“Inspect this repo and fix one verifiable site defect.”
fix-my-site
"headline": post.title,+ "author": {+ "@type": "Person",+ "name": post.author.name+ },
Connected adds a prioritized queue and re-audit closure.
20 open-source skills your coding agent reads. MIT, pinned v1.0.0, and no account or API key: it works from your site and your repo.
curl -fsSL https://raw.githubusercontent.com/techwright-lab/groundcrew-seo/v1.0.0/install.sh | bash› inspect this repo and fix one verifiable site defect.
finding13 article pages missing author markup
verifyfetched 13 pages · no author in the Article JSON-LD
fixapp/views/posts/_schema.html.erb · +4 −0
test6 runs, 0 failures
statelocally verified · deployed: not yet
One finding, one focused fix, your own tests. A fix isn’t finished until the next audit says so.
1 <script type="application/ld+json"> 2 <%= raw({ 3 "@context": "https://schema.org", 4 "@type": "Article", 5 "headline": post.title, 6 + "author": { 7 + "@type": "Person", 8 + "name": post.author.name 9 + },10 "datePublished": post.published_on.iso8601, 11 "image": post.cover_url 12 }.to_json) %> 13 </script>
Ask in your own words. Your agent picks the skill and returns evidence you can check.
“Inspect this repo and fix one verifiable site defect.”
fix-my-site
"headline": post.title,+ "author": {+ "@type": "Person",+ "name": post.author.name+ },
Connected adds a prioritized queue and re-audit closure.
“Run the full growth loop on northwind.example.”
grow
Connected runs the same loop against live findings.
“Audit my site and explain the Core Web Vitals.”
site-audit
Connected adds scheduled history and severity.
“Connect TrustGrowth and show what it can do here.”
trustgrowth
Optional. Every other skill runs without it.
“Can AI crawlers reach my site, and is our llms.txt right?”
ai-visibility
Readiness, kept apart from visibility. Connected adds score-level components today.
“Review our authorship and trust signals.”
eeat-review
Connected adds a persisted assessment.
“Why do competitors outrank us on equal content?”
authority-review
No score it can’t measure. Connected adds TrustGrowth’s authority pillar, named as such.
“Compare us with two competitors.”
competitor-watch
Connected adds curated tracking history.
“Give me a prioritized keyword shortlist.”
keyword-scout
Connected adds normalized opportunities.
“What should we publish and why?”
content-strategy
Connected adds measured gap inputs.
“Find link gaps versus our competitors.”
backlink-opportunities
Connected adds detailed reads, where documented.
“List the content we have published.”
content-desk
Read-only. Content writes stay on the waitlist.
“Turn the audit into a report for the team.”
audit-report
“Report keyword positions since last month.”
keyword-report
“Report our referring-domain movement.”
authority-report
“What did our competitors change?”
competitor-readout
“Can AI systems reach, read and recall us?”
geo-report
“What changed this week, and what’s next?”
weekly-report
“Write a claim-safe growth report.”
score-report
“Give me today’s standup.”
standup
No. Start standalone, and connect later if you want the managed layer.
The answers come from the repo, so you can check each one.
Twenty open-source Markdown skills, MIT licensed, that guide a coding agent through auditing a site, fixing one verified defect in your repository, and checking it again after deploy. The rules live in the repo, so you can read every one before your agent runs it.
No. No account, no API key. It works from your public site, your repository, and evidence you import. Connecting TrustGrowth later adds live findings, prioritisation, history, scheduled work, and post-deploy re-audits.
It changes root causes and prepares a pull request. It does not push to your default branch unless your workflow explicitly allows it, and anything that can deindex a site — robots, redirects, canonicals, content judgment — needs owner confirmation every time. Findings it cannot map are escalated for a human, not guessed.
It is the third of three states the skills keep separate: locally verified means the tests pass, deployed means the change is live, and audit-verified means a fresh measurement confirmed the finding is closed. A fix is not finished until the next audit says so.
The safety is inspectable rather than promised: the skills are plain Markdown you read before installing, fetched web content is treated as untrusted evidence and never as instructions to the agent, and billable research needs a bounded cost estimate and explicit approval for that batch. A dependency-free doctor script checks the whole set.
No. Disavow, toxicity verdicts and automated outreach are on the refusal list, in the repository, where you can check that they are.
Any agent host that reads Markdown skill files. File compatibility is not feature parity, though — hosts differ, and REST and MCP coverage can differ too, so the skills discover the live contract instead of assuming it.
Connected mode starts at $9/month. Standalone stays free and MIT.
Paste one line into your terminal, then ask your agent to fix one verifiable site defect.
curl -fsSL https://raw.githubusercontent.com/techwright-lab/groundcrew-seo/v1.0.0/install.sh | bash