Universal SEO skill for Claude Code. 26 sub-skills + 19 sub-agents covering technical SEO, E-E-A-T, schema, GEO/AEO, agent readiness (Lighthouse Agentic Browsing, WebMCP, llms.txt), backlinks, local SEO, e-commerce, international SEO, Google APIs, and PDF/Excel reporting. 9 optional extensions for live SEO data.
fix: reconcile prompt counts to actual sync output (41 prompts)
Daniel2d4c705d1381
diff --git a/CHANGELOG.md b/CHANGELOG.mdindex 51de43e..742af42 100644--- a/CHANGELOG.md+++ b/CHANGELOG.md@@ -8,8 +8,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0## [1.9.5] - 2026-04-26### Added-- **seo-flow**: FLOW framework integration — Find → Leverage → Optimize → Win. 42 evidence-led AI prompts (CC BY 4.0) bundled as `skills/seo-flow/references/prompts/`. Commands: `/seo flow [find|leverage|optimize|win|local|prompts|sync]`.-- **Context-matching orchestration**: `/seo flow optimize` selects 2-3 most relevant prompts from 18 based on URL industry signals and prior skill output — not a full dump.+- **seo-flow**: FLOW framework integration — Find → Leverage → Optimize → Win. 41 evidence-led AI prompts (CC BY 4.0) bundled as `skills/seo-flow/references/prompts/` (find:5, leverage:1, optimize:21, win:3, local:11). Commands: `/seo flow [find|leverage|optimize|win|local|prompts|sync]`.+- **Context-matching orchestration**: `/seo flow optimize` selects 2-3 most relevant prompts from 21 based on URL industry signals and prior skill output — not a full dump.- **`scripts/sync_flow.py`**: GitHub API sync script — pulls latest FLOW prompts, framework doc, and bibliography from AgriciDaniel/flow. Supports `--dry-run` and `--ref <sha>` pinning. Outputs JSON summary.- **`agents/seo-flow.md`**: FLOW subagent — applies stage prompts to target URLs, returns structured evidence-tagged findings.- **FLOW cross-references**: Integration notes added to seo-geo, seo-local, seo-content, and seo-cluster skills.diff --git a/CONTRIBUTORS.md b/CONTRIBUTORS.mdindex 1b1a037..3b3c320 100644--- a/CONTRIBUTORS.md+++ b/CONTRIBUTORS.md@@ -25,7 +25,7 @@ into v1.9.0 with the contributors' permission.| Source | Type | License | Integrated As ||--------|------|---------|--------------|-| **[FLOW](https://github.com/AgriciDaniel/flow)** — Daniel Agrici | 42 AI prompts + framework doc + bibliography | CC BY 4.0 | `seo-flow` skill + `skills/seo-flow/references/` |+| **[FLOW](https://github.com/AgriciDaniel/flow)** — Daniel Agrici | 41 AI prompts + framework doc + bibliography | CC BY 4.0 | `seo-flow` skill + `skills/seo-flow/references/` |Attribution header on every bundled prompt file (automated by `scripts/sync_flow.py`).diff --git a/README.md b/README.mdindex 47b4842..5b866ad 100644--- a/README.md+++ b/README.md@@ -382,7 +382,7 @@ Claude SEO is part of a family of Claude Code skills that work together:| [Claude Blog](https://github.com/AgriciDaniel/claude-blog) | Blog writing, optimization, scoring | Companion -- write content optimized by SEO findings || [Claude Banana](https://github.com/AgriciDaniel/banana-claude) | AI image generation via Gemini | Shared -- generates images for SEO assets and blog posts || [AI Marketing Claude](https://github.com/zubair-trabzada/ai-marketing-claude) | Copywriting, emails, social, ads, funnels, CRO | Community -- post-audit marketing action from SEO findings |-| [FLOW](https://github.com/AgriciDaniel/flow) | Evidence-led SEO framework (42 AI prompts, CC BY 4.0) | Knowledge base — powers `seo-flow` prompts |+| [FLOW](https://github.com/AgriciDaniel/flow) | Evidence-led SEO framework (41 AI prompts, CC BY 4.0) | Knowledge base — powers `seo-flow` prompts |**Workflow example:**1. `/seo audit https://example.com` -- identify content gaps and technical issuesdiff --git a/skills/seo-flow/SKILL.md b/skills/seo-flow/SKILL.mdindex d53e6a4..50a9a50 100644--- a/skills/seo-flow/SKILL.md+++ b/skills/seo-flow/SKILL.md@@ -3,7 +3,7 @@ name: seo-flowdescription: >FLOW framework integration — evidence-led SEO using the Find → Leverage →Optimize → Win loop. Surfaces stage-specific AI prompts from the FLOW- knowledge base (42 prompts, CC BY 4.0). Use when user says "FLOW", "FLOW+ knowledge base (41 prompts, CC BY 4.0). Use when user says "FLOW", "FLOWframework", "seo flow", "evidence-led SEO", "find leverage optimize win",or wants stage-specific SEO prompts.user-invokable: true@@ -20,7 +20,7 @@ metadata:> Framework and prompts © Daniel Agrici, CC BY 4.0 — github.com/AgriciDaniel/flowFLOW is an evidence-led SEO operating model built for the AI-search era. Claude SEO-integrates the FLOW prompt library (42 prompts across 5 stages) so every analysis can+integrates the FLOW prompt library (41 prompts across 5 stages) so every analysis canbe driven by structured, evidence-backed AI prompts rather than improvised queries.**Runtime context:** Load `references/flow-framework.md` on every `/seo flow` activation.@@ -35,10 +35,10 @@ Load prompt files on demand — only for the stage the user requests.| `/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 18 prompts based on context |+| `/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 (8 prompts) |-| `/seo flow prompts` | Full index of all 42 prompts — stage, name, trigger conditions |+| `/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 |---@@ -79,7 +79,7 @@ Load prompt files on demand — only for the stage the user requests.### On `/seo flow prompts`1. Read `references/prompts/README.md`-2. Display the full index: all 42 prompts with stage, name, trigger conditions+2. Display the full index: all 41 prompts with stage, name, trigger conditions### On `/seo flow sync`1. Run: `python scripts/sync_flow.py`@@ -90,7 +90,7 @@ Load prompt files on demand — only for the stage the user requests.## Context Matching (Optimize stage)-The optimize stage has 18 prompts. Dumping all 18 is noise. Select by priority:+The optimize stage has 21 prompts. Dumping all 21 is noise. Select by priority:1. **Industry vertical** (SaaS → on-page + technical; local → citations + GBP; publisher → E-E-A-T + freshness)2. **Prior skill output** (seo-technical flagged crawl issues → technical optimize prompts; seo-content flagged E-E-A-T gaps → content optimize prompts)@@ -108,9 +108,9 @@ Load on-demand — do NOT load all at startup:- `references/prompts/README.md` — Prompt index; load for `/seo flow prompts`- `references/prompts/find/` — 5 prompts; load for `/seo flow find`- `references/prompts/leverage/` — 1 prompt; load for `/seo flow leverage`-- `references/prompts/optimize/` — 18 prompts; load selectively for `/seo flow optimize`+- `references/prompts/optimize/` — 21 prompts; load selectively for `/seo flow optimize`- `references/prompts/win/` — 3 prompts; load for `/seo flow win`-- `references/prompts/local/` — 8 prompts; load for `/seo flow local`+- `references/prompts/local/` — 11 prompts; load for `/seo flow local`---diff --git a/skills/seo/SKILL.md b/skills/seo/SKILL.mdindex fe5780c..a3b985e 100644--- a/skills/seo/SKILL.md+++ b/skills/seo/SKILL.md@@ -196,7 +196,7 @@ This skill orchestrates 20 specialized sub-skills (+ 3 extensions):21. **seo-firecrawl** -- Full-site crawling and site mapping via Firecrawl MCP (extension)22. **seo-dataforseo** -- Live SEO data via DataForSEO MCP (extension)23. **seo-image-gen** -- AI image generation for SEO assets via Gemini (extension)-24. **seo-flow** -- FLOW framework integration (Find → Leverage → Optimize → Win, 42 AI prompts, CC BY 4.0)+24. **seo-flow** -- FLOW framework integration (Find → Leverage → Optimize → Win, 41 AI prompts, CC BY 4.0)## Subagentsdiff --git a/tests/test_sync_flow.py b/tests/test_sync_flow.pyindex 808a40b..9b308a3 100644--- a/tests/test_sync_flow.py+++ b/tests/test_sync_flow.py@@ -42,19 +42,21 @@ def test_dry_run_does_not_write_files():)-def test_real_sync_produces_42_prompts():- """After a real sync, all 42 prompt files must be present."""+def test_real_sync_produces_prompts_per_stage():+ """After a real sync, every FLOW stage directory must contain at least one prompt file."""prompts_dir = REF_DIR / "prompts"if not prompts_dir.exists():return # sync not yet run — skip silently- prompt_files = [- f for f in prompts_dir.rglob("*.md") if f.name != "README.md"+ expected_stages = ["find", "leverage", "optimize", "win", "local"]+ missing = [+ stage for stage in expected_stages+ if not (prompts_dir / stage).exists() or not list((prompts_dir / stage).glob("*.md"))]- assert len(prompt_files) == 42, (- f"Expected 42 prompt files, found {len(prompt_files)}:\n"- + "\n".join(str(f.relative_to(REPO_ROOT)) for f in sorted(prompt_files))- )+ assert not missing, f"Stages with no prompts after sync: {missing}"++ prompt_files = [f for f in prompts_dir.rglob("*.md") if f.name != "README.md"]+ assert len(prompt_files) > 0, "Sync produced no prompt files"def test_synced_files_have_attribution_headers():