Skills Explorer Add Skills

seo-drift

An agent skill by AgriciDaniel, from AgriciDaniel/claude-seo. Tags: deployment, monitoring, seo, validation, version-control.

What it does

SEO drift monitoring: capture baselines of SEO-critical elements, detect changes, and track regressions over time. Git for SEO: baseline, diff, and track changes to your on-page SEO. Use when user says "SEO drift", "baseline", "track changes", "did anything break", "SEO regression", "compare SEO", "before and after", "monitor SEO changes", or "deployment check".

Install

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

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

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-drift ~/.claude/skills/seo-drift

Safety box score

Grade C, moderate risk: 28 of 100 risk points, rated 2026-10-20. 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 local SEO change monitor that fetches web pages, compares them to stored baselines, and writes results to a SQLite database in the user’s home cache. The main risks are ordinary outbound network access, local data storage under `~/.cache`, and the fact that the core fetch/parse/diff behavior is delegated to scripts that are not present in the reviewed files.

Category levels, from 0 (none) to 3 (high)
CategoryLevelWhy
Code & shell execution2 (moderate)The skill explicitly runs code via `"${CLAUDE_PLUGIN_ROOT}/scripts/claude-seo" run drift_baseline.py <url>` and related commands, so installing it grants the agent the ability to execute shipped tooling.
Network access2 (moderate)Its normal workflow fetches arbitrary user-supplied URLs through `fetch_page.py` and may also call `pagespeed_check.py`, so it performs outbound network requests.
Filesystem reach2 (moderate)It stores baselines and comparisons in `~/.cache/claude-seo/drift/baselines.db`, which writes to a dot-directory under the user’s home folder.
Secrets & credentials0 (none)The reviewed files do not request passwords, tokens, keyfiles, browser sessions, or `.env` contents.
Privilege & persistence0 (none)There is no mention of sudo, global installs, services, scheduled tasks, or shell/OS setting changes.
Instruction hijack surface0 (none)The text does not instruct the agent to ignore safeguards, hide actions, follow remote instructions, or adopt deceptive behavior.
Irreversible actions0 (none)The skill compares and reports SEO drift only; it does not publish, pay, message, deploy, or delete anything.
Transparency2 (moderate)Core behavior is delegated to unprovided scripts such as `fetch_page.py`, `parse_html.py`, `drift_baseline.py`, and `drift_compare.py`, so the actual implementation cannot be audited from the supplied files.

Before installing

Rated 2026-10-20 by an automated review of 2 files from the skill's repository.

Source

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