Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add shawnpang/startup-founder-skills --skill seo-technicalgit clone --depth 1 https://github.com/shawnpang/startup-founder-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/shawnpang/startup-founder-skills/seo-technical)<a href="https://agentmods.dev/skills/shawnpang/startup-founder-skills/seo-technical"><img src="https://agentmods.dev/badge/skills/shawnpang/startup-founder-skills/seo-technical/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/shawnpang/startup-founder-skills/seo-technical"><img src="https://agentmods.dev/badge/skills/shawnpang/startup-founder-skills/seo-technical.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00035 | $0.01810 |
| Opus 5 | $0.00017 | $0.00905 |
| Sonnet 5 | $0.00007 | $0.00362 |
| Haiku 4.5 | $0.00003 | $0.00181 |
Grade A, and why
seo-technical scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
1 near-identical copy found in the catalogue:
- seo-technical — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SEO Technical
When to Use
- Running a technical SEO audit on an existing site.
- Diagnosing why pages are not being indexed or ranked.
- Optimizing Core Web Vitals or page speed.
- Setting up site architecture (sitemaps, robots.txt, canonicalization).
- Implementing structured data / schema markup.
- Managing AI crawler access via robots.txt.
- Preparing a new site or migration for SEO readiness.
- Reviewing JavaScript rendering and its impact on indexation.
Context Required
- From startup-context: product description, target audience, primary keywords, current domain and site structure.
- From the user: site URL, access to Google Search Console data (if available), specific pages of concern, known issues, tech stack (static site, SPA, WordPress, etc.), whether the site has been previously audited.
Workflow
Audit across 9 technical dimensions. Score on a 100-point scale with category breakdowns.
- Crawlability audit — Foundation; nothing else matters if search engines cannot crawl the site.
- Check robots.txt for unintended disallow rules.
- Verify XML sitemap exists, is submitted to Search Console, and is up to date.
- Identify crawl errors (4xx, 5xx status codes).
- Check for orphan pages (no internal links pointing to them).
- Audit redirect chains — flatten to single hops. Chains of 3+ waste crawl budget and dilute link equity.
- For sites with 10,000+ pages, analyze crawl budget efficiency and remove low-value pages from the index.
- Indexation audit — Ensure crawled pages are actually indexed.
- Check
site:domain.comresults vs. expected page count. - Look for
noindextags applied unintentionally. - Identify duplicate content issues and missing canonical tags.
- Check for thin content pages that may be filtered out.
- Review index coverage report in Search Console for excluded pages.
- Check
- Security and HTTPS — HTTPS is a ranking signal and a trust requirement.
- Verify HTTPS everywhere with proper redirects from HTTP.
- Check for mixed content issues.
- Validate SSL certificate and HSTS headers.
- URL structure — Short, descriptive, hyphenated URLs without parameters.
- Consistent URL patterns across the site.
- No duplicate content from URL variations (trailing slashes, www vs. non-www).
- Self-referencing canonical tags on every page.
- Mobile optimization — As of July 2024, Google crawls and indexes ALL websites exclusively with the mobile Googlebot user-agent. Mobile-first is not optional.
- Mobile and desktop content parity is mandatory.
- Test with mobile-friendly tools.
- Responsive design, no horizontal scroll, touch targets properly sized.
- Core Web Vitals — Google uses these as ranking signals. Current targets:
- LCP (Largest Contentful Paint): Target under 2.5 seconds. Fixes: optimize hero images, implement lazy loading, use CDN, reduce server response time.
- INP (Interaction to Next Paint): Target under 200ms. INP replaced FID in March 2024. Fixes: reduce JavaScript execution time, break up long tasks, optimize event handlers.
- CLS (Cumulative Layout Shift): Target under 0.1. Fixes: set explicit dimensions on images/embeds, avoid injecting content above existing content, use
font-display: swap. - Check for render-blocking CSS/JS, unoptimized images, excessive third-party scripts.
- Structured data — Implement schema markup for rich results.
- Organization schema on the homepage.
- Article/BlogPosting schema on content pages.
- Product schema on product pages.
- FAQ schema where applicable (boosts SERP real estate).
- BreadcrumbList schema for navigation clarity.
- Validate with Google's Rich Results Test.
- JavaScript rendering — Critical for SPAs and JS-heavy sites.
- Serve canonical tags, robots directives, and structured data in initial server-rendered HTML. Google may not reliably process these if injected via JavaScript.
- Verify server-side rendering or pre-rendering is in place for critical content.
- Test what Googlebot actually sees vs. what users see.
- AI crawler management — Managing AI crawlers via robots.txt is a critical 2025-2026 consideration.
- GPTBot (OpenAI), ClaudeBot (Anthropic), PerplexityBot, Bytespider (ByteDance), Google-Extended
- Blocking Google-Extended does NOT affect Google Search indexing or AI Overviews — only Gemini training data.
- Decide per-crawler based on business needs: allow, block, or rate-limit.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 108 lines · 35 tokens per session scan A 44893f103c7d
seo-technical is a skill published in the GitHub repository shawnpang/startup-founder-skills (321 stars, last pushed 5mo ago), licensed MIT. It adds 35 tokens to every session and 1,810 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…