agentsclimarketplace
Sign in

Relume sitemap

Skill kvalifik-workflows/relume-sitemap/skills/relume-sitemap

Generate Relume-ready visual sitemap clipboard payloads by crawling XML sitemaps or live pages with the relume-sitemap CLI.From its SKILL.md

Install
npx -y skills add kvalifik-workflows/relume-sitemap --skill relume-sitemap

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

2.8 KB, 644 tokens by cl100k_base, as published. Nobody here has run it

Relume Sitemap

Use this skill when a user asks to create, import, paste, reverse engineer, or stress-test a Relume sitemap from a website.

The CLI is the source of truth. Prefer commands in this order:

  1. relume-sitemap if it is already available on PATH.
  2. node ./bin/relume-sitemap.mjs when working inside this repository.
  3. npx -y @kvalifik/relume-sitemap@latest when the CLI is not installed.

Do not hand-author escaped Relume payload JSON unless patching the CLI itself.

Workflow

  1. Inspect the source sitemap or discovered URL list before crawling.
  2. If multiple language/path scopes are present, ask which language/path to cover before building. Do not combine languages unless explicitly requested.
  3. Ask whether the Relume sitemap should include page sections or only page nodes.
  4. Crawl pages from the selected source sitemap/path scope.
  5. Build the visual sitemap tree from crawl.json using the actual URL/folder structure.
  6. Validate the generated Relume payload.
  7. Copy the HTML payload to the clipboard when the environment supports it.
  8. Tell the user to paste into Relume's sitemap canvas.

Commands

Inspect:

relume-sitemap inspect --sitemap https://www.example.com/sitemap.xml

Discover when the sitemap is missing or sparse:

relume-sitemap discover --url https://www.example.com --out ./work/example

Crawl one language/path scope:

relume-sitemap crawl \
  --sitemap https://www.example.com/sitemap.xml \
  --include / \
  --exclude /da,/de \
  --out ./work/example-en

Build with sections:

relume-sitemap build \
  --crawl ./work/example-en/crawl.json \
  --out ./work/example-en \
  --sections include \
  --copy

Build without sections:

relume-sitemap build \
  --crawl ./work/example-en/crawl.json \
  --out ./work/example-en \
  --sections none

Validate:

relume-sitemap validate --payload ./work/example-en/relume-payload.html

Quality Checks

  • Crawl status counts should be mostly or entirely 200.
  • Payload validation must pass.
  • The generated root and page count should match expectations.
  • Review sitemap.md for hierarchy sanity.
  • Multilingual sites should be scoped to one language/path unless all languages were explicitly requested.
  • The tree should follow URL/folder structure unless the user explicitly asks for custom grouping.
  • Section mode must match the user's choice.

Outputs

The build command writes:

  • crawl.json
  • sitemap-tree.json
  • relume-payload.json
  • relume-payload.html
  • sitemap.md
  • copy-to-clipboard.html

Prefer showing sitemap.md for review and using relume-payload.html for Relume paste.

What ships with it

Read from the repository

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

Gives 0 of the 12 instructions most seo skills give in 644 tokens

Counted across 342 of the 364 authors here whose files we hold, read 2026-09-06

  • Read product marketing context before asking questionsin 38 of 342, across 16 files
  • Use one clear H1 per pagein 25 of 342, across 13 files
  • Measure Core Web Vitals against stated thresholdsin 23 of 342, across 16 files
  • Verify robots.txt allows AI crawlersin 22 of 342, across 16 files
  • Use descriptive anchor text for internal linksin 22 of 342, across 16 files
  • Keep title tags around 50-60 charactersin 19 of 342, across 16 files
  • Add a self-referencing canonical URL to every pagein 16 of 342, across 14 files
  • Lead every section with a direct answerin 15 of 342, across 9 files
  • Submit the sitemap to Google Search Consolein 15 of 342, across 12 files
  • Keep key answer passages to 40-60 wordsin 14 of 342, across 8 files
  • Add statistics with cited sourcesin 14 of 342, across 8 files
  • Give each page one primary search intentin 13 of 342, across 7 files

Said here and by no other author read

  • Inspect the source sitemap or URL list before crawling
  • Ask which language or path scope to cover
  • Ask whether to include page sections
  • Crawl pages from the selected scope
  • Build the sitemap tree from crawl.json
  • Follow URL folder structure when building the tree

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.