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/28-seo-knowledge-graph/desktop/tools/ourseo.md

@@ -0,0 +1,53 @@
+# OurSEO Agent (CLI + MCP)
+
+**Default** for Knowledge Graph + entity SEO end-to-end. Only backend with an integrated KG lookup → entity audit → schema build → schema fix workflow.
+
+## CLI commands (Claude Code)
+
+```bash
+# KG lookup (Google KG Search API)
+our research kg lookup "<entity>" --language ko
+our research kg resolve "<entity>" --domain <site> --language ko
+
+# Entity audit (sameAs, entity schemas on the site)
+our audit entity https://<site> --entity "<entity>" --language ko
+our audit sameas https://<site> --brand "<brand>"
+
+# Build entity schema as JSON-LD @graph
+our build kg-schema --type Organization --name "<entity>" --url https://<site> --auto-sameas
+
+# Fix entity schema in CMS (Ghost / WordPress / Strapi)
+our fix entity-schema --site https://<site> --type Organization \
+  --entity-name "<entity>" --auto-sameas --cms ghost --deploy
+
+# Archive audit to Notion
+our output notion kg-audit --input entity-report.json
+```
+
+## MCP tools (Claude Desktop)
+
+```
+mcp__ourseo__search_knowledge_graph(query="<entity>", language="ko")
+```
+
+## Strengths for this skill
+
+- **Only end-to-end path**: KG lookup → entity audit → schema build → CMS deploy.
+- **sameAs validation** — checks that JSON-LD sameAs links resolve (not 404 / 403).
+- **Korean coverage** — Korean entity workflows (Naver encyclopedia, 지식iN) baked in via the CLI.
+- **`@graph` JSON-LD output** with auto-sameAs — produces deploy-ready schema.
+
+## Not for this skill when
+
+- **Knowledge Panel detection on Google SERP** — WebSearch (no MCP exposes Knowledge Panel structure).
+- **Wikipedia / Wikidata presence** — WebSearch / WebFetch.
+- **First-party brand-query data** (impressions, CTR for brand searches) — GSC or Ahrefs `gsc-keywords`.
+
+## Config
+
+| Env var | Purpose |
+|---|---|
+| `GOOGLE_KG_API_KEY` | Knowledge Graph Search API key (op://Development/...) |
+| `OURSEO_GHOST_API_KEY` / `OURSEO_WP_*` / `OURSEO_STRAPI_API_TOKEN` | CMS adapter auth for `--deploy` |
+
+Cross-reference: [[reference_1password_api_credentials]] in memory.

custom-skills/28-seo-knowledge-graph/desktop/tools/semrush.md

@@ -0,0 +1,29 @@
+# Semrush MCP
+
+Semrush has **no dedicated Knowledge Graph / entity endpoints.** Use only as a supplement for **brand SERP overview** and organic positions on entity-related queries.
+
+Call pattern: discovery → `get_report_schema` → `execute_report`.
+
+## What Semrush can do here
+
+```
+# Brand SERP overview — what shows up for the brand name
+mcp__semrush__overview_research(query="<brand>", database="us")
+
+# Organic positions for entity-related queries (FAQ-style queries the entity should answer)
+mcp__semrush__organic_research(query="<brand>", database="us")
+```
+
+## Not for this skill when
+
+- **Knowledge Graph lookup / entity resolution** — OurSEO `search_knowledge_graph` / `our research kg lookup`.
+- **Wikipedia / Wikidata / Naver encyclopedia presence** — WebSearch / WebFetch.
+- **Entity schema audit + fix** (Organization, Person, LocalBusiness, sameAs) — OurSEO `our audit entity` / `our fix entity-schema`.
+- **PAA / FAQ rich result detection** — WebSearch on the brand SERP.
+
+## When Semrush is useful here
+
+- Branded vs non-branded query split for the entity (post-process `organic_research` output).
+- Competitor entity comparison ("does competitor X also have an organic presence for entity Y?").
+
+Always pair with OurSEO + WebSearch for the actual entity work; Semrush is auxiliary here.