Skip to content

Basinfy/Basinfy-SaaS-Studio / .agents/skills/saas-seo

saas-seo

Unverified

SaaS SEO, GEO & Agentic Readiness hub — technical, schema, AI search, llms.txt, and drift.

Running this workflow on this client

Run commands from the project root (use Git Bash on Windows if bash points to an unavailable WSL distro). Shared studio files live in .claude/; follow .agents/PORTABLE-RUNTIME.md and .claude/docs/config-resolution.md for client tools, delegation, and approval rules.

Run bash .claude/hooks/yaml-helper.sh resolve_config --keys locale,review_mode,automation and use its output below.

Resolved above — use as-is; --review overrides review_mode for this run.

SaaS SEO Command Center

Locale & User Profile: Match locale (pt-BR → natural Brazilian Portuguese questions/options, overriding English examples; en → English) and user_profile (founder → plain business language with (Recomendado) first, zero tech jargon; developer → technical). Keep code/tests in English.

Master command hub for SaaS search optimization, generative AI search visibility (GEO), autonomous agent readiness, and on-page technical integrity.


1. Quick Command Dispatch

CommandSkill RoutedPrimary Objective
/saas-seo audit <url>saas-seo-auditFull multi-agent SaaS website audit & prioritized fix plan
/saas-seo technical <url>saas-seo-technical9-category technical crawlability, SSR/SSG rendering, robots.txt
/saas-seo schema <url>saas-seo-schemaSchema.org JSON-LD generation (SoftwareApplication, Organization)
/saas-seo geo <url>saas-seo-geoGenerative Engine Optimization (AI Overviews, Perplexity, ChatGPT)
/saas-seo agentic <url>saas-seo-agenticLighthouse Agentic Browsing (X/N), llms.txt, WebMCP, discovery
/saas-seo content <url>saas-seo-contentSaaS value messaging, E-E-A-T, AI text humanization & watermarks
/saas-seo competitor-pages [url]saas-seo-competitor-pagesHigh-converting 'X vs Y' and 'Alternatives to X' pages
/saas-seo programmatic [plan]saas-seo-programmaticScaled template pages (tools, directories) with <40% thin-content gate
/saas-seo sxo <url> [keyword]saas-seo-sxoSearch Experience Optimization & SERP intent mismatch detection
/saas-seo drift <cmd> <url>saas-seo-driftGit-like SQLite baseline snapshotting and CI/CD regression diffs
/saas-seo scaffold [component]internalScaffold Next.js 14+ SEO files (robots.ts, sitemap.ts, llms.txt)
/saas-seo doctorinternalCheck Python runtime readiness and dependencies without modifying system

2. Bundled Python Execution Engine

All bundled CLI tools live in scripts/seo/ and execute with zero external network bloat and built-in SSRF protection:

python scripts/seo/parse_html.py <url> --json
python scripts/seo/agentic_check.py <url> --json
python scripts/seo/drift_baseline.py <url>
python scripts/seo/drift_compare.py <url>
python scripts/seo/schema_generate.py profile --script-tag

For local development servers (http://localhost:3000), the engine safely allows loopback inspection when CLAUDE_SEO_LOCAL_TARGETS=localhost:3000 is present.


3. Next.js 14+ App Router Code Generation Standards

Whenever implementing SEO features directly into a SaaS codebase, strictly generate code conforming to Next.js App Router conventions:

  1. Static & Dynamic Metadata: Use export const metadata: Metadata or export async function generateMetadata(): Promise<Metadata>.
  2. Granular AI Crawler Management: Generate app/robots.ts (or app/robots.txt/route.ts when emitting Content-Signal headers) explicitly distinguishing AI training bots (GPTBot, ClaudeBot, Google-Extended, Amazonbot, Applebot-Extended, CCBot) from AI search citability bots (OAI-SearchBot, Claude-SearchBot, PerplexityBot).
  3. Dynamic Sitemaps: Generate app/sitemap.ts implementing MetadataRoute.Sitemap.
  4. Agentic Discovery & Machine-Readable Endpoints: Implement app/llms.txt/route.ts, Accept: text/markdown content negotiation + RFC 8288 Link headers, and /.well-known/ manifests (agent-skills/index.json, mcp/server-card.json, api-catalog, ai-catalog.json, oauth-protected-resource, http-message-signatures-directory, auth.md) targeting IsItAgentReady Level 4–5.
  5. JSON-LD Structured Data: Deliver server-rendered <script type="application/ld+json"> components to ensure instant indexing by crawlers without client-side hydration delays.

4. Execution Workflow

  1. Identify Request Intent: Route single-domain requests to the respective specialized /saas-seo-* skill.
  2. Execute Diagnostic Check: If URL is provided, run scripts/seo/parse_html.py or scripts/seo/agentic_check.py.
  3. Formulate Findings: Structure findings into Critical (P0), High (P1), Medium (P2), and Low (P3).
  4. Draft Code or Recommendations: Provide copy-pasteable Next.js 14+ components or configuration files.
  5. Ask for Approval: Follow the studio 5-step collaborative loop before writing to disk: "May I write this to [filepath]?"
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 469kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 321kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 321kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 321kUpdated Claude CodeCodexVerifiedInstall