Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add zubair-trabzada/ai-restaurant-claude --skill restaurant-local-seogit clone --depth 1 https://github.com/zubair-trabzada/ai-restaurant-claudeWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/zubair-trabzada/ai-restaurant-claude/restaurant-local-seo)<a href="https://agentmods.dev/skills/zubair-trabzada/ai-restaurant-claude/restaurant-local-seo"><img src="https://agentmods.dev/badge/skills/zubair-trabzada/ai-restaurant-claude/restaurant-local-seo/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/zubair-trabzada/ai-restaurant-claude/restaurant-local-seo"><img src="https://agentmods.dev/badge/skills/zubair-trabzada/ai-restaurant-claude/restaurant-local-seo.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00035 | $0.02825 |
| Opus 5 | $0.00017 | $0.01412 |
| Sonnet 5 | $0.00007 | $0.00565 |
| Haiku 4.5 | $0.00003 | $0.00282 |
Grade A, and why
restaurant-local-seo scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 318 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Local SEO Audit & Strategy
You audit a restaurant's local SEO performance — focusing on how it ranks for "best [cuisine] near me," map pack visibility, GBP optimization, NAP consistency across the citation web, and Restaurant schema markup. Then produce a prioritized 90-day local SEO roadmap.
DISCLAIMER: AI-generated SEO audit. Local search ranking is influenced by many factors including review velocity, proximity, and Google's evolving algorithm.
When to use
/restaurant local-seo <name>— full local SEO audit- "rank for best [cuisine] near me"
- "how do I show up in Google maps"
The 3 Pillars of Local SEO for Restaurants
- Relevance — Does Google understand what you serve and where?
- Distance — How close is the searcher to the restaurant?
- Prominence — How well-known/reviewed/cited is the business?
You can only control #1 and #3.
Execution Pipeline
Step 1: Capture Current Rankings
Run searches and note position:
WebSearch("best [cuisine] in [city]")
WebSearch("best [cuisine] [neighborhood] [city]")
WebSearch("[cuisine] near me [city]")
WebSearch("[cuisine] restaurants [zip code]")
WebSearch("[cuisine] delivery [city]")
WebSearch("[specific dish] [city]")
For each search, capture:
- Map pack position (1, 2, 3, or not in map pack)
- Organic position
- Total competitors in the map pack
- Featured rich snippets / "people also ask"
Step 2: Audit GBP for SEO
Critical SEO elements on GBP:
- Primary category: Restaurant ✓ — must match
- Secondary categories: "Italian Restaurant", "Pizza Restaurant", "Catering" — up to 4 more
- Business description: Front-load with primary keyword
- Services: Listed for "Dine-in", "Takeout", "Delivery", "Catering"
- Attributes: All applicable
- Posts: 1+ per week with target keywords naturally placed
- Q&A: Pre-seed with FAQs containing target keywords
- Reviews: Total count, recency, response rate (all SEO signals)
- Photos: Geo-tagged photos help relevance
- Products: Top menu items as products with names/descriptions/prices
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 318 lines · 35 tokens per session scan A a4c0d3eb8ebb
restaurant-local-seo is a skill published in the GitHub repository zubair-trabzada/ai-restaurant-claude (26 stars, last pushed 3mo ago), licensed MIT. It adds 35 tokens to every session and 2,825 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
analyze-restaurant-reviews
Reads a pile of reviews and names the three to five things guests keep saying, each backed by their own words. Use when the owner says "what are people saying", "read through these reviews", "any patterns in our reviews", or pastes a review export. Does not write replies — for one reply, see google-review-reply.
google-review-reply
Drafts a reply to a Google review in the owner's own voice — short, specific, and inside Google's review policy. Use when the owner says "reply to this review", "someone left us a 2 star", "how do I respond to this", or pastes review text. For finding patterns across many reviews, see analyze-restaurant-reviews.
menu-descriptions
Turns a dish name and its real ingredients into a short menu description that sounds like the restaurant rather than a caterer. Use when the owner says "write my menu descriptions", "make this dish sound better", "my menu is just a list", or pastes a dish list. Does not set prices or make dietary claims.
geo-schema
Schema.org structured data audit and generation optimized for AI discoverability — detect, validate, and generate JSON-LD markup.
varlock
Secure environment variable management with Varlock. Use when handling secrets, API keys, credentials, or any sensitive configuration. Ensures secrets are never exposed in terminal, logs, or LLM context. Provides guidance around integrating varlock into a project, reading/editing .env.schema and other .env files…
portaljs-define-schema
Define a dataset's metadata profile — infer a Frictionless Table Schema from its data, add Data Package metadata (license, sources, keywords), and write it into datasets.json so the showcase renders a typed field table. Extend or customize via the L0-L3 profile ladder. Use when a registered dataset needs field types…