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.

fix(agents): anchor the last repo-relative path and widen its guard (#252)

Agrici Daniel4f7e336ea7f3
diff --git a/agents/seo-flow.md b/agents/seo-flow.md
index f142ad3..a345c85 100644
--- a/agents/seo-flow.md
+++ b/agents/seo-flow.md
@@ -11,7 +11,7 @@ You are a FLOW framework SEO analyst. You apply evidence-led FLOW prompts to a t
When given a URL and a FLOW stage (find, leverage, optimize, win, or local):
1. Fetch the target URL with WebFetch to understand the page content and industry signals
-2. Read the relevant prompt files from `skills/seo-flow/references/prompts/{stage}/`
+2. Read the relevant prompt files from `${CLAUDE_PLUGIN_ROOT}/skills/seo-flow/references/prompts/{stage}/`
3. For the optimize stage: read all file names in `prompts/optimize/` first, then select 2-3 most relevant based on:
- Industry vertical signals from the fetched page
- Content gaps visible on the page
diff --git a/tests/test_manual_install_layout.py b/tests/test_manual_install_layout.py
index 5fea276..caba23a 100644
--- a/tests/test_manual_install_layout.py
+++ b/tests/test_manual_install_layout.py
@@ -42,7 +42,7 @@ def test_cross_skill_paths_resolve_outside_the_repo_checkout():
absolute skills directory."""
import re
- bare = re.compile(r"`(?:skills|data)/[A-Za-z0-9_./-]+\.(?:md|json|html|txt)`")
+ bare = re.compile(r"(?<![}/\w])`?(?:skills|data)/[A-Za-z0-9_./{}-]+(?:\.(?:md|json|html|txt)|/)`")
offenders = []
for path in [*ROOT.glob("agents/*.md"), *ROOT.glob("skills/**/*.md"),
*ROOT.glob("extensions/*/agents/*.md"), *ROOT.glob("extensions/*/skills/**/*.md")]: