When a restaurant, cafe, or bar wants to audit how it shows up for local diners — local-pack rank for its cuisine/city queries, review themes, and recent social buzz (TikTok) about the venue and its…
$ npx skills add unifapi-agent/agents --skill restaurant-local-buzz -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install unifapi-agent/agents restaurant-local-buzz --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/unifapi-agent/agents.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/restaurant-marketing/restaurant-local-buzz .claude/skills/restaurant-local-buzz && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "restaurant-local-buzz" agent skill from https://github.com/unifapi-agent/agents/tree/main/skills/restaurant-marketing/restaurant-local-buzz into .claude/skills/restaurant-local-buzz/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "restaurant-local-buzz", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/unifapi-agent/agents/tree/main/skills/restaurant-marketing/restaurant-local-buzzType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add unifapi-agent/agents --skill restaurant-local-buzz -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install unifapi-agent/agents restaurant-local-buzz --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/unifapi-agent/agents.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/restaurant-marketing/restaurant-local-buzz .agents/skills/restaurant-local-buzz && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "restaurant-local-buzz" agent skill from https://github.com/unifapi-agent/agents/tree/main/skills/restaurant-marketing/restaurant-local-buzz into .agents/skills/restaurant-local-buzz/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "restaurant-local-buzz", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add unifapi-agent/agents --skill restaurant-local-buzz -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install unifapi-agent/agents restaurant-local-buzz --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/unifapi-agent/agents.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/restaurant-marketing/restaurant-local-buzz .cursor/skills/restaurant-local-buzz && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "restaurant-local-buzz" agent skill from https://github.com/unifapi-agent/agents/tree/main/skills/restaurant-marketing/restaurant-local-buzz into .cursor/skills/restaurant-local-buzz/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "restaurant-local-buzz", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/unifapi-agent/agents.git --path skills/restaurant-marketing/restaurant-local-buzz--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add unifapi-agent/agents --skill restaurant-local-buzz -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install unifapi-agent/agents restaurant-local-buzz --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/unifapi-agent/agents.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/restaurant-marketing/restaurant-local-buzz .gemini/skills/restaurant-local-buzz && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "restaurant-local-buzz" agent skill from https://github.com/unifapi-agent/agents/tree/main/skills/restaurant-marketing/restaurant-local-buzz into .gemini/skills/restaurant-local-buzz/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "restaurant-local-buzz", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install unifapi-agent/agents restaurant-local-buzzInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add unifapi-agent/agents --skill restaurant-local-buzz -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/unifapi-agent/agents.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/restaurant-marketing/restaurant-local-buzz .github/skills/restaurant-local-buzz && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "restaurant-local-buzz" agent skill from https://github.com/unifapi-agent/agents/tree/main/skills/restaurant-marketing/restaurant-local-buzz into .github/skills/restaurant-local-buzz/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "restaurant-local-buzz", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add unifapi-agent/agents --skill restaurant-local-buzz -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install unifapi-agent/agents restaurant-local-buzz --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/unifapi-agent/agents.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/restaurant-marketing/restaurant-local-buzz .opencode/skills/restaurant-local-buzz && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "restaurant-local-buzz" agent skill from https://github.com/unifapi-agent/agents/tree/main/skills/restaurant-marketing/restaurant-local-buzz into .opencode/skills/restaurant-local-buzz/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "restaurant-local-buzz", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
restaurant-local-buzzWhen a restaurant, cafe, or bar wants to audit how it shows up for local diners — local-pack rank for its cuisine/city queries, review themes, and recent social buzz (TikTok) about the venue and its…
Restaurant Local Buzz is an agent skill from unifapi-agent/agents. When a restaurant, cafe, or bar wants to audit how it shows up for local diners — local-pack rank for its cuisine/city queries, review themes, and recent social buzz (TikTok) about the venue and its category. Also use on "are we in the map pack for [cuisine] near me," "restaurant reviews," "why aren't we showing up for dinner near me," "what are people saying about us," "is our restaurant trending on TikTok," or "restaurant local marketing." Reads public listing and social data only — marketing research, not…
Its SKILL.md is about 2.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `README.md`).
It sits in Marketing & SEO, covering Local SEO. It works with TikTok. The repository describes itself as: Open-source marketing agents for Claude, ChatGPT, Codex, OpenClaw & Hermes. One plugin: SEO audits, GEO / AI-visibility, local SEO, KOL pricing, social listening & competitive… The licence is MIT.
5 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit fb53247. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Restaurant Local Buzz loads about 2.5k tokens when it runs. Until then it costs about 143 tokens; SKILL.md has 1,060 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from unifapi-agent/agents at commit fb53247, republished under its MIT licence (© unifapi-agent). 1,060 words, ~2,458 tokens.
.claude/skills/restaurant-local-buzz/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.You are a local + social discovery analyst for restaurants. Restaurants win discovery on three signals: local-pack rank for "best [cuisine] near me" and "dinner near me," reviews (count, rating, velocity, and the themes diners repeat), and social buzz — TikTok and Instagram food trends drive a growing share of where people decide to eat. This skill audits all three for one venue and rolls them into a single Local Buzz Index, read-only, so the operator knows exactly where they stand before changing anything.
This is an enhanced skill: it reads live public data through UnifAPI.
Rank, reviews, and buzz are all live and local — you pull the actual pack, the actual listing, and the actual social feed, not memory. Use the unifapi skill to connect (OAuth MCP), then call:
local/search, maps/search — for each cuisine + city diner query, the map listings that surface and the 3–5 nearest competitors, each with name, place_id, rating, review_count, category, position, plus the trailing-90-day review count (velocity) and a sample of recent review text to tally themes. Pass the neighborhood centroid as the search point so positions are reproducible; match the venue on place_id, not name.seo/serp — the organic local results around the diner queries, to confirm what else wins the click and whether the venue ranks organically when it's absent from the pack.tiktok/search (recent clips naming the venue by name/handle/location and rising posts for its cuisine + city, with view/like counts and recency), tiktok/search/hashtags (whether a cuisine or city hashtag — e.g. #ramentok — is rising locally and what's trending under it), and tiktok/videos/{id}/comments (on a clip naming the venue or a viral local dish, read what diners are actually saying — the dish, the wait, the vibe).UnifAPI reads public data only. Keep any billing metadata so the report can state record cost.
.agents/product-marketing.md / .claude/product-marketing.md first if it exists.)local/search + maps/search per query; record where the venue ranks (pack 1–3, extended 4–10, below-pack-but-organic via seo/serp, or absent) and which competitors hold the top slots, with their review counts. Stamp each with search point + date.rating, review_count, 90-day velocity, and tally the review themes from the text sample (see rubric) — service, wait, specific dishes, value, ambiance, noise.tiktok/search to find recent clips naming the venue, tiktok/search/hashtags to scan its cuisine/city for rising hashtags and sounds, and tiktok/videos/{id}/comments on the most-viewed relevant clip to read diner sentiment. Note any dish or trend the venue could ride, with links and view counts.Score three legs 0–100 each, then weight into one index. Reviews carry the most weight because they drive both pack rank and conversion; rank is the visibility multiplier; buzz is the swing factor that can spike covers fast.
| Leg | What it measures | 0 | 50 | 100 |
|---|---|---|---|---|
| Rank | Local-pack presence across the diner queries | absent on all core queries | in pack on ~half, mid positions | pack 1 on most core queries |
| Reviews | Standing + freshness + sentiment themes vs the local leader | far behind on count/velocity, negative themes recur | mid-pack count, steady velocity, mixed themes | at/above leader on count + velocity, positive themes dominate |
| Buzz | Live social momentum for the venue and its category | no mentions, flat category | occasional mentions, category steady | recent venue mentions and/or a rising local dish/sound to ride |
Reviews leg reuses the shared reputation-scoring prominence math (volume 40 / velocity 35 / rating 15 / language 10, normalized to 0–100) so it's comparable with the other local benchmarks. Local Buzz Index = 0.40·Reviews + 0.35·Rank + 0.25·Buzz. Report the index and the three legs — the legs say what to fix, the index says how urgent.
Review-theme tally: from the recent review-text sample (and the tiktok/videos/{id}/comments read), count mentions per theme (service, wait, a named dish, value, ambiance, noise, cleanliness) for the venue and the leader. A theme that recurs negatively for the venue but not the leader is a conversion leak; a dish named repeatedly and positively is a promotion asset and a possible social hook.
# Restaurant Local Buzz — <venue> — <date>
Search params: search point <neighborhood centroid> · language <…>
## Combined report
| Venue | Rank leg | Reviews leg | Buzz leg | Local Buzz Index |
| ------------------ | -------- | ----------- | -------- | ---------------- |
| Target venue | 35 | 48 | 70 | 49 |
| Leader (Ramen Bar) | 90 | 88 | 40 | 78 |
## Local-pack rank table
- Venue vs nearest competitors across the key diner queries, position per cell, each competitor's review count, stamped with search point + date.
## Review snapshot
- Count, rating, 90-day velocity, prominence score, top recurring themes (positive + negative), venue vs leader — every number cited to its public listing record.
## Social-buzz brief
- Recent TikTok clips naming the venue (`tiktok/search`), rising hashtags/sounds for the category (`tiktok/search/hashtags`), diner sentiment from a top clip (`tiktok/videos/{id}/comments`) — with links and view counts.
## Where we stand
- The index, the three legs, and the single highest-leverage move tying rank, reviews, and buzz together.
- Record cost consumed (or best estimate if billing metadata is unavailable).A ramen shop in a dense neighborhood. "best ramen near me" → venue absent from pack (
local/search, rank leg 35); the leader holds pack 1 with 540 reviews vs the venue's 95. Review themes: "wait" recurs negatively for the venue (12 of 40 sampled) but not the leader, while "tonkotsu broth" is named positively 9 times. TikTok:tiktok/searchfinds a local creator's clip of the venue's spicy miso bowl at 60k views in 2 weeks;tiktok/search/hashtagsshows #ramentok rising locally;tiktok/videos/{id}/commentson the clip is full of "where is this" → buzz leg 70. Index ≈ 0.40·48 + 0.35·35 + 0.25·70 = 49. Where we stand: reviews and rank trail the leader, but live buzz on the spicy miso bowl is the swing — the highest-leverage move is riding that clip (the venue's own team posts) while the wait-time theme is the conversion leak to address operationally.
© unifapi-agent, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 1 other file in skills/restaurant-marketing/restaurant-local-buzz of unifapi-agent/agents.
Open the folder on GitHubat commit fb53247
Restaurant Local Buzz next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Restaurant Local Buzz this skillunifapi-agent/agents | 589 | — | ~2.5k | Automated safety check: Pass | MIT | |
| 11 Channel Setup Globalminhnv0807/ai-business-skills | 610 | — | ~3.2k | Automated safety check: Pass | MIT | |
| 11 Thiet Lap Kenhminhnv0807/ai-business-skills | 610 | — | ~5.1k | Automated safety check: Pass | MIT | |
| FLOW SEO FrameworkAgriciDaniel/claude-seo | 19k | 2 repos | ~1.4k | Automated safety check: Pass | MIT | |
| Google Mapscablate/mcp-google-map | 469 | — | ~909 | Automated safety check: Pass | MIT | |
| Ad Creativecoreyhaines31/marketingskills | 54k | — | ~6.3k | Automated safety check: Pass | MIT |
minhnv0807/ai-business-skills
A skill your agent uses when the user needs to choose and stand up marketing channels and the tech behind them — channel selection scoring, platform-by-platform setup checklists, business account…
minhnv0807/ai-business-skills
Dung khi can MO va thiet lap kenh marketing tu con so khong — TikTok Brand, Zalo OA, Fanpage, Instagram Business, Google Business Profile, TikTok Shop, tai khoan email: checklist setup 4 giai doan…
AgriciDaniel/claude-seo
Brings the FLOW framework's stage-specific SEO prompts into the agent, from keyword discovery through backlinks, on-page work and conversion to local SEO, loaded on demand.
cablate/mcp-google-map
Search places, resolve addresses, compare routes, inspect neighborhoods, and retrieve geographic or environmental facts through the standalone @cablate/mcp-google-map CLI.
coreyhaines31/marketingskills
When the user wants to generate, iterate, or scale ad creative — headlines, descriptions, primary text, or full ad variations — for any paid advertising platform.
cablate/mcp-google-map
Analyze Google Business Profile visibility, geographic grid rankings, local search keywords, and nearby competitors through the standalone Google Maps CLI.
unifapi-agent/agents
When the user wants to track how often their brand or domain gets mentioned across ChatGPT and AI search engines over a set of prompts, and how that share of voice compares to named competitors over…
unifapi-agent/agents
When a seller or SDR wants to catch public buying intent on X/Twitter and LinkedIn — someone asking for a tool they sell, complaining about or switching off a competitor, or hiring for a role that…
unifapi-agent/agents
When the user wants to research customers from public communities, or synthesize customer language, pains, and objections.
unifapi-agent/agents
When the user wants to research keywords, find keyword opportunities, run a keyword gap analysis, build topic clusters, or compare what competitors rank for.
unifapi-agent/agents
When the user wants to add, fix, or optimize schema markup and structured data on their site.
unifapi-agent/agents
When the user wants to audit, review, or diagnose SEO issues on their site.
Works with
Categories
When a restaurant, cafe, or bar wants to audit how it shows up for local diners — local-pack rank for its cuisine/city queries, review themes, and recent social buzz (TikTok) about the venue and its…. Restaurant Local Buzz is an agent skill from unifapi-agent/agents. When a restaurant, cafe, or bar wants to audit how it shows up for local diners — local-pack rank for its cuisine/city queries, review themes, and recent social buzz (TikTok) about the venue and its category.
Restaurant Local Buzz fits situations like: tasks that involve Local SEO.
Run `npx skills add unifapi-agent/agents --skill restaurant-local-buzz -a claude-code`. Or copy the skill folder (skills/restaurant-marketing/restaurant-local-buzz in unifapi-agent/agents) into .claude/skills/restaurant-local-buzz in your project. Claude Code loads it when a task matches its description.
Run `npx skills add unifapi-agent/agents --skill restaurant-local-buzz -a codex`. Or copy the skill folder (skills/restaurant-marketing/restaurant-local-buzz in unifapi-agent/agents) into .agents/skills/restaurant-local-buzz in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add unifapi-agent/agents --skill restaurant-local-buzz -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/restaurant-local-buzz, .gemini/skills/restaurant-local-buzz, .github/skills/restaurant-local-buzz and .opencode/skills/restaurant-local-buzz in your project.
SKILL.md names no scripts, command-line tools or credentials: Restaurant Local Buzz is instructions for the agent only.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Restaurant Local Buzz is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.5k tokens (SKILL.md is roughly 9.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Restaurant Local Buzz: 11 Channel Setup Global (minhnv0807/ai-business-skills, 610 stars), 11 Thiet Lap Kenh (minhnv0807/ai-business-skills, 610 stars), FLOW SEO Framework (AgriciDaniel/claude-seo, 19k stars) and Google Maps (cablate/mcp-google-map, 469 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
unifapi-agent (a GitHub organization) maintains it in unifapi-agent/agents, which has 589 GitHub stars. The repository holds 47 skills in this directory. The repository was last updated on September 5, 2026.
Source: unifapi-agent/agents on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.
