Skip to content

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.

docs(backlinks): use the canonical launcher form in the score-gate docs

Agrici Daniel2be70073cc4a
diff --git a/skills/seo-backlinks/SKILL.md b/skills/seo-backlinks/SKILL.md
index d9dd840..d0af1c4 100644
--- a/skills/seo-backlinks/SKILL.md
+++ b/skills/seo-backlinks/SKILL.md
@@ -203,7 +203,7 @@ This rule has been stated in this skill before and was violated anyway, so it is
now checkable. **Before writing any backlink output, run the validator:**
```bash
-claude-seo run validate_backlink_report.py --report <report>.json --json
+"${CLAUDE_PLUGIN_ROOT}/scripts/claude-seo" run validate_backlink_report.py --report <report>.json --json
```
Pass the sources you actually collected (`cc_data`, `moz_data`, `bing_data`,
diff --git a/skills/seo/references/free-backlink-sources.md b/skills/seo/references/free-backlink-sources.md
index 6a179d7..2b88277 100644
--- a/skills/seo/references/free-backlink-sources.md
+++ b/skills/seo/references/free-backlink-sources.md
@@ -41,7 +41,7 @@ Common Crawl *does* support as low-confidence findings, and note "limited to
domain-level metrics" in the report. The same applies to any finding written with
`source: not-assessed`.
-This is enforced, not advisory: `claude-seo run validate_backlink_report.py` fails
+This is enforced, not advisory: `"${CLAUDE_PLUGIN_ROOT}/scripts/claude-seo" run validate_backlink_report.py` fails
a report (`status: FAIL`) that carries a number in either case. See the
`seo-backlinks` skill's "MUST NOT: score what you did not measure" section.