Seo llmeo
Broomva agent-skills monorepo — 48 Tier-2 skills compatible with Claude Code, Codex, Cursor, Gemini CLI, Goose, Copilot. Layout follows anthropics/skills (agentskills.io spec). Install: npx skills add broomva/skills --skill <name>.
npx -y skills add broomva/skills --skill seo-llmeoAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 3 stars3 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.
What its author says it does
Copied from the file, not written here
SEO and LLM Engine Optimization (LLMEO) skill for BroomVA content. Analyzes pages for traditional search-engine signals (meta tags, structured data, Core Web Vitals, internal linking) and for LLM discoverability (llms.txt, semantic headings, FAQ schema, citation-friendly structure). Generates actionable audits and rewrites. Use when: (1) auditing a page or site for SEO health, (2) optimizing content for LLM citation and AI search surfaces, (3) generating meta tags and structured data, (4) creating or updating llms.txt, (5) improving content structure for both Google and AI answer engines.
SKILL.md
4.0 KB, 837 tokens by cl100k_base, as published. Nobody here has run it
SEO / LLMEO
Search-engine optimization plus LLM engine optimization for BroomVA content.
Capabilities
| Area | What it does |
|---|---|
| Traditional SEO | Meta tags, Open Graph, canonical URLs, sitemap, robots.txt, structured data (JSON-LD) |
| Core Web Vitals | LCP, CLS, INP guidance based on page structure |
| LLMEO | llms.txt generation, semantic heading hierarchy, FAQ schema, citation-friendly paragraphs |
| Content audit | Readability score, keyword density, internal/external link ratio |
| Rewrite suggestions | Actionable diffs to improve both SEO and LLMEO signals |
Commands
audit <url-or-path>
Run a full SEO + LLMEO audit on a page. Returns a scored checklist with fix suggestions.
llms-txt <site-root>
Generate or update an llms.txt file for the site, following the emerging standard for
LLM-friendly site descriptions.
meta <url-or-path>
Generate optimal meta tags (title, description, OG, Twitter card) for a page.
structured-data <url-or-path>
Generate JSON-LD structured data (Article, FAQ, HowTo, etc.) for a page.
Audit Checklist
Traditional SEO Signals
- Title tag present, 50-60 characters, includes primary keyword
- Meta description present, 150-160 characters, includes CTA
- Canonical URL set correctly
- Open Graph tags complete (og:title, og:description, og:image, og:url)
- Twitter Card tags present (twitter:card, twitter:title, twitter:description, twitter:image)
- H1 tag present, unique per page, includes primary keyword
- Heading hierarchy valid (no skipped levels)
- Internal links present (minimum 3 per page)
- Images have alt text
- Structured data valid (JSON-LD, no errors in schema.org validator)
- robots.txt allows crawling
- sitemap.xml present and valid
LLMEO Signals
-
llms.txtpresent at site root - Semantic heading hierarchy (H1 > H2 > H3, logically nested)
- FAQ schema present where appropriate
- Citation-friendly paragraphs (clear topic sentences, factual claims with sources)
- Content chunked into digestible sections (300-500 words per section)
- Key definitions and concepts clearly stated (not buried in prose)
- Tables used for structured comparisons
- Code blocks properly labeled with language
Core Web Vitals Guidance
| Metric | Good | Needs Improvement | Poor |
|---|---|---|---|
| LCP | < 2.5s | 2.5s - 4.0s | > 4.0s |
| CLS | < 0.1 | 0.1 - 0.25 | > 0.25 |
| INP | < 200ms | 200ms - 500ms | > 500ms |
llms.txt Specification
The llms.txt file lives at the site root and describes the site for LLM crawlers:
# Site Name
> Brief description of what this site is about.
## Docs
- [Page Title](url): Description of what this page covers
- [Another Page](url): Description
## API
- [Endpoint docs](url): API reference description
## Optional
- [Less important page](url): Description
Integration
Works with:
content-creation— apply SEO/LLMEO checks before publishingarcan-glass— ensure design system pages have proper metabroomva.tech— site-wide audit and llms.txt managementbrand-icons— ensures OG/Twitter meta tags reference correct image assets
Gives 2 of the 12 instructions most seo skills give in 837 tokens
Counted across 454 of the 460 authors here whose files we hold, read 2026-08-06
- implement structured data using JSON-LDhere, and in 30 of 454, across 26 files
- write unique meta descriptions under 160 charactershere, and in 27 of 454, across 20 files
- verify one H1 exists per pagein 24 of 454, across 15 files
- maintain a single h1 per pagein 24 of 454, across 15 files
- use JSON-LD format for all schema markupin 23 of 454, across 15 files
- use descriptive anchor text for internal linksin 21 of 454, across 16 files
- add descriptive alt text to imagesin 19 of 454, across 15 files
- read product marketing context before auditingin 19 of 454, across 10 files
- write unique title tags under 60 charactersin 19 of 454, across 14 files
- add unique title and meta description per pagein 19 of 454, across 17 files
- Reference the sitemap in robots.txtin 19 of 454, across 18 files
- verify core web vitals meet thresholdsin 17 of 454, across 9 files
Said here and by no other author read
- use FAQ schema where appropriate
- write citation-friendly paragraphs
- chunk content into digestible sections
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.