Best for
- Use when the user wants to find a restaurant, plan a dinner, search for izakayas, or book a group meal in Japan.
jackchuka/skills/restaurant-search/SKILL.md
Use it for engineering and operations tasks; the detail page covers purpose, installation, and practical steps.
Decision brief
Find Japanese restaurants using the hpp CLI (HotPepper Gourmet API). https://github.com/jackchuka/hpp
Compatibility matrix
| Platform | Status | Evidence | What to check |
|---|---|---|---|
| Codex | Not declared | No explicit evidence | Portability before use |
| Claude Code | Not declared | No explicit evidence | Portability before use |
| Cursor | Not declared | No explicit evidence | Portability before use |
| Gemini CLI | Not declared | No explicit evidence | Portability before use |
Installation
The source command is displayed only when detected. A safe inspection prompt is always available so your agent can explain every action before execution.
npx skills add https://github.com/jackchuka/skills --skill "restaurant-search"Inspect the Agent Skill "restaurant-search" from https://github.com/jackchuka/skills/blob/7b0b33f68b8f11522e43622e5cb3bacd802999d2/restaurant-search/SKILL.md at commit 7b0b33f68b8f11522e43622e5cb3bacd802999d2. List every install step, command, network request, credential, file read/write, external action, and rollback step. Explain whether it fits my task. Do not install or execute anything until I approve.
Workflow
Extract from the user's request:
hpp CLI installed and HOTPEPPERAPIKEY env var set
Extract from the user's request:
The API requires area codes, not free-text location names. Resolve the location:
If the user requests a specific cuisine type:
Permission review
No configured static risk pattern was detected
This is not proof of safety. Runtime behavior, indirect dependencies, and hidden external systems are outside the static scan.
Evidence record
| Signal | Value | Evidence type | Meaning |
|---|---|---|---|
| Quality score | 88/100 | Computed | Documentation, specificity, maintenance, and trust rules |
| Repository stars | 15 | Source | Repository attention, not individual Skill quality |
| Compatibility | 0 platforms | Source | Declared in the catalog source record |
| Usage guide | automated source guide | Editorial | Generated or reviewed according to the visible evidence level |
Pinned source
Find Japanese restaurants using the hpp CLI (HotPepper Gourmet API).
https://github.com/jackchuka/hpp
hpp CLI installed and HOTPEPPER_API_KEY env var setExtract from the user's request:
--party-capacity)open/close fields)--genre)--budget)--private-room), non-smoking (--non-smoking), WiFi (--wifi), free drink (--free-drink), etc.--keyword)The API requires area codes, not free-text location names. Resolve the location:
hpp area small --keyword "<location-name>"
This returns small area codes (e.g., X085 for 浜松町) along with parent middle/large area codes.
If no small area matches, try middle area:
hpp area middle --keyword "<location-name>"
If the user provides coordinates (lat/lng), skip area lookup and use --lat, --lng, --range instead.
If the user requests a specific cuisine type:
hpp genre
Common genre codes:
| Code | Genre |
|---|---|
| G001 | 居酒屋 |
| G002 | ダイニングバー・バル |
| G003 | 創作料理 |
| G004 | 和食 |
| G005 | 洋食 |
| G006 | イタリアン・フレンチ |
| G007 | 中華 |
| G008 | 焼肉・ホルモン |
| G009 | アジア・エスニック |
| G010 | 各国料理 |
| G011 | カラオケ・パーティ |
| G012 | バー・カクテル |
| G013 | ラーメン |
| G014 | カフェ・スイーツ |
| G016 | お好み焼き・もんじゃ |
| G017 | 韓国料理 |
If unsure, run hpp genre to get the full list.
If the user specifies a budget:
hpp budget
Common budget codes:
| Code | Range |
|---|---|
| B001 | ~1500円 |
| B002 | 2001~3000円 |
| B003 | 3001~4000円 |
| B008 | 4001~5000円 |
| B004 | 5001~7000円 |
| B005 | 7001~10000円 |
| B006 | 10001~15000円 |
| B012 | 15001~20000円 |
| B013 | 20001~30000円 |
| B014 | 30001円~ |
Build the hpp search command with resolved codes and flags:
hpp search --small-area <code> --party-capacity <N> --count 10
Key flags to apply based on user needs:
| Need | Flag |
|---|---|
| Party size | --party-capacity <N> |
| Genre | --genre <code> |
| Budget | --budget <code> |
| Private room | --private-room |
| Non-smoking | --non-smoking |
| WiFi | --wifi |
| All-you-can-drink | --free-drink |
| All-you-can-eat | --free-food |
| English menu | --english |
| Card payment | --card |
| Late night (after 11pm) | --midnight |
| Lunch | --lunch |
| Keyword | --keyword "<text>" |
| Coordinates | --lat <lat> --lng <lng> --range <1-5> |
Range values for coordinate search: 1=300m, 2=500m, 3=1km, 4=2km, 5=3km.
Always use JSON output (default) for parsing, then present results as a table.
Display results as a markdown table with these columns:
| Column | Source |
|---|---|
| # | Row number |
| Restaurant | name |
| Genre | genre.name |
| Budget | budget.average |
| Access | access (summarize to station + walk time) |
| Private Room | private_room (yes/no/semi) |
| Hours | open (show relevant day only) |
| Link | urls.pc (as clickable markdown link) |
After the table, add brief recommendations highlighting the best options for the user's specific needs (e.g., closest to station, best for groups, has private rooms).
If the user wants to narrow down, add more flags and re-search. Common refinements:
--private-room--budget B001,B002,B003--non-smoking--count or use --start for paginationhpp shop --name "<name>" — Look up a specific restaurant by namehpp special list — Browse special features/tagshpp creditcard — List accepted credit card types--count to limit results (default 10, max 100)open/close fields to verify the restaurant is open on the requested dayclose field for regular holidays (e.g., 日 = Sunday)coupon_urls.sp — mention if the user asks about dealsAlternatives
event4u-app/agent-config
Use when the user says "review the design", "check the UI", or wants a comprehensive UI/UX review. Uses a 7-phase methodology covering interaction, responsiveness, accessibility, and more.
K-Dense-AI/scientific-agent-skills
Distributed computing for larger-than-RAM pandas/NumPy workflows. Use when you need to scale existing pandas/NumPy code beyond memory or across clusters. Best for parallel file processing, distributed ML, integration with existing pandas code. For out-of-core analytics on single machine use vaex; for in-memory speed use polars.
K-Dense-AI/scientific-agent-skills
Medicinal chemistry filters for compound triage. Apply drug-likeness rules (Lipinski, Veber, CNS), structural alert catalogs (PAINS, NIBR, ChEMBL), complexity metrics, and the medchem query language for library filtering.
K-Dense-AI/scientific-agent-skills
Use NeuroKit2 to build or audit reproducible research workflows for physiological time-series preprocessing, event/interval analysis, multimodal alignment, variability, and complexity. Trigger when code imports neurokit2 or needs its current APIs, schemas, and method-aware validation—not for diagnosis or device validation.