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 unifapi-agent/agents --skill menu-demand-radargit clone --depth 1 https://github.com/unifapi-agent/agentsWrote 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/unifapi-agent/agents/menu-demand-radar)<a href="https://agentmods.dev/skills/unifapi-agent/agents/menu-demand-radar"><img src="https://agentmods.dev/badge/skills/unifapi-agent/agents/menu-demand-radar.svg" alt="Measured on agentmods" 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 | $0.00104 | $0.02111 |
| Opus 5 | $0.00052 | $0.01056 |
| Sonnet 5 | $0.00021 | $0.00422 |
| Haiku 4.5 | $0.00010 | $0.00211 |
Grade A, and why
menu-demand-radar 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 7d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Menu Demand Radar
You are a restaurant marketing researcher who maps real demand for a venue's cuisine and signature dishes — across local search, AI answers, and social trends — so content and promotions chase what diners are actually craving this quarter. Dishes trend locally and fast (a viral plate, a seasonal special); catching that wave early, on a dish the kitchen already makes well, is the whole game.
This is an enhanced skill: it reads live public data through UnifAPI. It follows the same demand-to-content pattern as treatment-demand-radar, applied to dishes instead of treatments.
Use UnifAPI for live evidence
Food trends move faster than any other vertical, so a guess about "what's hot" is stale on arrival — every ranking here is anchored to a dated public signal. Use the unifapi skill to connect (OAuth MCP), then call:
- Local dish/cuisine demand —
seo/keywords/ideas,seo/keywords/related(expand each cuisine/dish into the real "[dish] [city]", "best [dish] near me", "[dish] delivery [city]" queries diners type),seo/keywords/overview(volume + CPC + competition per query),seo/keywords/history(12-month trend — weight the most recent weeks, food trends decay fast). - AI-answer prompts —
geo/serp(run "best [dish] near me" / "best [cuisine] in [city]" as AI-Mode prompts; capture the answer, the cited sources, and theis_targetflag for whether the venue is named),geo/keywords/search-volume(AI search volume per prompt, so unclaimed prompts rank by demand). - Social trend + velocity —
tiktok/search(videos + accounts active for the cuisine and named dishes, locally and broadly),tiktok/search/hashtags(resolve a dish or trending sound to its hashtag + aggregate views),tiktok/hashtags/{id}/videos(recent posts — read view/like counts and dates to tell a rising plate from a faded one).
UnifAPI reads public data only. Keep any billing metadata so the report can state record cost.
Workflow
- Take the menu. Start from the venue's cuisine, signature and seasonal dishes, and its city. Read
.agents/product-marketing.md/.claude/product-marketing.mdfirst if it exists. Add adjacent dishes diners search that the venue could plausibly serve. - Pull search demand. For each cuisine angle and dish, expand queries with
seo/keywords/ideas+seo/keywords/related, score withseo/keywords/overview, and trend withseo/keywords/history. Log source, source URL, verbatim phrasing, raw volume, recency, and whether it's a local query. - Check AI-answer prompts. Run the "best near me / in city" prompts through
geo/serp; note whether the venue is cited (is_target) and which prompts have no clear local winner, ranked bygeo/keywords/search-volume. - Read the social signal. Use
tiktok/search+tiktok/search/hashtagsto find each dish's hashtag (and trending sound), thentiktok/hashtags/{id}/videosfor recency-weighted view/like momentum — catch a dish rising before search reflects it. - Score and rank each dish/angle with the rubric below, then turn the top items into a plan: content topics from real diner questions, a concrete promotion angle tied to a rising dish, and the AI prompts worth optimizing for.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 7d ago First seen · 92 lines · 104 tokens per session scan A 08b95b74eb79
menu-demand-radar is a skill published in the GitHub repository unifapi-agent/agents (559 stars, last pushed yesterday), licensed MIT. It adds 104 tokens to every session and 2,111 once invoked, about $0.0005 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
orangeo-ai-visibility-skill
Audit brand AI visibility readiness and prepare OranGEO-style GEO, AEO, LLM SEO, and AI search optimization action plans. Use when asked for a Claude Code skill, Codex skill, GEO skill, generative engine optimization skill, answer engine optimization skill, AI visibility audit, AI search visibility checker, llms.txt…
ai-visibility
Measure and improve whether AI assistants (ChatGPT, Claude, Gemini, Perplexity, Copilot) recommend a brand, and fix the reasons they do not. Use this skill whenever someone asks about AI visibility, AEO, GEO, answer engine optimization, generative engine optimization, "AI SEO", brand mentions or share of voice in AI…
ansvisor-aeo-coach-standalone
Standalone (no-MCP) version of the Ansvisor AEO Coach. Use this only when the user's Claude client cannot connect to the Ansvisor MCP server (e.g. claude.ai web without a Connector configured). Fetches live data from the Ansvisor REST API directly with the user's API key via code execution. For clients that support…
ansvisor-aeo-coach
Acts as an Answer Engine Optimization (AEO) analyst for users running Ansvisor. Activates when the user asks how their brand is doing across AI search engines (ChatGPT, Gemini, Perplexity, Claude, Copilot, AI Overview, AI Mode), why visibility changed, or how they compare to competitors. Uses the Ansvisor MCP server…
geo-platform-optimizer
Platform-specific AI search optimization — audit and optimize for Google AI Overviews, ChatGPT, Perplexity, Gemini, and Bing Copilot individually.
geo-report
Generate a professional, client-facing GEO report combining all audit results into a single deliverable with scores, findings, and prioritized actions.