agentsclimarketplace

Seo loop

Skill euphoriawolf/ai-assisted-app-kit/skills/new-app/templates/project-kit/seo-loop

Run the {{APP_NAME}} SEO/LLM growth loop from SEO-LOOP.md — measure search + AI-referral traffic, pick the highest-leverage improvement, build it, verify, gated-deploy, log. Use for growing organic/chatbot traffic to {{APP_NAME}}.From its SKILL.md

Install
npx -y skills add euphoriawolf/ai-assisted-app-kit --skill seo-loop

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

1.8 KB, 382 tokens by cl100k_base, as published. Nobody here has run it

{{APP_NAME}} — seo-loop

Executes the growth playbook in SEO-LOOP.md (repo root). The marketing surface is content-as-code in packages/web (Astro content collections + programmatic SEO pages), so improvements are code.

The loop (see SEO-LOOP.md for the full version)

  1. Measure — pull current search + AI-referral data (scripts/seo/: GSC, analytics). Write a dated snapshot + diff.
  2. Analyze / prioritize — pick the one change with the best effort/leverage (a new head-term landing page, better internal linking, JSON-LD, a thin page to fill).
  3. Build — implement in packages/web. Every landing page ships with real examples before the closing CTA, HowTo/FAQ/Breadcrumb JSON-LD, and correct canonical/sitemap entries.
  4. Verifyastro check + build clean; preview the page; validate structured data.
  5. Deploy (gated) — additive marketing scope only; deploy + verify live + be ready to roll back.
  6. Log — append the iteration to scripts/seo/log.md.

Rules

  • Copy goes through /brand-voice; visuals through /design.
  • Additive marketing scope only in the autonomous path — never touch app/api/auth/billing here.
  • If a human and this loop can edit the same marketing files, pause one while the other works.
  • Credentials live in gitignored .seo.env (template: scripts/seo/.seo.env.example).

Optional autonomy

This can run as a weekly scheduled task (the user's schedule skill) inside the SEO-LOOP.md §5 guardrails: additive scope, build-gated, deploy+verify+rollback.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most marketing audience skills give in 382 tokens

Counted across 690 of the 894 authors here whose files we hold, read 2026-08-07

  • Apply Poppins font to headingsin 41 of 690, across 6 files
  • Apply Lora font to body textin 41 of 690, across 6 files
  • Use Arial fallback for headingsin 39 of 690, across 4 files
  • Use Georgia fallback for body textin 39 of 690, across 4 files
  • Maintain text hierarchy and formattingin 39 of 690, across 4 files
  • Use accent colors for non-text shapesin 38 of 690, across 3 files
  • Use RGB values for precise color matchingin 38 of 690, across 3 files
  • Use brand colors for primary text and backgroundsin 36 of 690, across 1 file
  • Read product marketing context file before asking questions, starting, or auditingin 35 of 690, across 23 files
  • Use active voice instead of passive voicein 26 of 690, across 10 files
  • Implement or generate appropriate JSON-LD structured datain 24 of 690, across 17 files
  • Prioritize clarity over clevernessin 22 of 690, across 8 files

Said here and by no other author read

  • write a dated seo snapshot and diff
  • pick the highest leverage improvement
  • implement improvements in packages/web
  • include examples before closing cta
  • add howto faq and breadcrumb json-ld
  • run astro check and verify clean build

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.