By zhizdev
Automate SEO and GEO optimization for static sites: inventory pages and tech stack, audit on-page signals like titles/metas/structure/links/AI-readiness, generate landing pages/blogs/internal links/sitemaps/robots.txt/llms.txt via query-fanout, humanize AI copy, and dispatch from Bonemeal growth queue using CLI skills.
npx claudepluginhub zhizdev/overgrow --plugin overgrowAudit on-page SEO and GEO (generative engine optimization) signals across the site — title tags, meta descriptions, H1/H2/H3 hierarchy, canonical tags, Open Graph, structured data, content length, internal link density, and AI-citation readiness. Use this skill whenever the user asks to "audit SEO", "check metadata", "review titles and descriptions", "check heading structure", "run an SEO audit", "GEO audit", "check schema markup", "find SEO issues", or review any on-page signal affecting organic or AI-search visibility. Output is a prioritized issue list with per-page findings and fixes.
Pull the open Bonemeal action queue (landing pages and blog posts the user has not built yet) via the bonemeal MCP server, let the user pick which ones to build, dispatch each to the spawn-pages or spawn-blogs skill with the action's brief, and mark each completed in Bonemeal once the file is written. Use this whenever the user says "grow", "/grow", "build my Bonemeal queue", "what's in my Bonemeal queue", "build the suggested pages", or wants to act on Bonemeal's content suggestions. Stop and ask the user before marking actions complete the first time, then remember their preference.
Systematically rewrites AI-generated or AI-sounding text on web pages, documents, or pasted content to sound human. Use this skill whenever a user asks to "humanize", "de-AI", "make this sound less like AI", "rewrite to avoid AI detection", or "clean up AI writing". Also trigger when a user pastes text and asks to make it sound more natural, more human, or less robotic. The skill applies a strict deterministic rule pipeline — NOT creative rewriting — making it safe for agentic/automated use.
Scan the current codebase to identify and categorize every public-facing page (landing pages, product/feature pages, solutions, pricing, resources, blogs, case studies, about, legal) and produce a single authoritative inventory document. Use this skill whenever the user asks to "init overgrow", "set up overgrow", "scan the site", "inventory the pages", "categorize pages", "map the site", or whenever any other overgrow skill needs a baseline page map and none exists yet. Output is a structured markdown inventory at `.overgrow/inventory.md` that all other overgrow skills read from.
Generate or audit an `/llms.txt` file at the site root that makes the site legible to LLMs and AI answer engines at inference time, following the llms.txt proposal (Jeremy Howard, 2024). Use this skill whenever the user asks to "build llms.txt", "create llms.txt", "generate llms.txt", "audit llms.txt", "make my site LLM-friendly", "expose the site to AI assistants", "let ChatGPT / Claude / Perplexity cite my site", "add an AI assistants index", or asks about `.md` companion pages for LLM consumption. Output is a valid `llms.txt` file (or an audit) plus optional `.md` companion page generation for top pages.
Audit an existing sitemap.xml / robots.txt or generate new ones following sitemaps.org protocol and Google Search Central guidance, with a growth-first default that allows every crawler including AI search and AI training bots. Use this skill whenever the user asks to "build a sitemap", "generate sitemap.xml", "audit the sitemap", "refresh sitemap", "write robots.txt", "check robots", "allow AI crawlers", "block AI crawlers", "fix crawl budget", "submit to Google", or any other discovery / indexing configuration task. Output is a valid sitemap.xml (or sitemap index) and/or robots.txt, plus a written audit when auditing.
Given the product and the existing page inventory, identify missing blog topics and generate new blog posts that capture search/AI intent using the query-fanout pattern. Use this skill whenever the user asks to "spawn blogs", "generate blog posts", "expand the blog", "build out a content cluster", "write blog ideas", "cover more search intents", "query fanout for blogs", or wants new long-form content that supports existing pillars. Output is one new post per topic in the project's existing post format (markdown, MDX, component, or CMS migration note), with frontmatter shape mirrored from an existing post.
Examine every existing page on the site, build a semantic map across pillars, and add missing internal links so the site becomes a semantic graph anchored on clear topical pillars. Use this skill whenever the user asks to "add internal links", "build internal linking", "build a semantic graph", "link related pages", "strengthen topical authority", "fix orphan pages", "add pillar linking", or wants hub-and-spoke linking between pillars, hubs, and supporting content. Output is an edit list (proposed link insertions) plus optionally direct edits to page source files.
Given the product offering and existing page inventory, create new core landing and resource pages (homepage refresh, features, solutions, pricing, comparison, resource hubs, about) that capture core product intent using the query-fanout pattern. Use this skill whenever the user asks to "spawn pages", "generate landing pages", "create marketing pages", "build a pricing page", "add a solutions page", "build out the site", "fill in missing pages", or wants new top-level marketing/product pages. Output is one new page per route in the project's native file format (component or markdown), matching the existing page style and framework idiom.
Standalone image generation plugin using Nano Banana MCP server. Generates and edits images, icons, diagrams, patterns, and visual assets via Gemini image models. No Gemini CLI dependency required.
Memory compression system for Claude Code - persist context across sessions
Streamline people operations — recruiting, onboarding, performance reviews, compensation analysis, and policy guidance. Maintain compliance and keep your team running smoothly.
Prospect, craft outreach, and build deal strategy faster. Prep for calls, manage your pipeline, and write personalized messaging that moves deals forward.
Create content, plan campaigns, and analyze performance across marketing channels. Maintain brand voice consistency, track competitors, and report on what's working.
External network access
Connects to servers outside your machine
Share bugs, ideas, or general feedback.
Overgrow is your AI CMO as a plugin, with a comprehrensive suite of commands to optimize your SEO and GEO. Overgrow is distilled from human written knolwedge and official web standards documentation.
Get Started in Claude Code
/plugin marketplace add zhizdev/overgrow
/plugin install overgrow@overgrow
/overgrow:init
Scans the repo to build an understanding of the existing project.
/overgrow:audit
Check titles, meta, H-hierarchy, canonicals, OG, JSON-LD schema, content depth, internal links, AI-citation readiness
/overgrow:spawn-pages
Draft landing pages that target query fan-out patterns to maximize AI visibility.
/overgrow:spawn-blogs
Draft blogs that target query fan-out patterns to maximize AI visibility.
/overgrow:spawn-internal-links
Build a web of internal links around semantic pillars.
/overgrow:sitemap
Audit or build sitemap.xml + robots.txt to maximize growth.
/overgrow:llmstxt
Audit or build /llms.txt to maximize growth.
/overgrow:humanize
Make it sounds human.
/overgrow:init # build the inventory
/overgrow:audit # find gaps & issues
/overgrow:spawn-pages # fill missing core pages
/overgrow:spawn-blogs # fill thin pillars
/overgrow:spawn-internal-links # wire the semantic graph
/overgrow:humanize # clean AI-sounding drafts
/overgrow:sitemap # expose everything to search & AI
/overgrow:llmstxt # ship an LLM-legible site map
/overgrow:humanize "paste AI-generated text here"
/overgrow:humanize content/blog/new-post.md
We curated hundreds of SEO and GEO best practices from official documentations and tutorials and distilled the knowledge into this set of skills for overgrow. Each individual primary source is summarized by gpt-5.4 into a few concise bullet points. We then use opus-4.7 to group and cluster all summarized bullet points into a condensed markdown format ready for skill usage at knowledge/geo.md.
Web searches on ChatGPT, Gemini, and Claude all use query fan-out to discover releveant content pieces before answering the prompt. We curated a base set of searches covering both specific and broad search intents and capture hundreds of real query fan-out behavior. We distill the behavior into a set of rules for reverse engineering fan-out patterns in knowledge/query-fanout.md. Overgrow uses this knowledge to propose new landing, blog, and resources pages.
/plugin marketplace add zhizdev/overgrow
/plugin install overgrow@overgrow
Commands appear as /overgrow:init, /overgrow:audit, etc. Update with /plugin update overgrow@overgrow, or enable auto-update in /plugin → Marketplaces.
cp -r .cursor your-project/
Cursor skills require setup: switch to Nightly in Settings → Beta, then enable Agent Skills in Settings → Rules. Cursor skills docs
The drop-in includes
.cursor/mcp.jsonwiring the Bonemeal MCP server (powers/grow). Cursor handles OAuth / dynamic client registration on first tool call.
cp -r .gemini your-project/
Gemini CLI requires the preview channel:
npm i -g @google/gemini-cli@preview, then/settings→ enable Skills, then/skills list. Gemini CLI skills docsThe drop-in includes
.gemini/settings.jsonwiring the Bonemeal MCP server withoauth.enabled = true, so Gemini CLI runs the discovery + DCR + PKCE flow itself.
cp -r .codex your-project/
Codex uses a different command prefix:
$overgrow:init,$overgrow:audit, etc.The drop-in includes
.codex/config.toml, which Codex loads as a project-scoped override once the project is trusted (Codex prompts on first run). Themcp_servers.overgrowentry uses Codex's built-in OAuth login (scopes+oauth_resource), so on first$overgrow:growcall Codex opens a browser for consent — no bearer token to paste.
.cursor/.gemini/.codex/One source of truth in source/skills/. The build transforms it into each provider's expected layout, frontmatter shape, and placeholder conventions — authored once, shipped four ways.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claim