Generative Engine Optimization

> English | 中文

dsh-geo 是“生成式引擎优化” DeepSeek Harness Bundle，为 Markdown 知识库提供可解释的 SEO、GEO 和 AEO 工具。

dsh-geo is a DeepSeek Harness bundle that gives the agent explainable SEO, GEO and AEO tools for Markdown knowledge bases.

Public six-plugin collaboration contract: SUITE.md.

协作可靠与增长测量

geo_artifact_review 校验 GEO/SEO/AEO 工件；geo_growth_measurement_plan 将内容、渠道和目标指标绑定起来，但不会把相关性直接当成因果。

geo_artifact_review validates GEO/SEO/AEO artifacts; geo_growth_measurement_plan binds content and channels to target metrics without treating correlation as causation.

> Technical package ID: dsh-geo · DeepSeek Harness plugin for SEO, GEO and AEO

Plugin Positioning and Collaboration Navigation

dsh-geo is the content-discoverability layer in the six-plugin system. It turns product, commercial and user language into content that search engines and AI answer engines can understand, trust and cite, with traceable evidence for reviewing impact.

• Owns: SEO/GEO/AEO audits, keyword and intent maps, content briefs, Markdown content production/review, provenance and freshness, site discoverability, product-discovery preflight and impact reviews.
• Inputs: User problems and external language from [dsh-idea](../dsh-idea/README.md), product facts from [dsh-product](../dsh-product/README.md), audience/value/conversion goals from [dsh-business](../dsh-business/README.md), and query, CTR, referral and conversion snapshots from [dsh-growth](../dsh-growth/README.md).
• Outputs: SEO/GEO/AEO audits, keyword opportunities, content briefs, previewable Markdown changes, manual distribution packs and impact reviews for growth and opportunity discovery.
• Does not own: Ranking or traffic guarantees, Search Console, PageSpeed, paid keyword tools, full crawling or website engineering. It does not log in, submit forms or mass-post.

Positioning Architecture: Commercial Strategy Layer + Four-Stage Core Flow

The six plugins work together to turn a real demand signal into a deliverable product, reach target customers through marketing, and use monetization results to drive product iteration or discover new opportunities.

flowchart TB
    S["dsh-business<br/>Commercial strategy layer<br/>Value · model · pricing · profit"]

    subgraph MAIN["Four-stage core flow"]
        direction LR
        A["1. Demand<br/>dsh-idea"] --> B["2. Product<br/>dsh-product"]
        B --> C["3. Marketing<br/>dsh-geo + dsh-growth"]
        C --> D["4. Monetization execution<br/>dsh-sales"]
    end

    S -. "Sets commercial direction and guardrails" .-> A
    D --> R["Feedback<br/>Deals · renewals · revenue · cost"]
    R -->|Product iteration| B
    R -->|New discovery| A

    classDef strategy fill:#FFF4D6,stroke:#B7791F,color:#5C4500
    classDef stage fill:#E8F1FF,stroke:#3366CC,color:#173A7A
    classDef feedback fill:#E8F7EE,stroke:#2F855A,color:#1C4532
    class S strategy
    class A,B,C,D stage
    class R feedback

This plugin owns content and discoverability in the marketing stage: it turns “what users are looking for, what the product can prove and why it should be trusted” into publishable, reviewable content assets. [dsh-business](../dsh-business/README.md) supplies value, audience and commercial boundaries; [dsh-growth](../dsh-growth/README.md) measures acquisition impact. Customer problems and content gaps found during monetization feed back to [dsh-product](../dsh-product/README.md) and [dsh-idea](../dsh-idea/README.md).

Plugin Navigation

Recommended Handoffs

What it does

• Audit one Markdown note for SEO, GEO and AEO readiness.
• Scan a vault for metadata gaps, missing sources, broken knowledge structure, orphan notes and duplicate titles.
• Check the configured root before scanning and create a shareable project report.
• Build a content brief with query, intent, audience, outline, questions and source gaps.
• Run the complete workflow from a public website URL, public account URL, Markdown export or HTML snapshot.
• Build a qualitative keyword plan from source signals, optional seed terms and Harness web search results; it never invents search volume.
• Turn the diagnosis into a four-stage production plan: diagnose, map keywords, draft, and verify.
• Check source provenance and freshness fields.
• Map the available source to a Google Search Essentials checklist: people-first content, topic language, title/description, crawlable links, HTTPS, canonical/robots signals, structured data, image alt and mobile viewport.
• Use related local knowledge-base titles, headings, entities and queries as a private keyword/content input dimension.
• Preview or apply a complete Markdown replacement, including safe creation of a new note inside defaultRoot.
• Incorporate the backlink_skills approach to candidate resources, quality gates, idempotency keys, manual queues and truthful status records; default behavior is read-only preflight and submission preparation, not mass posting.
• Compare manually supplied before/after Search Console, site-analytics or referral snapshots and route the next cycle back to diagnosis.
• Store business goal, audience, market, brand and conversion context locally so each cycle starts from the same project boundary.
• Import keyword opportunities from CSV/JSON/Markdown and map clusters to target pages, including unassigned terms and cannibalization.
• Use geo_coach to select the next useful action without introducing approval or role management.
• Review competitor gaps, backlink profile signals, bounded same-origin site audits and manually captured answer-engine citation evidence.

The plugin is local-first. Core analysis runs through the Harness filesystem service. Public URLs use the official anonymous ctx.web fetch seam; cookies and credentials are never used. Private or JavaScript-rendered pages should be exported as Markdown/HTML and analyzed as a local snapshot.

Standard SEO assistance

The built-in standard is based on Google Search Essentials, the SEO Starter Guide and the SEO maintenance guidance. It is an execution checklist, not a ranking guarantee.

For one geo_workflow run, the plugin combines four dimensions:

1. Source evidence: the page or Markdown note, its intent, facts, headings, links and provenance. 2. Local knowledge base: related note titles, headings, entities, primary queries and bounded local excerpts from defaultRoot; this stays local. 3. Keyword signals: user seed terms, source signals and qualitative public search result titles/snippets when the source is a public URL. 4. SEO standard: content, crawl/index, search presentation, links, media and monitoring checks.

The returned productionPlan.contentInputs makes these dimensions explicit before drafting. The model can then produce a Markdown draft, and geo_preview_content/geo_apply_content provide the reviewable writeback path.

The plugin deliberately reports unknown when a source cannot prove a deployment-level fact. It does not replace Search Console, PageSpeed, a full public-site crawler or a paid keyword-volume provider. Sitemap coverage, indexing, queries, clicks, Core Web Vitals and server-level robots behavior must be checked with the appropriate external tool after publication.

User and business pain points

Teams publishing content for both search engines and AI answer engines commonly face these problems:

• Traditional SEO checks focus on keywords and metadata, but do not explain whether an answer engine can understand, trust and cite the content.
• Enterprise knowledge bases accumulate missing sources, stale notes, duplicate titles and orphan pages, making content quality difficult to govern at scale.
• Writers, subject-matter experts and SEO teams use different review standards, so content decisions are slow and hard to reproduce.
• Content optimization is often disconnected from the original Markdown source, creating manual copy-paste work and a risk of overwriting newer edits.
• Teams may not be able to send private product, customer or internal knowledge-base content to an external GEO/SEO service.

This plugin turns those needs into explainable, local-first checks with evidence, scores, priorities and guarded content updates.

Typical application scenarios

• Pre-publication review: Check a new article, product page or technical note for SEO, GEO and AEO readiness before release.
• Knowledge-base governance: Scan a team or enterprise Markdown vault to find missing metadata, weak provenance, stale content, orphan notes and duplicate titles.
• Content planning: Convert a topic or existing note into a brief with audience, intent, outline, questions and source gaps.
• Product and technical documentation: Improve documentation discoverability while preserving source context and review history.
• Agency and multi-brand operations: Apply a consistent, auditable review framework across clients, sites or content teams without sharing the source vault with a third-party service.

Included tools

Install from npm

dsh plugin --profile default add dsh-geo

Install from GitHub

dsh plugin --profile default add github:winyh/dsh-geo

The package builds itself after a GitHub source install. For reproducible deployments, pin the command to a reviewed commit, for example github:winyh/dsh-geo#<commit>.

GitHub discoverability

Publish this directory as a public repository and add the repository topic dsh-plugin. The package metadata already includes dsh-plugin; the GitHub topic is what makes the repository appear in the Harness plugin topic listing.

Usage

You do not need to memorize tool names. Describe the goal, source and desired output in natural language; the examples below are copy-and-paste starting points.

Start here: a five-minute first run

You need only:

1. DeepSeek Harness installed and available as the dsh command. 2. One input: a public URL, an exported Markdown/HTML page, or a Markdown knowledge-base root. 3. A goal and audience if you want recommendations tailored to a business outcome.

Follow this first-run sequence:

1. Install the plugin. 2. Set defaultRoot in the dsh-geo Bundle configuration. It is the only directory the plugin can read or write. 3. Start or restart Harness with dsh web. 4. Ask for a readiness check. 5. Save the project boundary with geo_project_context. 6. Run geo_workflow on one page and keep the first run read-only.

Minimal Bundle configuration:

defaultRoot: "<your-knowledge-base-root>"

If you do not have a knowledge base yet, use a public URL first. For a private page, export it as Markdown or HTML and put that file under defaultRoot; no platform login is needed by this plugin.

Choose the right entry point

The complete operating method

Use this order for a professional SEO/GEO/AEO job:

0. Define the business goal, target audience, language/region and desired next action. 1. Connect the source: public URL, exported snapshot or local Markdown. 2. Establish a baseline: inspect SEO, GEO, AEO, provenance, freshness and internal links. 3. Build a keyword and intent map: assign one primary query, supporting topics, question terms and entities to page sections. 4. Create the content brief and information architecture: direct answer, outline, FAQs, sources and next action. 5. Produce or revise content while preserving factual claims and source context. 6. Verify structure, citations, links, answerability and unknown data. 7. Preview the Markdown diff, explicitly confirm, apply the guarded write, and re-audit the current file. 8. Review same-scope performance: prioritize striking-distance, low-CTR, indexing and cannibalization evidence. 9. Optionally distribute through relevant product-discovery channels: qualify candidates first, submit manually through the platform, then record the truthful outcome. 10. Return to the next diagnosis; the loop can be manual and does not require automation.

The plugin does not invent search volume, ranking difficulty or traffic. Treat qualitative as topic signals from public search and seed-only as a privacy-preserving plan based on the supplied source and seed terms.

SOP: inputs, outputs and completion criteria

geo_workflow returns sop. currentStep tells you what to do next, while steps contains the full operating path:

If a step is not complete, follow sop.steps[n].nextAction instead of jumping straight to publication.

Recommended project files

project-context.json                 # business goal, audience, market, brand and page actions
seo/keyword-opportunities.json       # imported keyword opportunities and page mapping
backlinks/campaign.json              # truthful outcomes from manual distribution work

Create these directories under defaultRoot if needed. Keyword data may come from Search Console, Ads, a keyword provider or manual research. Missing volume, difficulty or CPC stays unknown; the plugin does not estimate it.

Diagnosis -> production -> measurement -> diagnosis

geo_project_context
  -> geo_workflow / geo_audit_note
  -> geo_keyword_import -> geo_keyword_opportunities
  -> content brief and Markdown draft
  -> geo_preview_content -> geo_apply_content
  -> geo_source_check + geo_audit_note
  -> geo_effect_review (baseline/current + rows)
  -> geo_coach
  -> next geo_workflow

Pass query/page rows to geo_effect_review when available. It routes second-p

…