본문으로 건너뛰기
cccskills
무료GitHub에 공개

sitemap

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.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

zhizdev/overgrow
설치 방법 보기

포함된 파일(1)

  • SKILL.md5.3 KB

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

Overgrow — Sitemap & robots.txt

This skill is the deterministic pipeline for producing and auditing sitemap.xml, sitemap indexes, and robots.txt. It is tuned for growth — by default it invites every compliant crawler, including AI search and AI training bots, unless the user explicitly opts out per user-agent.

Primary reference

Read knowledge/sitemap.md from the plugin root before doing anything. That file is the canonical, rule-by-rule pipeline this skill implements. Follow it exactly. This SKILL.md is the entry-point summary; knowledge/sitemap.md is the source of truth.

Also consult knowledge/geo.md sections on technical SEO and indexability for AI visibility considerations that affect sitemap/robots decisions.

Mode selection

Parse $ARGUMENTS:

  • audit (or no args, existing sitemap present) → run the audit flow.
  • build (or no args, no sitemap present) → run the generation flow.
  • A full origin URL like https://example.com → use as the canonical origin.

If mode is ambiguous, STOP and call the AskUserQuestion tool to clarify.

Audit flow

  1. Read .overgrow/inventory.md for the authoritative page list. If missing, run init first.
  2. Locate existing sitemap(s): public/sitemap.xml, static/sitemap.xml, sitemap.xml.ts, Next.js app/sitemap.ts, framework-generated routes. If none found, switch to build mode.
  3. Locate existing robots.txt: public/robots.txt, static/robots.txt, app/robots.ts, or config-driven.
  4. Validate against knowledge/sitemap.md. Report findings:
    • Protocol violations (invalid URL, missing <loc>, bad encoding, over 50k URLs in one file, over 50MB uncompressed).
    • Coverage gaps (pages in inventory missing from sitemap, sitemap URLs missing from inventory — possible 404s or stale entries).
    • lastmod hygiene (missing, future-dated, identical across all entries).
    • Canonical mismatches (sitemap URL vs. rendered canonical tag).
    • robots.txt issues (blocking assets needed for render, blocking sitemap path, contradictory allow/disallow, outdated AI-bot rules).
    • AI-crawler posture (GPTBot, ClaudeBot, PerplexityBot, Google-Extended, Bingbot — flag if silently blocked).
  5. Write findings to .overgrow/sitemap-audit.md with severity (critical / high / medium / low) and specific fixes.

Build flow

  1. Read .overgrow/inventory.md for the list of indexable pages. Exclude utility and anything the user flags.
  2. Collect inputs (see knowledge/sitemap.md § "Inputs to collect"). If any input is missing, ask once in a single message.
  3. Generate sitemap.xml following the rules in knowledge/sitemap.md. For > 50k URLs, emit a sitemap index plus shard files.
  4. Generate or update robots.txt. Default posture: open (allow all user-agents, disallow explicit exclusion paths, reference the sitemap). Only switch to restricted or closed when the user says so — typically for staging, internal, or compliance-locked sites.
  5. Write the files to the project's static root (public/, static/, framework-specific path). Do not overwrite existing files without asking; produce .next/.proposed variants if there's an existing file.
  6. Print a short summary: URL count, shard count, AI-crawler posture, where the files were written.

Defaults for AI bots (growth-first)

Unless the user says otherwise, robots.txt explicitly allows:

  • GPTBot (OpenAI)
  • ChatGPT-User
  • OAI-SearchBot
  • ClaudeBot / anthropic-ai / Claude-Web
  • PerplexityBot
  • Google-Extended
  • Applebot-Extended
  • Bingbot (always)
  • CCBot (Common Crawl)

Explicit allow lines beat silence — spell them out so the posture is auditable. If the user wants to restrict one or more, ask for the list and write Disallow: / blocks per user-agent.

Constraints

  • Never emit sitemap entries for routes that do not exist in the inventory.
  • Never include query-stringed URLs unless the user intentionally exposes them.
  • Respect canonical tags — the sitemap URL must match the page's own canonical.
  • Follow knowledge/sitemap.md for encoding, escaping, lastmod formatting, and sharding rules. Do not improvise.
  • Output must pass XML validation against the sitemaps.org schema.

What this skill does NOT do

  • Does not submit sitemaps to Search Console / Bing Webmaster — print the URL for the user to submit.
  • Does not generate HTML sitemaps (user-facing navigation pages).
  • Does not touch hreflang beyond noting issues in the audit — i18n link generation lives in a dedicated sitemap that this skill will build if the inventory declares locales.

리뷰

아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.

댓글

로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.

아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.

보내면 바로 공개됩니다. 이메일 주소나 전화번호 같은 개인 정보는 쓰지 마세요. URL은 2개까지입니다.

0 / 1,000자

이 양식은 reCAPTCHA로 보호되며 Google 개인정보처리방침 및 서비스 약관이 적용됩니다.

같은 저장소의 스킬

audit

무료

Audit 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.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

zhizdev/overgrow72026년 5월 2일 업데이트

grow

무료

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.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

zhizdev/overgrow72026년 5월 2일 업데이트

humanize

무료

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.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

zhizdev/overgrow72026년 5월 2일 업데이트

init

무료

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.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

zhizdev/overgrow72026년 5월 2일 업데이트

llmstxt

무료

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.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

zhizdev/overgrow72026년 5월 2일 업데이트

spawn-blogs

무료

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.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

zhizdev/overgrow72026년 5월 2일 업데이트

zhizdev의 스킬 모두 보기

이 스킬의 문제 신고