Skills Explorer Add Skills

seo-sxo

An agent skill by AgriciDaniel, from AgriciDaniel/claude-seo. Tags: analysis, search, seo, strategy, ui-ux.

What it does

Search Experience Optimization: reads Google SERPs backwards to detect page-type mismatches, derives user stories from search intent signals, and scores pages from multiple persona perspectives. Identifies why well-optimized pages fail to rank by analyzing what Google rewards for each keyword. Use when user says "SXO", "search experience", "page type mismatch", "SERP analysis", "user story", "persona scoring", "why isn't my page ranking", "intent mismatch", or "wireframe".

Install

With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:

npx skills add AgriciDaniel/claude-seo --skill seo-sxo

Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):

git clone --depth 1 https://github.com/AgriciDaniel/claude-seo
cp -r claude-seo/skills/seo-sxo ~/.claude/skills/seo-sxo

Safety box score

Grade B, low risk: 25 of 100 risk points, rated 2026-10-19. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.

This skill is a read-only SEO/SXO analysis helper that fetches a target URL, inspects page structure, queries search results, and optionally uses paid DataForSEO tools. The main risks are external network calls and the fact that normal operation depends on running bundled helper scripts; it does not appear to edit system files or require elevated privileges.

Category levels, from 0 (none) to 3 (high)
CategoryLevelWhy
Code & shell execution2 (moderate)Normal use invokes shipped helpers via `"${CLAUDE_PLUGIN_ROOT}/scripts/claude-seo" run render_page.py <URL> --mode auto` and `parse_html.py <URL>`, so the skill depends on executing code rather than only reading text.
Network access2 (moderate)It sends the target URL and keyword to WebSearch and may call DataForSEO, and it also fetches SERP data such as top results, PAA, ads, and related searches.
Filesystem reach1 (low)The skill reads bundled reference docs like `references/page-type-taxonomy.md` and `references/user-story-framework.md`, but it does not describe editing files outside the working area.
Secrets & credentials0 (none)There is no instruction to read or request passwords, tokens, `.env` files, keychains, or browser sessions.
Privilege & persistence0 (none)No `sudo`, global installs, services, scheduled tasks, or shell/OS setting changes are described.
Instruction hijack surface0 (none)The files do not tell the agent to ignore rules, hide actions, follow remote prompts, or otherwise override its instructions.
Irreversible actions2 (moderate)The skill can trigger paid external analysis through DataForSEO, and it explicitly says to `run cost estimate and confirm with user` before API calls.
Transparency0 (none)All shipped files are readable Markdown; there are no binaries, base64 blobs, or unreviewable installers in the bundle.

Before installing

Rated 2026-10-19 by an automated review of 5 files from the skill's repository.

Source

Repository
AgriciDaniel/claude-seo (all skills from this repository)
Path
skills/seo-sxo/SKILL.md
Branch
main
Collection
claude-seo
Updated
2026-09-21