seo-flow
agricidaniel/claude-seo
Evidence-led SEO using the FLOW framework — Find, Leverage, Optimize, Win with 41 structured AI prompts.
What is seo-flow?
FLOW is an evidence-backed SEO operating model organized into five stages: Find (keyword research & gap analysis), Leverage (backlink strategy), Optimize (on-page & technical), Win (conversion & BOFU), and Local (GBP & citations). Use this skill when you need stage-specific SEO analysis driven by structured prompts rather than ad-hoc queries.
- Access 41 curated SEO prompts organized across 5 FLOW stages
- Run stage-specific analysis: Find (5 prompts), Leverage (1), Optimize (21 context-aware), Win (3), Local (11)
- Automatically select 2–3 most relevant prompts for Optimize stage based on industry vertical and prior analysis
- Cross-reference related skills (backlinks, content, technical, local) for deeper investigation
- Sync latest prompt library from the FLOW GitHub repository
- Display full prompt index with trigger conditions and stage mapping
How to install seo-flow
npx skills add https://github.com/agricidaniel/claude-seo --skill seo-flow- Node.js and npm installed
- GitHub CLI (gh) for syncing latest prompts (optional but recommended)
- Initial sync: run `/seo flow sync` to pull prompt library from github.com/AgriciDaniel/flow
How to use seo-flow
- 1.Run `/seo flow` to see the FLOW stage overview and choose a stage
- 2.For keyword research: run `/seo flow find [url|topic]` to apply 5 Find-stage prompts
- 3.For backlink strategy: run `/seo flow leverage [url]` to apply Leverage-stage analysis
- 4.For on-page/technical: run `/seo flow optimize [url]` — the skill auto-selects 2–3 most relevant prompts from 21 based on context
- 5.For conversion analysis: run `/seo flow win [url]` to apply Win-stage prompts
- 6.For local SEO: run `/seo flow local [url]` to apply 11 Local-stage prompts
- 7.View all 41 prompts: run `/seo flow prompts` to see the full index with trigger conditions
- 8.Keep prompts current: run `/seo flow sync` to pull latest updates from the FLOW repository
Use cases
- Conduct keyword research and SERP intent mapping for a new topic using Find-stage prompts
- Develop backlink and off-site authority strategy for a URL using Leverage-stage analysis
- Audit on-page and technical SEO with context-aware prompt selection from 21 Optimize prompts
- Analyze conversion readiness and bottom-of-funnel optimization using Win-stage prompts
- Optimize Google Business Profile, local citations, and local meta tags using Local-stage prompts
- SEO strategists and consultants building evidence-led campaigns
- Content teams needing structured keyword and gap analysis
- Technical SEO auditors integrating on-page and crawl insights
- Local SEO specialists optimizing GBP and citation profiles
- AI-assisted SEO workflows in Claude Code or Cursor
seo-flow FAQ
The skill reads prior analysis context (URL, industry vertical, prior skill output in conversation) and selects exactly 2–3 most relevant prompts from 21 based on: (1) industry vertical (SaaS → on-page + technical; local → citations + GBP; publisher → E-E-A-T + freshness), (2) prior skill output (technical issues → technical prompts; content gaps → content prompts), (3) URL signals (product pages → conversion; blog → freshness + authority).
If reference files are not synced, the skill will prompt: 'FLOW reference files not synced. Run: `/seo flow sync`'. Run the sync command to pull the latest prompts from github.com/AgriciDaniel/flow.
Yes. Run `/seo flow prompts` to display the full index of all 41 prompts with their stage, name, and trigger conditions.
Run `/seo flow sync` to pull the latest prompt files from the FLOW GitHub repository. The skill will display a JSON summary of files added, updated, and unchanged.
FLOW is an evidence-led SEO operating model with five stages: Find (keyword research, gap analysis, SERP intent), Leverage (backlink strategy, off-site authority), Optimize (on-page, technical, content), Win (conversion, BOFU, dual-surface scoring), and Local (GBP, citations, local audits). Each stage has curated AI prompts to drive structured, evidence-backed analysis.
Full instructions (SKILL.md)
Source of truth, from agricidaniel/claude-seo.
name: seo-flow description: > FLOW framework integration — evidence-led SEO using the Find → Leverage → Optimize → Win loop. Surfaces stage-specific AI prompts from the FLOW knowledge base (41 prompts, CC BY 4.0). Use when user says "FLOW", "FLOW framework", "seo flow", "evidence-led SEO", "find leverage optimize win", or wants stage-specific SEO prompts. user-invocable: true argument-hint: "[stage] [url|topic]" license: MIT metadata: author: AgriciDaniel version: "2.2.0" category: seo
FLOW Framework — Find · Leverage · Optimize · Win
Framework and prompts © Daniel Agrici, CC BY 4.0 — github.com/AgriciDaniel/flow
FLOW is an evidence-led SEO operating model built for the AI-search era. Claude SEO integrates the FLOW prompt library (41 prompts across 5 stages) so every analysis can be driven by structured, evidence-backed AI prompts rather than improvised queries.
Runtime context: Load references/flow-framework.md on every /seo flow activation.
Load prompt files on demand — only for the stage the user requests.
Commands
| Command | What it does |
|---|---|
/seo flow | Show FLOW overview + stage menu |
/seo flow find [url|topic] | Find-stage: keyword research, gap analysis, SERP intent mapping (5 prompts) |
/seo flow leverage [url] | Leverage-stage: backlink strategy, off-site authority (1 prompt) |
/seo flow optimize [url] | Optimize-stage: select 2-3 most relevant of 21 prompts based on context |
/seo flow win [url] | Win-stage: BOFU, conversion rate, dual-surface scorecard (3 prompts) |
/seo flow local [url] | Local-stage: GBP optimization, meta, title tags, local audits (11 prompts) |
/seo flow prompts | Full index of all 41 prompts — stage, name, trigger conditions |
/seo flow sync | Pull latest prompt files from github.com/AgriciDaniel/flow |
Orchestration Logic
On /seo flow (no sub-command)
- Read
references/flow-framework.md - Show the FLOW stage overview with a one-line description of each stage
- Ask: which stage matches the user's current situation?
On /seo flow find [url|topic]
- Read all files in
references/prompts/find/ - Apply each prompt to the URL or topic
- Cross-reference: "For deeper SERP clustering, see
/seo cluster <seed-keyword>"
On /seo flow leverage [url]
- Read the file in
references/prompts/leverage/ - Apply to the URL's current backlink context
- Cross-reference: "For raw backlink data, see
/seo backlinks <url>"
On /seo flow optimize [url]
- Read all file names in
references/prompts/optimize/ - Read prior analysis context (URL, industry vertical, any prior skill output in conversation)
- Select 2-3 most relevant prompts; load only those files
- Apply selected prompts; note the others are accessible via
/seo flow prompts - Cross-reference: "For full content quality analysis, see
/seo content <url>and/seo geo <url>"
On /seo flow win [url]
- Read all files in
references/prompts/win/ - Apply each prompt to the URL's conversion and BOFU context
- Cross-reference: "For SXO persona scoring, see
/seo sxo <url>"
On /seo flow local [url]
- Read all files in
references/prompts/local/ - Apply to the URL's local SEO context
- Cross-reference: "For full local SEO analysis, see
/seo local <url>and/seo maps [command]"
On /seo flow prompts
- Read
references/prompts/README.md - Display the full index: all 41 prompts with stage, name, trigger conditions
On /seo flow sync
- Run:
python3 scripts/sync_flow.py - Display the JSON summary (files added, updated, unchanged)
- Show attribution notice after sync completes
Context Matching (Optimize stage)
The optimize stage has 21 prompts. Dumping all 21 is noise. Select by priority:
- Industry vertical (SaaS → on-page + technical; local → citations + GBP; publisher → E-E-A-T + freshness)
- Prior skill output (seo-technical flagged crawl issues → technical optimize prompts; seo-content flagged E-E-A-T gaps → content optimize prompts)
- URL signals (product pages → conversion; blog → freshness + authority)
Always surface exactly 2-3 prompts. State which prompts you chose and why.
Reference Files
Load on-demand — do NOT load all at startup:
references/flow-framework.md— FLOW operating model (load on every/seo flowactivation)references/bibliography.md— Evidence sources; load when citing studies or statisticsreferences/prompts/README.md— Prompt index; load for/seo flow promptsreferences/prompts/find/— 5 prompts; load for/seo flow findreferences/prompts/leverage/— 1 prompt; load for/seo flow leveragereferences/prompts/optimize/— 21 prompts; load selectively for/seo flow optimizereferences/prompts/win/— 3 prompts; load for/seo flow winreferences/prompts/local/— 11 prompts; load for/seo flow local
Attribution
Every /seo flow activation (any sub-command) outputs before analysis:
Framework and prompts © Daniel Agrici, CC BY 4.0 — github.com/AgriciDaniel/flow
Do not omit or modify the attribution.
Error Handling
| Scenario | Action |
|---|---|
references/flow-framework.md missing | "FLOW reference files not synced. Run: /seo flow sync" |
| Prompt file missing | "Run /seo flow sync to pull the latest prompts from the FLOW repo." |
sync_flow.py network error | Display the script's stderr. Check rate limits: gh api rate_limit. |
sync_flow.py auth error | Run gh auth login then retry. |
Related skills
More from agricidaniel/claude-seo and the wider catalog.

seo-geo
Optimize content for AI search engines (Google AI Overviews, ChatGPT, Perplexity) with citability scoring and platform-specific analysis.

seo-google
Access Google's real SEO data: Search Console, PageSpeed, CrUX field metrics, GA4 organic traffic, and Indexing API.

seo-hreflang
Audit, validate, and generate hreflang tags for multi-language and multi-region SEO.

seo-image-gen
Generate SEO-optimized images (OG, hero, product, infographics) powered by Gemini via banana MCP.

seo-images
Analyze and optimize images for SEO: alt text, file size, format, lazy loading, SERP rankings, and metadata.

seo-local
Analyze local SEO for Google Business Profile optimization, NAP consistency, citations, reviews, and location-specific ranking factors.