Agentic SEO Skill
Deterministic LLM-first SEO audits with evidence scripts and confidence-labeled fixes, for Antigravity, Codex and Claude.
- What
- Deterministic LLM-first SEO audits with evidence scripts and confidence-labeled fixes, for Antigravity, Codex and Claude.
- Cost
- Free
- Needs
- an AI agent with file tools (Read, Write, Bash), such as Claude Code or Codex; Python 3 for the 89 bundled evidence scripts. Optional: a GitHub token or the gh CLI only for the GitHub-repo-SEO features; Playwright only for visual screenshots. No paid service is required for the core checks.
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor: a deterministic, LLM-first SEO audit framework for coding agents. Sixteen named sub-skills cover the full checklist (full audit, single page, technical SEO, content quality and E-E-A-T, schema, sitemap, images, GEO for AI search, AEO for answer engines, hreflang, programmatic SEO, competitors, links, and GitHub repository SEO), and ten specialist agents adopt roles like technical SEO, content quality, performance, and a global verifier that deduplicates findings and suppresses contradictions before anything is written. The signature move is evidence over vibes: 89 bundled Python scripts fetch and parse pages, check robots.txt, Core Web Vitals through the free PageSpeed API, security headers, broken links, redirects, readability, and llms.txt readiness, and every finding must carry evidence, impact, and a concrete fix with an explicit confidence label (confirmed, likely, or hypothesis). Full audits ship a FULL-AUDIT-REPORT.md plus a prioritized ACTION-PLAN.md, and a scoring rubric with published weights keeps results comparable across runs. By @Bhanunamikaze, listed here with credit to its creator. Positioned against ultimate-seo-geo (also in this batch, which presents itself as a Claude-focused SEO and GEO audit with scoring): this one targets several agent platforms (Antigravity, Codex, Claude) and leans on script-verified evidence and confidence labels rather than a headline score. Honest caveats: the full pipeline assumes an agent that can run Python and shell commands; visual analysis needs Playwright; paid APIs like Search Console or Knowledge Graph are optional extras, the core checks work for free; and as with any audit, fix priorities are guidance, not gospel. Skill Harbor never reviews the code, review it yourself before use.
Version:
Quick answer
Agentic SEO Skill is a free deterministic, LLM-first SEO audit framework for coding agents, built for Antigravity, Codex and Claude. Sixteen named sub-skills cover full audits, single pages, technical SEO, content quality, schema, sitemaps, images, GEO for AI search, AEO for answer engines, hreflang, competitors and links, with evidence scripts and confidence-labeled fixes.
Install
Copy the install package below, then paste it into Muse🧪 Install ran in our test sandbox · Nov 11, 2026📌 Pinned version: commit 6919916Prerequisites: an AI agent with file tools (Read, Write, Bash), such as Claude Code or Codex; Python 3 for the 89 bundled evidence scripts. Optional: a GitHub token or the gh CLI only for the GitHub-repo-SEO features; Playwright only for visual screenshots. No paid service is required for the core checks. Install "Agentic SEO Skill" for me. A deterministic LLM-first SEO audit framework: 16 named sub-skills, 10 specialist agents, and evidence scripts that back every finding with proof and a confidence label. Repository: https://github.com/Bhanunamikaze/Agentic-SEO-Skill Pinned version: install the code at commit 69199160e18372bc5cdf9ddec20ccb9fb1b509f1 exactly (Skill Harbor tested this version). Do not substitute a newer version. If this commit is unreachable, stop and tell me. 1. Fetch the SKILL.md file (plus its resources/ and scripts/ folders) from the repository into a temporary folder 2. Safety check: review the SKILL.md and scripts for anything suspicious (unexpected network calls, shell commands, credential harvesting). The skill loads API keys from CLI flags, env vars, or a local .env file; it must never contain hardcoded secrets. Verify that holds here; STOP on any red flag and tell me. 3. Install it as a skill: copy SKILL.md and its helper files into the agent's skills directory, in a folder named "agentic-seo". 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself (e.g. save my API key in the vault). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.
Saved to your recent installs. Find it anytime on /connect.
🔒 Security, provenance and what this touches
- It works with an API key or a token that you provide.
What the scan found — excerpts from the install prompt
- uses API keys or tokens — 5. Rapporte ce qui a été installé, où, et ce qu'il me reste à faire moi-même (ex. enregistrer ma clé API dans
The install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?
Verification certificate
Dated facts about what was checked for this listing, and how. This is not a safety certification.
- Pinned version
- 6919916 · 2026-10-13
- Sandbox install test
- Install ran in our test sandbox · Nov 11, 2026 · Observed during the install test: files.pythonhosted.org, pypi.org
- Creator identity
- Not verified
- Fingerprint watch
- Last checked · Nov 19, 2026 : no change detected in the files linked by this install prompt
- Install prompt analysis
- 2026-10-13 : uses API keys or tokens
Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify
Questions
How do I install a skill?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the skill up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a skill before installing it.