AD seo-audit
Audit and optimize any website's SEO + GEO (AI/LLM visibility) + Core Web Vitals, then fix what's broken. Runs a portable, zero-dependency hard-gate audit over a build output directory (Astro/Next/Hugo/Jekyll/plain HTML) and a live-URL crawl/GEO audit (robots.txt AI-crawler policy, sitemap, llms.txt, on-page JSON-LD, canonical, security headers). Includes a battle-tested LCP playbook (7.5s → 1.5s mobile on the reference site): render-blocking CSS, critical-CSS split, font preload discipline, third-party JS deferral. Use when asked to: check/improve a site's SEO, raise a Lighthouse/PageSpeed score, fix slow LCP / Core Web Vitals, make a site discoverable by AI agents (ChatGPT/Claude/Perplexity/Gemini), add structured data, set up robots/sitemap/llms.txt, or review a site before launch. Distilled from the reference site's production build-time SEO gates.
Audit and optimize any website's SEO + GEO (AI/LLM visibility) + Core Web Vitals, then fix what's broken.
As a process D 45/100 · Unfinished process — weak spots: result and completion, inputs and preconditions, failures and branches
How to improve
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 13. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "keywords"
Process rating: all ten parameters 45/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 40Consistency. Frontmatter name (seo-audit) differs from the folder (seo-geo-gate)
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, web, node) that frontmatter does not declare
- 100Steps. 44 steps
- 100Execution cost. Instruction body is 2503 tokens
- 100Running it twice. Mutating operations check current state
- low 10 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (7 tags): a typed call is more reliable
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 864: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Structure: 17 headings
- +3Step-by-step instructions: 44 items
- +4Has examples (5 code blocks)
- +4Reference files are cited in the instructions (4 of 4)
- +3All 2 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.