, or source domains.

Do not count `category_keywords` as brand mentions. A category hit can improve topical relevance, but it is not brand visibility.

Recommended alias expansion for Chinese local brands:

- full legal or school/company name
- short brand name
- city + brand
- brand + service/category
- brand + school/company/store/training center
- old names and common public listing names
- pinyin/English names if used publicly
- likely punctuation, spacing, and suffix variants

Example:

```json
{
  "brand_name": "大连米嘟西点培训学校",
  "brand_aliases": [
    "大连米嘟西点培训学校",
    "米嘟西点",
    "米嘟西点培训",
    "米嘟西点培训学校",
    "大连米嘟西点培训",
    "大连米嘟国际西点培训",
    "大连米嘟国际西点培训学校"
  ],
  "category_keywords": ["大连西点培训", "西点培训学校", "烘焙培训", "蛋糕培训"]
}
```

## Evidence Levels

Use one of these levels for every model claim:

| Level | Meaning | Allowed claims |
|---|---|---|
| `verified_live_check` | Live/API/platform result captured with query, answer, time, source | mention, citation, source rank, score, trend |
| `manual_check` | User-provided copied answer, screenshot, manual record, or source list | mention/citation/rank if evidence is visible |
| `inferred_estimate` | Reasoning from brand materials only | content readiness and likely gaps only |
| `unverified_assumption` | Weak planning assumption | planning tasks only |

If evidence is not `verified_live_check` or `manual_check`, do not say "ranked top 3", "not mentioned", "model cited us", or "score is X".

## Mention Types

Separate these fields:

- `answer_mention`: alias appears in generated answer body.
- `citation_mention`: alias appears in source/citation title, snippet, URL, or source card.
- `source_rank`: first citation/source position where an alias appears.
- `brand_alias_hits`: exact aliases found.
- `category_keyword_hits`: category/search terms found.
- `competitor_mentions`: competitor aliases found.

Recommended output:

```json
{
  "answer_mention": false,
  "citation_mention": true,
  "source_rank": 2,
  "brand_alias_hits": ["米嘟西点"],
  "category_keyword_hits": ["大连西点培训"],
  "evidence_level": "manual_check",
  "claim_allowed": true
}
```

## Ranking Rules

Ranking can mean different things:

- `answer_rank`: position in a recommended list inside the model answer.
- `source_rank`: position in citation/source cards.
- `search_rank`: position in an external search result page.

Always label which rank is being discussed. If a brand is "top 3 in citations" but not in the answer body, report that distinction plainly

Github ReposUpdated 1d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.