# Momentic Skills for Claude Code Free, MIT-licensed agent skills for SEO, GEO, AEO, and AI-search-readiness audits. Built and maintained by [Momentic](https://momenticmarketing.com). They run on the public Momentic MCP server (https://momenticmarketing.com/mcp) — no signup, no auth. Anything that follows the [Agent Skills RFC v0.2.0](https://agentskills.io) can install them. Tested in Claude Code; should work in any compliant runtime. ## One-line install (Claude Code) ```bash curl -fsSL https://momenticmarketing.com/install-skills.sh | sh ``` Downloads each skill, verifies its SHA-256 against the published index, and installs to `~/.claude/skills/`. Re-run any time to update. Pipe-to-shell makes you nervous? Read the script first: ```bash curl -fsSL https://momenticmarketing.com/install-skills.sh | less ``` Override the install path with `CLAUDE_SKILLS_DIR`: ```bash CLAUDE_SKILLS_DIR=./skills curl -fsSL https://momenticmarketing.com/install-skills.sh | sh ``` After install, restart your Claude Code session so the new skills register. ## Skills ### `page-seo-score` Score any public URL on six on-page SEO categories (title/meta, headings, content, schema, links, agent-readiness) and return a graded report with the top three fixes. ```bash mkdir -p ~/.claude/skills/page-seo-score && curl -fsSL https://momenticmarketing.com/.well-known/agent-skills/page-seo-score/SKILL.md -o ~/.claude/skills/page-seo-score/SKILL.md ``` ### `geo-aeo-readiness` Evaluate whether a site or page is ready to be cited by AI search (ChatGPT, Claude, Perplexity, Gemini, Copilot). Performs a three-pass audit — automated checks via the Momentic MCP, a structured manual checklist, and a six-stage diagnostic ladder for root-causing failure — and returns a verdict (AI-ready / partial / not-ready) with the specific stage where the site is losing. Use for serious audits, not just SERP checks. ```bash mkdir -p ~/.claude/skills/geo-aeo-readiness && curl -fsSL https://momenticmarketing.com/.well-known/agent-skills/geo-aeo-readiness/SKILL.md -o ~/.claude/skills/geo-aeo-readiness/SKILL.md ``` ### `google-update-impact` Assess whether a site is exposed to a recent Google algorithm update by reading Momentic's tracker coverage of the update and matching its risk factors against the site's signals. ```bash mkdir -p ~/.claude/skills/google-update-impact && curl -fsSL https://momenticmarketing.com/.well-known/agent-skills/google-update-impact/SKILL.md -o ~/.claude/skills/google-update-impact/SKILL.md ``` ### `schema-recommender` Diagnose missing or wrong JSON-LD on any URL and prescribe specific schema.org types with ready-to-paste payloads. ```bash mkdir -p ~/.claude/skills/schema-recommender && curl -fsSL https://momenticmarketing.com/.well-known/agent-skills/schema-recommender/SKILL.md -o ~/.claude/skills/schema-recommender/SKILL.md ``` ### `robots-ai-audit` Audit how a site treats AI crawlers (GPTBot, ClaudeBot, PerplexityBot, GoogleOther, CCBot, Google-Extended, Applebot-Extended, etc.) across all four layers — robots.txt, firewall/WAF, CDN bot management, and access-log error rates. Uses analyze_site for the robots.txt layer and check_bots for live per-bot WAF/CDN reachability with verdicts. Returns a per-bot reachability verdict with explanations and the exact fixes. ```bash mkdir -p ~/.claude/skills/robots-ai-audit && curl -fsSL https://momenticmarketing.com/.well-known/agent-skills/robots-ai-audit/SKILL.md -o ~/.claude/skills/robots-ai-audit/SKILL.md ``` ### `agent-ready-checklist` Walk the agent-readiness stack (markdown negotiation, Link headers, llms.txt, MCP server card, agent skills index, api-catalog) and prescribe paste-ready code/config to add what is missing. Reference implementation is momenticmarketing.com. ```bash mkdir -p ~/.claude/skills/agent-ready-checklist && curl -fsSL https://momenticmarketing.com/.well-known/agent-skills/agent-ready-checklist/SKILL.md -o ~/.claude/skills/agent-ready-checklist/SKILL.md ``` ### `ask-momentic-blog` Answer SEO, GEO, AEO, and content strategy questions using Momentic's blog as a primary source. Searches the blog, fetches relevant posts, and synthesizes a cited answer. ```bash mkdir -p ~/.claude/skills/ask-momentic-blog && curl -fsSL https://momenticmarketing.com/.well-known/agent-skills/ask-momentic-blog/SKILL.md -o ~/.claude/skills/ask-momentic-blog/SKILL.md ``` ### `ai-search-explained` Authoritative explanation of how AI search actually works — the AI answer chain, where it diverges from classic search, the 4 gates of visibility, the 3 forces (freshness, authenticity, semantic richness), the centroid model, and the three eras of AI visibility. Use to explain grounding, evidence selection, passage selection, query fan-out, and citation mechanics. ```bash mkdir -p ~/.claude/skills/ai-search-explained && curl -fsSL https://momenticmarketing.com/.well-known/agent-skills/ai-search-explained/SKILL.md -o ~/.claude/skills/ai-search-explained/SKILL.md ``` ### `internal-linking` Audit a site's internal link graph — find orphan pages, hub-and-authority structure, anchor-text quality issues, isolated clusters, and link-equity distribution. The agent crawls pages on the user's machine (their IP, no Worker subrequest cap) and the MCP does the graph computation. Returns prescriptive fixes with specific (source, target, anchor) recommendations. ```bash mkdir -p ~/.claude/skills/internal-linking && curl -fsSL https://momenticmarketing.com/.well-known/agent-skills/internal-linking/SKILL.md -o ~/.claude/skills/internal-linking/SKILL.md ``` ### `entity-graph-audit` Audit how a brand or person is represented in the open entity graph — Wikidata presence, Wikipedia coverage, social profile linkage, sameAs consistency, and citation drift across surfaces. Combines lookup_entity (free Wikidata + Wikipedia APIs), the agent's native web search, and analyze_page to detect entity-name drift, missing canonical surfaces, and AI-grounding trust gaps. ```bash mkdir -p ~/.claude/skills/entity-graph-audit && curl -fsSL https://momenticmarketing.com/.well-known/agent-skills/entity-graph-audit/SKILL.md -o ~/.claude/skills/entity-graph-audit/SKILL.md ``` ### `content-brief` Generate a content brief anchored to the same authoritative sources AI grounding systems prefer — Wikipedia/Wikidata for canonical structure, the agent's own web search for live citation snapshot, and analyze_page for current top-source signals. No SERP API costs, no scraping. Output is a paste-ready outline with H2 structure, must-cover entities, schema recommendations, and a coverage-gap analysis against the user's existing pages. ```bash mkdir -p ~/.claude/skills/content-brief && curl -fsSL https://momenticmarketing.com/.well-known/agent-skills/content-brief/SKILL.md -o ~/.claude/skills/content-brief/SKILL.md ``` ## Discovery (machine-readable) - Index: https://momenticmarketing.com/.well-known/agent-skills/index.json (with SHA-256s) - Each skill: https://momenticmarketing.com/.well-known/agent-skills//SKILL.md - MCP server: https://momenticmarketing.com/mcp · [server card](https://momenticmarketing.com/.well-known/mcp/server-card.json) ## Help The skills call our MCP tools (`analyze_page`, `analyze_site`, etc.). All free, all read-only. If a skill finds problems on your site and you'd like help fixing them, [book a 30-minute call](https://momenticmarketing.com/contact).