← 返回 Skills 市场
berthelol

SEO GEO for SaaS

作者 berthelol · GitHub ↗ · v1.0.2 · MIT-0
cross-platform ✓ 安全检测通过
134
总下载
1
收藏
2
当前安装
3
版本数
在 OpenClaw 中安装
/install seo-geo
功能描述
Complete SEO + GEO (Generative Engine Optimization) system for SaaS companies wanting to rank on both Google and AI search engines (ChatGPT, Perplexity, Gemi...
使用说明 (SKILL.md)

SEO + GEO for SaaS

A battle-tested SEO system built by a bootstrapped SaaS founder who grew from 0 to 30k+ organic sessions/month. This isn't theory — it's the exact methodology, templates, and checklists used to rank a real SaaS product.

This skill covers two modes:

  1. Setup — onboard a new SaaS, analyze existing SEO, build a strategy, create a content calendar
  2. Publish — write, optimize, and ship SEO+GEO articles using proven templates

First-time setup

If the user has never used this skill before (no seo/ directory in their project), run the onboarding flow. Read references/onboarding.md for the full step-by-step process.

Onboarding creates these files in the user's project:

seo/
├── overview.md        # Site architecture, clusters, competitor landscape — context for spawning new agents
├── keywords.md        # Master keyword table — local cache, avoids repeat API calls
├── opportunities.md   # Prioritized gaps, CTR fixes, quick wins
├── published.md       # Log of every published article — avoids needing a database
├── calendar.md        # 5-month content calendar with progress tracking
├── positioning.md     # Current rankings snapshot — updated during audits
├── templates.md       # Article templates adapted for the user's SaaS
└── screenshots/       # Product screenshots to use as article images
├── positioning.md     # Current rankings snapshot
└── templates.md       # Article templates adapted for their SaaS

Choosing your SEO data source

This skill works with two data providers. During onboarding, ask the user which they have access to:

Option A: SemRush (preferred if available)

  • More accurate keyword data, better competitor intelligence
  • If the user has the semrush-research skill installed, use it directly
  • Otherwise, ask the user to export data from SemRush web UI (CSV exports)

Option B: DataForSEO (recommended if no SemRush)

  • Cheaper, API-first, good enough for most SaaS
  • If the user has the dataforseo skill installed, use it directly
  • If the user has an account, help them configure credentials

Option C: Manual data

  • User pastes data from Google Search Console, exports, or screenshots
  • Works but slower — encourage API setup for ongoing use

Always check which skills are available before asking the user to install anything.


Two operating modes

Mode 1: Strategy & Analysis

Use when the user asks to analyze their SEO, find opportunities, audit performance, or plan content.

Workflow:

  1. Read the user's seo/ files to understand current state
  2. Pull fresh data (via SemRush, DataForSEO, or user-provided exports)
  3. Update the relevant files (keywords.md, opportunities.md, positioning.md)
  4. Recommend next actions based on the data

Key analyses available:

  • Keyword gap analysis (what competitors rank for that you don't)
  • CTR audit (high-impression pages with low CTR = quick wins)
  • Content cluster mapping (identify missing hub/spoke pages)
  • Competitor benchmarking (traffic, keywords, content strategy)
  • Ranking movement tracking (what's improving, what's dropping)

For keyword research methodology, read references/keyword-research.md. For content cluster strategy, read references/content-strategy.md. For the biweekly audit framework, read references/audit-framework.md.

Mode 2: Content Publishing

Use when the user asks to write an article, blog post, or any SEO content.

Workflow:

  1. Read seo/templates.md to pick the right template
  2. Read seo/keywords.md to identify target keywords
  3. Write the article following the template structure
  4. Apply GEO optimization (read references/geo-optimization.md)
  5. Run pre-publish checklist (read references/pre-publish-checklist.md)
  6. Generate thumbnail if needed (read references/thumbnail-guide.md)

Important: Before writing ANY article, invoke the seo-geo companion skill for validation (listed in recommended skills above). It handles technical SEO validation, schema markup, AI bot access, and GEO scoring. This skill handles strategy, templates, and the publishing workflow. They complement each other.

For article templates, read references/templates.md. For the pre-publish checklist, read references/pre-publish-checklist.md.


Reference files

File When to read
references/onboarding.md First-time setup, when user says "set up SEO" or no seo/ folder exists
references/keyword-research.md Keyword analysis, finding opportunities, gap analysis
references/content-strategy.md Cluster planning, content architecture, competitor mapping
references/templates.md Writing any article or blog post
references/pre-publish-checklist.md Before publishing any content (ALWAYS read this)
references/geo-optimization.md Optimizing for AI search engines (ChatGPT, Perplexity, etc.)
references/audit-framework.md Biweekly performance audits, tracking progress
references/thumbnail-guide.md Creating blog post thumbnails

Key principles

This skill is built for SaaS companies. Every recommendation assumes:

  • You're selling software, not content
  • Articles exist to drive signups, not ad revenue
  • Your product IS the CTA — not affiliate links
  • Competitor comparisons are a core content type
  • Technical credibility matters more than content volume

Content clusters, not random articles. Every piece of content belongs to a cluster with a pillar page. Orphan content is wasted effort.

CTR fixes before new content. If you have pages with thousands of impressions but \x3C1% CTR, fix those first. It's the fastest ROI in SEO.

GEO is not optional. AI search engines (ChatGPT, Perplexity, Gemini, Claude) are sending increasing traffic. Every article must be optimized for both Google AND AI citation. The Princeton 9 methods are baked into every template.

Measure everything. Biweekly audits are built into the calendar. No audit = no idea if your strategy is working.

安全使用建议
This skill appears internally consistent for SEO work, but because it asks for sensitive API credentials and the package has no public homepage or identifiable author you should take precautions before installing: 1) Prefer granting read-only, least-privilege Google access (or use a service account / limited OAuth scopes) rather than full account credentials or a long-lived refresh token if possible. 2) Store secrets in a secrets manager rather than pasting them into chat. 3) Back up and review any existing seo/ files before running the onboarding flow — the skill will create/modify files in your project. 4) Review generated content and any quoted/external-sourced material for accuracy and copyright concerns before publishing. 5) Verify and inspect the recommended companion skill (seo-geo / dataforseo / ga4) implementations before invoking them. 6) If you are unsure about granting tokens to an unknown source, run onboarding manually (export GSC/Ga4/DataForSEO CSVs) instead of providing live credentials.
功能分析
Type: OpenClaw Skill Name: seo-geo Version: 1.0.2 The seo-geo-for-saas skill bundle is a comprehensive and legitimate SEO/GEO optimization tool. While it requires sensitive environment variables (Google OAuth tokens and DataForSEO credentials) and the 'curl' binary, these are functionally necessary for its stated purpose of auditing search performance and keyword research. The extensive documentation in files like SKILL.md and onboarding.md provides clear, non-malicious instructions for the AI agent to manage SEO workflows, and there is no evidence of data exfiltration, malicious execution, or prompt injection intended to subvert the agent's behavior.
能力标签
cryptocan-make-purchasesrequires-oauth-token
能力评估
Purpose & Capability
The skill is an SEO/GEO system and it requests Google OAuth credentials (client id/secret/refresh token) and DataForSEO login — both are reasonable for pulling Search Console/GA4 and DataForSEO data. curl is used for robots.txt and bot-access checks and matches the documented workflows. No unrelated services, binaries, or config paths are requested.
Instruction Scope
SKILL.md is instruction-only and stays within SEO scope: it reads/writes an seo/ directory in the user's project (creates overview/keywords/opportunities/calendar/etc), pulls data from Search Console / GA4 / DataForSEO / SemRush (when available), and runs pre-publish checks (robots.txt, schema validation). There are no instructions to read unrelated system files or user shell history. Note: the skill will create and modify files in the user's project — review those outputs before publishing.
Install Mechanism
No install spec or external downloads — instruction-only. This minimizes risk because no archive or arbitrary executable is fetched or written to disk by an installer step.
Credentials
The required env vars (GOOGLE_CLIENT_ID, GOOGLE_CLIENT_SECRET, GOOGLE_REFRESH_TOKEN, DATAFORSEO_LOGIN, DATAFORSEO_PASSWORD) are proportionate to the described integrations. However these are sensitive credentials: Google tokens give access to Search Console/GA4 data and DataForSEO credentials give API access. The skill asks for multiple secrets, which is expected for this use case but warrants careful handling (use least-privilege tokens, read-only scopes, service accounts where possible).
Persistence & Privilege
The skill does not request always:true and does not try to modify other skills or system-wide configs. Its runtime behavior writes files into the user's project (creates seo/ and reference files) which is expected for its purpose. Autonomous model invocation is allowed by default but not, by itself, a red flag here.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install seo-geo
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /seo-geo 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.2
- Added required environment variables for Google and DataForSEO integrations (`GOOGLE_CLIENT_ID`, `GOOGLE_CLIENT_SECRET`, `GOOGLE_REFRESH_TOKEN`, `DATAFORSEO_LOGIN`, `DATAFORSEO_PASSWORD`). - Updated onboarding instructions for DataForSEO: now helps users configure credentials directly if they have an account. - Clarified that invoking the companion `seo-geo` skill is required before article publishing, referencing its inclusion in recommended skills instead of a manual install command. - Removed reference to `python3` as a required binary. - No functional or logic changes; documentation and metadata only.
v1.0.1
- Documentation updated for clarity; no functional or technical changes in this version. - All code and configuration files remain the same as previous release (no file changes detected). - No impact to existing onboarding, workflows, or SEO/GEO methodology. - Safe to upgrade; no action required for users.
v1.0.0
Initial release of seo-geo-for-saas - Provides a complete SEO + GEO system tailored for SaaS companies targeting both Google and AI search engines (ChatGPT, Perplexity, Gemini, Claude). - Supports both strategy/analysis (gap analysis, audits, competitor benchmarking) and content publishing (templates, article writing, GEO optimization). - Includes a guided onboarding process that creates a full set of SEO planning and tracking files. - Integrates with SemRush, DataForSEO, or manual data sources, with recommendations based on available access. - Emphasizes content clusters, CTR-focused optimizations, and biweekly audit workflows. - Designed to maximize SaaS signups by aligning all output with proven, product-focused SEO best practices.
元数据
Slug seo-geo
版本 1.0.2
许可证 MIT-0
累计安装 2
当前安装数 2
历史版本数 3
常见问题

SEO GEO for SaaS 是什么?

Complete SEO + GEO (Generative Engine Optimization) system for SaaS companies wanting to rank on both Google and AI search engines (ChatGPT, Perplexity, Gemi... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 134 次。

如何安装 SEO GEO for SaaS?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install seo-geo」即可一键安装,无需额外配置。

SEO GEO for SaaS 是免费的吗?

是的,SEO GEO for SaaS 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

SEO GEO for SaaS 支持哪些平台?

SEO GEO for SaaS 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 SEO GEO for SaaS?

由 berthelol(@berthelol)开发并维护,当前版本 v1.0.2。

💬 留言讨论