feat(seo-skills): multi-backend Data Source Selection (#7)

Replaces single-vendor (Ahrefs-only) tool defaults with a per-task
backend menu across all 14 SEO skills. Each skill now lists every
capable MCP in allowed-tools and documents how to pick between
Semrush, Ahrefs, OurSEO Agent (CLI + MCP), DataForSEO, and GSC
in its SKILL.md Data Source Selection section.

Tool stubs (~40 new files) populated per skill with capability
deltas, call patterns, and explicit "not for this skill when"
callouts so the menu is self-correcting.

Skills affected: 19-keyword-strategy, 20-serp-analysis,
21-position-tracking, 22-link-building, 23-content-strategy,
24-ecommerce, 25-kpi-framework, 26-international, 27-ai-visibility,
28-knowledge-graph, 31-competitor-intel, 32-crawl-budget,
33-migration-planner, 34-reporting-dashboard.

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

custom-skills/33-seo-migration-planner/desktop/SKILL.md

@@ -24,30 +24,84 @@ Comprehensive site migration planning and post-migration monitoring for SEO: cra
 10. **Recovery Estimation** - Estimate traffic recovery timeline based on migration type
 11. **Alert Generation** - Flag traffic drops >20%, broken redirects, indexation loss
 
-## MCP Tool Usage
+## Data Source Selection
 
-### SEO Data
-```
-our-seo-agent CLI: Primary SEO baseline data source (future); use --input for pre-fetched JSON
-WebSearch / WebFetch: Supplementary migration data
+Site migration spans **URL inventory** (crawl), **traffic/keyword/backlink baseline** (third-party + first-party), **redirect verification** (live HTTP), and **post-launch monitoring** (delta over time). Pick per data class — migration baselines often combine 3-4 backends.
+
+| Backend | Best for | Notes |
+|---|---|---|
+| **OurSEO** (CLI + MCP) | **Default** for URL inventory, on-page crawl, index status, technical audit, schema baseline | CLI: `our collect crawl`, `our collect distributed`, `our audit tech`, `our research google index`. MCP: `mcp__ourseo__crawl_website`, `mcp__ourseo__check_index`. Distributed crawler for sites >5K URLs. |
+| **Firecrawl MCP** (`mcp__firecrawl__*`) | Large-scale URL inventory when OurSEO crawler is unavailable; per-URL redirect verification | `firecrawl_crawl` for full site map; `firecrawl_scrape` for redirect health on a specific URL. Useful when target is JS-heavy. |
+| **Ahrefs MCP** (`mcp__ahrefs__*`) | Per-URL **traffic value + backlink count** baseline (risk scoring), top pages by traffic | `site-explorer-top-pages` (traffic per URL), `site-explorer-pages-by-backlinks`, `site-explorer-metrics`, `site-explorer-metrics-history`, `site-explorer-pages-history`. |
+| **Semrush MCP** (`mcp__semrush__*`) | Per-URL organic traffic + keyword baseline | `organic_research`, `url_research`, `overview_research`. |
+| **GSC** (via `our research search-console`) | **First-party impression baseline** — what Google rendered for each URL pre-migration | Required for ground-truth post-migration comparison. Use `pages` / `combined` reports. |
+| **GA4** (via `our research ga4 *`) | First-party traffic baseline (sessions, conversions per URL) | Best for actual user-traffic baseline, complements GSC impressions. |
+| **Perplexity MCP** (`mcp__perplexity__*`) | Research migration best practices, common pitfalls per migration type | Not a data source — guidance enrichment. |
+
+### How to pick
+
+1. **User named a backend explicitly** → use it.
+2. **User preference memory** — read `feedback_seo_tool_preferences.md`; honor the task-type default.
+3. **URL inventory** → **OurSEO** crawler (CLI primary). Use Firecrawl only when OurSEO crawler can't handle the target (e.g., JS-heavy SPA).
+4. **Per-URL traffic value for risk scoring** → Ahrefs `site-explorer-top-pages` is the strongest signal. Semrush `url_research` is the alternate.
+5. **First-party baseline (REQUIRED for accurate post-migration diff)** → GSC + GA4 via `our` CLI. Always capture before migration date.
+6. **Redirect verification** (post-launch) → Firecrawl `firecrawl_scrape` per URL OR `WebFetch` with redirect following.
+7. **Default baseline stack**: OurSEO crawl + Ahrefs top-pages + GSC pages + GA4 traffic. Document every source.
+8. **Still ambiguous + non-trivial** → ask once via `AskUserQuestion`.
+
+### Backend call patterns
+
+**OurSEO CLI (default — URL inventory + audit):**
+```bash
+our collect crawl https://<site> --max-pages 5000
+our collect distributed https://<site> --workers 8 --max-pages 50000
+our audit tech https://<site>
+our research google index --domain <site>
 ```
 
-### Firecrawl for URL Inventory & Redirect Verification
+**OurSEO MCP (Claude Desktop):**
 ```
-mcp__firecrawl__firecrawl_crawl: Crawl entire site for URL inventory
-mcp__firecrawl__firecrawl_scrape: Verify individual redirect health
+mcp__ourseo__crawl_website(url="<site>", max_pages=5000)
+mcp__ourseo__check_index(domain="<site>")
 ```
 
-### Notion for Report Storage
+**Firecrawl (URL inventory + redirect verification):**
 ```
-mcp__notion__notion-create-pages: Save reports to SEO Audit Log
+mcp__firecrawl__firecrawl_crawl(url="<site>", limit=5000)
+mcp__firecrawl__firecrawl_scrape(url="<specific URL>", formats=["markdown"])
 ```
 
-### Perplexity for Migration Best Practices
+**Ahrefs MCP (per-URL traffic + backlink baseline):**
 ```
-mcp__perplexity__search: Research migration best practices and common pitfalls
+mcp__ahrefs__site-explorer-top-pages(target="<site>", country="us", limit=500)
+mcp__ahrefs__site-explorer-pages-by-backlinks(target="<site>", limit=500)
+mcp__ahrefs__site-explorer-metrics(target="<site>")
+mcp__ahrefs__site-explorer-metrics-history(target="<site>", history="weekly")
+mcp__ahrefs__site-explorer-pages-history(target="<site>")
 ```
 
+**Semrush MCP (per-URL organic baseline):**
+```
+mcp__semrush__organic_research(query="<site>", database="us")
+mcp__semrush__url_research(query="<specific URL>", database="us")
+mcp__semrush__overview_research(query="<site>", database="us")
+```
+
+**First-party baseline (GSC + GA4):**
+```bash
+our research search-console pages --site sc-domain:<site> --days 90
+our research search-console combined --site sc-domain:<site> --days 90
+our research ga4 traffic --property-id <id>
+our research ga4 landing-pages --property-id <id>
+```
+
+**Migration best practices (Perplexity):**
+```
+mcp__perplexity__search(query="SEO migration <type> best practices")
+```
+
+Always record the chosen data source(s) per metric in the **planning report's Baseline** section and re-use the same sources in **post-migration monitoring** so the diff is meaningful.
+
 ## Workflow
 
 ### Pre-Migration Planning

custom-skills/33-seo-migration-planner/desktop/skill.yaml

@@ -1,10 +1,18 @@
 name: seo-migration-planner
 description: |
   SEO site migration planning and monitoring. Triggers: site migration, domain move, redirect mapping, platform migration, URL restructuring, 사이트 이전.
+
+# Allowed tools list every backend the skill can pull migration-baseline / monitoring data from.
+# Per-task selection happens in SKILL.md > Data Source Selection — NOT here.
 allowed-tools:
-  - mcp__ahrefs__*
-  - mcp__firecrawl__*
+  - mcp__ourseo__*                # default — crawl_website, audit_page, check_index
+  - mcp__firecrawl__*             # large-scale URL inventory + redirect verification
+  - mcp__ahrefs__*                # site-explorer-* for traffic-value + backlink baseline
+  - mcp__claude_ai_Ahrefs__*      # Ahrefs (Claude.ai namespace)
+  - mcp__semrush__*               # organic_research, overview_research baseline
+  - mcp__dfs-mcp__*               # DataForSEO MCP fallback
+  - Bash                          # `our` CLI full surface
   - mcp__notion__*
-  - mcp__perplexity__*
+  - mcp__perplexity__*            # research migration best practices
   - WebSearch
   - WebFetch

custom-skills/33-seo-migration-planner/desktop/tools/gsc.md

@@ -0,0 +1,54 @@
+# Google Search Console
+
+**Required** for migration baseline + post-launch monitoring. GSC is the only source for first-party impressions / clicks per URL pre-migration — modelled estimates from Semrush/Ahrefs cannot substitute.
+
+## CLI commands
+
+```bash
+# Pre-migration baseline (PULL THIS BEFORE THE MIGRATION DATE)
+our research search-console pages --site sc-domain:<old-domain> --days 90
+our research search-console combined --site sc-domain:<old-domain> --days 90
+our research search-console queries --site sc-domain:<old-domain> --days 90
+
+# Post-migration (after new domain is verified in GSC)
+our research search-console pages --site sc-domain:<new-domain> --days 28
+our research search-console combined --site sc-domain:<new-domain> --days 28
+```
+
+`sc-domain:` prefix for Domain-verified properties; URL-prefix uses plain URL.
+
+## Baseline checklist
+
+Pre-migration, capture at minimum:
+
+| File | Source | Window |
+|---|---|---|
+| `gsc-pages-90d.json` | `our research search-console pages` | 90 days pre-migration |
+| `gsc-combined-90d.json` | `our research search-console combined` | 90 days pre-migration |
+| `gsc-queries-90d.json` | `our research search-console queries` | 90 days pre-migration |
+
+Store these alongside the OurSEO crawl baseline in the migration workspace.
+
+## Post-launch monitoring
+
+1. Wait for the new domain to verify in GSC (~24h after DNS propagation + sitemap submission).
+2. Pull `pages` and `combined` on the new domain at +7d, +14d, +28d, +60d, +90d.
+3. Diff against the baseline: which URLs lost impressions? Which queries dropped?
+4. Cross-reference with OurSEO redirect verification — broken redirects are the most common cause of impression loss.
+
+## Ahrefs GSC alternates
+
+If both old and new domains are connected as Ahrefs projects:
+
+```
+mcp__ahrefs__gsc-pages(project_id="<id>")
+mcp__ahrefs__gsc-pages-history(project_id="<id>")
+mcp__ahrefs__gsc-performance-history(project_id="<id>")
+```
+
+## Not for this skill when
+
+- **Pre-migration baseline before GSC verification** of the property — not possible. Get the domain verified well in advance.
+- **Competitor migration analysis** — GSC is single-site.
+
+Gotcha: `our-claude-skills/custom-skills/15-seo-search-console/code/gotcha/gsc-cli-integration.md`.

custom-skills/33-seo-migration-planner/desktop/tools/ourseo.md

@@ -0,0 +1,54 @@
+# OurSEO Agent (CLI + MCP)
+
+**Default** for URL inventory, on-page crawl, technical audit, and index-status baseline. Distributed crawler scales to large catalogs.
+
+## CLI commands (Claude Code)
+
+```bash
+# URL inventory crawl (pre-migration)
+our collect crawl https://<old-site> --max-pages 5000
+our collect distributed https://<old-site> --workers 8 --max-pages 50000
+
+# Technical audit (catches redirect chains, canonical issues that affect migration)
+our audit tech https://<old-site>
+
+# Index baseline
+our research google index --domain <old-site>
+
+# Schema baseline (preserve schema across migration)
+our analyze mysql-batch --session <id> --export missing-schema --format excel
+
+# Post-migration: re-run on new domain and diff
+our collect crawl https://<new-site> --max-pages 5000
+our research google index --domain <new-site>
+our audit tech https://<new-site>
+```
+
+## MCP tools (Claude Desktop)
+
+```
+mcp__ourseo__crawl_website(url="<site>", max_pages=5000)
+mcp__ourseo__check_index(domain="<site>")
+mcp__ourseo__audit_page(url="<url>", audit_type="tech")
+```
+
+## Strengths for this skill
+
+- **Distributed crawl** with URL-hash partitioning — handles catalogs >50K URLs.
+- **Resume support** (`--resume`) — critical for multi-day baseline captures.
+- **MySQL workspace** stores baseline crawl; post-migration diff is a SQL query against the same DB.
+- **Index status spot-check** via `check_index` — finds URLs Google still has indexed from the old domain.
+
+## Pair with Firecrawl
+
+Firecrawl (`mcp__firecrawl__*`) is already in this skill's `allowed-tools`:
+
+- Use **OurSEO** as the default crawler for most sites.
+- Switch to **Firecrawl** when the target is JS-heavy (React/Vue/Angular SPA) and OurSEO's HTTP-level crawler under-reports URLs.
+- Use Firecrawl `firecrawl_scrape` for per-URL **redirect verification** post-launch (cheaper than re-crawling the whole site).
+
+## Not for this skill when
+
+- **Per-URL traffic value for risk scoring** — Ahrefs `site-explorer-top-pages` / Semrush `url_research`.
+- **First-party impression baseline** — GSC `pages` (REQUIRED for accurate post-migration diff).
+- **GA4 traffic baseline** — `our research ga4 *` (covered in OurSEO CLI but distinct from crawl path).

custom-skills/33-seo-migration-planner/desktop/tools/semrush.md

@@ -0,0 +1,39 @@
+# Semrush MCP
+
+For migrations, Semrush contributes **per-URL organic baseline**, **traffic value baseline**, and **cross-database comparison** when the migration involves a market change.
+
+Call pattern: discovery → `get_report_schema` → `execute_report`.
+
+## Key reports
+
+- `organic_research` — full organic keyword list for the domain (baseline)
+- `url_research` — per-URL organic data (KPI for redirect risk scoring)
+- `overview_research` — site-level traffic + visibility baseline
+- `trends_research` — period-over-period traffic deltas (post-launch monitoring)
+
+## Example
+
+```
+# Pre-migration baseline
+mcp__semrush__organic_research(query="<old-domain>", database="us")
+mcp__semrush__url_research(query="<specific old URL>", database="us")
+mcp__semrush__overview_research(query="<old-domain>", database="us")
+
+# Post-migration monitoring
+mcp__semrush__trends_research(query="<new-domain>", database="us")
+```
+
+Korean market: `database="kr"`.
+
+## Strengths for this skill
+
+- **`url_research`** gives per-URL organic data — useful input for redirect risk scoring alongside Ahrefs traffic value.
+- **`trends_research`** simplifies post-migration period-over-period delta.
+- Cross-database comparison helps validate visibility recovery across markets.
+
+## Not for this skill when
+
+- **URL inventory** — OurSEO `crawl_website` / Firecrawl `firecrawl_crawl`.
+- **Backlink baseline** for risk scoring — Ahrefs `site-explorer-pages-by-backlinks`.
+- **First-party impression baseline** — GSC `pages` / `combined` reports.
+- **Redirect health checking post-launch** — Firecrawl `firecrawl_scrape` or WebFetch.