# LLMSRank docs > How the LLMSRank score is built, audit by audit, and how the rubric has changed. This file covers /docs only; the site-wide index is https://llmsrank.dev/llms.txt. ## Docs - [Docs overview](https://llmsrank.dev/docs.md): The docs landing page: what each docs section covers. - [Method](https://llmsrank.dev/docs/method.md): The scoring model: categories, weights, grade bands and caps. - [Audits](https://llmsrank.dev/docs/audits.md): Every audit the scanner runs, what it checks and how to fix it. - [Changelog](https://llmsrank.dev/docs/changelog.md): Rubric versions, what changed, and the corpus impact. - [Corrections](https://llmsrank.dev/docs/corrections.md): The public log of mistakes we've fixed in scans. ## Retrievability audits - [Covering llms.txt (R1)](https://llmsrank.dev/docs/audits/covering-llms-txt.md): Whether an llms.txt file covers the URL you scanned, at the root (/llms.txt) or at its path (/docs/llms.txt). - [Clean fetch (R2)](https://llmsrank.dev/docs/audits/clean-fetch.md): Whether the file fetches cleanly: HTTP 200, no auth, at most one same-host redirect. - [Content type (R3)](https://llmsrank.dev/docs/audits/content-type.md): Whether the file is served as text/plain or text/markdown. - [Encoding and parsing (R4)](https://llmsrank.dev/docs/audits/encoding-and-parsing.md): Whether the file is valid UTF-8 and parses cleanly as markdown. - [AI crawler access (R5)](https://llmsrank.dev/docs/audits/ai-crawler-access.md): Whether robots.txt lets the major AI crawlers fetch your llms.txt. ## Spec audits - [Single H1 (S1)](https://llmsrank.dev/docs/audits/single-h1.md): Whether the file has exactly one H1, and it names your site or organization. - [Summary blockquote (S2)](https://llmsrank.dev/docs/audits/summary-blockquote.md): Whether a blockquote summary follows directly after the H1. - [H2 sections (S3)](https://llmsrank.dev/docs/audits/h2-sections.md): Whether the body is organized into H2 sections that contain link lists. - [Link line format (S4)](https://llmsrank.dev/docs/audits/link-line-format.md): Whether link lines follow the spec form - [name](url): description. ## Curation audits - [Signal-to-noise (C1)](https://llmsrank.dev/docs/audits/signal-to-noise.md): The share of the file’s links that lead to answer-bearing pages. - [Link descriptions (C2)](https://llmsrank.dev/docs/audits/link-descriptions.md): How many links carry a description, and whether each says what the page answers. - [Ordering (C3)](https://llmsrank.dev/docs/audits/ordering.md): Whether the most citation-worthy content comes first. - [Token budget (C4)](https://llmsrank.dev/docs/audits/token-budget.md): Whether the file fits an agent’s context budget, about 8,000 tokens. - [URL hygiene (C5)](https://llmsrank.dev/docs/audits/url-hygiene.md): Whether link URLs are absolute, canonical, parameter-free and redirect-free. - [Curation, not a sitemap (C6)](https://llmsrank.dev/docs/audits/curation-not-sitemap.md): Whether the file curates your site rather than mirroring your sitemap. - [Freshness signals (C7)](https://llmsrank.dev/docs/audits/freshness-signals.md): Whether the file carries dates that agree with your sitemap and show current content. - [LLM-friendly links (C8)](https://llmsrank.dev/docs/audits/llm-friendly-links.md): The share of the file’s links that point to LLM-friendly content: markdown or plain text rather than an HTML page. ## Agent readiness audits - [Role and scope (A1)](https://llmsrank.dev/docs/audits/role-and-scope.md): Whether the file frames its role, its intended audience and its scope for agents. - [Data-freshness tiers (A2)](https://llmsrank.dev/docs/audits/data-freshness-tiers.md): Whether volatile facts are labelled with how fresh they are, and how to caveat them. - [Intent routing (A3)](https://llmsrank.dev/docs/audits/intent-routing.md): Whether the file routes each kind of user question to the right page. - [Journey flows (A4)](https://llmsrank.dev/docs/audits/journey-flows.md): Whether multi-step user paths are written out as numbered flows. - [Machine surface (A5)](https://llmsrank.dev/docs/audits/machine-surface.md): Whether your API or MCP server is documented well enough for an agent to call it. - [Action endpoints (A6)](https://llmsrank.dev/docs/audits/action-endpoints.md): Whether the file tells agents how users can book, quote, apply, buy or get in touch. - [FAQ blocks (A7)](https://llmsrank.dev/docs/audits/faq-blocks.md): Whether the file includes question-and-answer blocks for common questions. - [Entity identity (A8)](https://llmsrank.dev/docs/audits/entity-identity.md): Whether the file states who you are: your legal or brand name, other names or identifiers, and the meaning of your terms. - [API error handling (A9)](https://llmsrank.dev/docs/audits/api-error-handling.md): Whether the API documentation covers errors, rate limits, auth and fallbacks. ## Compliance audits - [Regulatory guardrails (P1)](https://llmsrank.dev/docs/audits/regulatory-guardrails.md): Whether the file carries the guardrails of the industry playbook you declared, rule by rule. - [Prohibited claims (P2)](https://llmsrank.dev/docs/audits/prohibited-claims.md): Whether the file tells agents which claims they must never make, for each prohibited claim in your declared playbook. - [Required disclosures (P3)](https://llmsrank.dev/docs/audits/required-disclosures.md): Whether the file tells agents to give the disclosures your declared playbook requires. - [Human handoff (P4)](https://llmsrank.dev/docs/audits/human-handoff.md): Whether the file tells agents when to hand the user to a person, and how to reach one. - [Disclaimer text (P5)](https://llmsrank.dev/docs/audits/disclaimer-text.md): Whether the file gives agents disclaimer text, word for word, to attach to answers. - [Citation and licensing (P6)](https://llmsrank.dev/docs/audits/citation-and-licensing.md): Whether the file says how you’d like to be cited, and on what terms content may be used by AI systems. ## Ecosystem audits - [Named AI crawlers (E1)](https://llmsrank.dev/docs/audits/named-ai-crawlers.md): Whether robots.txt names AI crawlers explicitly, rather than relying on a catch-all rule. - [Sitemap freshness (E2)](https://llmsrank.dev/docs/audits/sitemap-freshness.md): Whether sitemap.xml is present and its lastmod dates are plausible. - [Markdown versions (E3)](https://llmsrank.dev/docs/audits/markdown-versions.md): Whether the pages your llms.txt links to have clean markdown versions. - [JSON-LD agreement (E4)](https://llmsrank.dev/docs/audits/json-ld-agreement.md): Whether your JSON-LD / schema.org markup agrees with what the file says about who you are. - [Canonical agreement (E6)](https://llmsrank.dev/docs/audits/canonical-agreement.md): Whether the URLs in your file match the pages’ rel=canonical URLs. - [Agent files (E7)](https://llmsrank.dev/docs/audits/agent-files.md): Whether the site publishes agent instruction files: AGENTS.md, CLAUDE.md or SKILL.md. - [Link relations (E8)](https://llmsrank.dev/docs/audits/link-relations.md): Whether your pages declare their markdown version and the llms.txt that covers them, with link relations.