← Back to Skills Marketplace
alexpolonsky

Jlm Coffee

by alexpolonsky · GitHub ↗ · v2.1.0
darwinlinux ✓ Security Clean
435
Downloads
0
Stars
0
Active Installs
2
Versions
Install in OpenClaw
/install jlm-coffee
Description
Search Jerusalem specialty coffee shops by name, amenities, ratings, and opening hours. Use when user asks about "coffee in Jerusalem", "Jerusalem cafe", "בי...
README (SKILL.md)

Jerusalem Coffee Finder

Search specialty coffee shops in Jerusalem - ratings, amenities, opening hours, reviews, and locations from coffee.amsterdamski.com, created and curated by Shaul Amsterdamski (@amsterdamski2).

Data from the official public JSON export provided by the site maintainer. May not reflect current status. Provided "as is" without warranty of any kind.

Quick Start

# List all coffee shops
python3 {baseDir}/scripts/jlm-coffee.py list

# Find a shop by name
python3 {baseDir}/scripts/jlm-coffee.py search "סיבריס"

Commands

Command Description
list List all approved specialty coffee shops
search \x3Cquery> Search shops by name (Hebrew or English)
get \x3Cid_or_name> Get full details for a specific shop
filter \x3Camenity> Filter shops by amenity (wifi, dogs, kosher, etc.)
open-now Show shops currently open
amenities List all available amenity filters
surprise Pick a random coffee shop (prefers open ones)

Search and Filter Examples

# Search by name (Hebrew or English)
python3 {baseDir}/scripts/jlm-coffee.py search "רוסטרס"
python3 {baseDir}/scripts/jlm-coffee.py search "Cafe Pepa"

# Filter by amenity
python3 {baseDir}/scripts/jlm-coffee.py filter wifi
python3 {baseDir}/scripts/jlm-coffee.py filter dogs
python3 {baseDir}/scripts/jlm-coffee.py filter kosher
python3 {baseDir}/scripts/jlm-coffee.py filter laptop

# Shops open right now
python3 {baseDir}/scripts/jlm-coffee.py open-now

# Full details for a shop
python3 {baseDir}/scripts/jlm-coffee.py get "בארוק"
python3 {baseDir}/scripts/jlm-coffee.py get EljFiggwObssQpypWMf0

Options Reference

Option Commands Description
--json all Output in JSON format (agent-friendly)
--no-color all Disable colored output (auto-detected for non-TTY)

Amenity Filters

Key Label Aliases
wifi WiFi
dogs Dog-friendly dog, dog-friendly
laptop Laptop-friendly laptops
outdoor Outdoor seating outside, terrace
accessible Wheelchair accessible wheelchair
vegan Vegan options
kids Kid-friendly children, kid-friendly
quiet Quiet atmosphere
smoking Smoking area
local-roasting Local roasting roasting
sell-beans Sells beans beans
filter-coffee Filter coffee filter
kosher Kosher
open-saturday Open Saturday saturday, shabbat
power Power outlets outlets
parking Parking

Workflow Example

# 1. Find shops with WiFi and look at the list
python3 {baseDir}/scripts/jlm-coffee.py filter wifi

# 2. Get details on one that looks good
python3 {baseDir}/scripts/jlm-coffee.py get "מטאפורה"

# 3. Check what's open right now
python3 {baseDir}/scripts/jlm-coffee.py open-now

# 4. Feeling lucky? Get a random pick
python3 {baseDir}/scripts/jlm-coffee.py surprise

Notes

  • Community-curated: All specialty coffee in Jerusalem, community-reviewed
  • Official data source: Reads from a public JSON export provided by the site maintainer (no API key, no Firestore)
  • Bilingual: Search works with Hebrew and English names
  • Opening hours: Based on Google Places data, cached by the site
  • Reviews included: Shop details show community reviews with ratings
  • Color output: ANSI colors in terminal (respects NO_COLOR env var and --no-color flag)
  • CLI shortcut: Install as jlm-coffee via symlink to the wrapper script
  • No dependencies: Python stdlib only (urllib, json)
  • Fast caching: 15-minute local cache TTL - one fetch covers all commands
Usage Guidance
This skill fetches a public JSON export from a Google Docs URL and caches it under your system temp directory; it does not ask for credentials or install additional software. If you trust the data source (coffee.amsterdamski.com / the Google Doc owner), using the skill is reasonable. If you have concerns: inspect the DOC_ID URL in a browser to verify the data, run the script in an isolated environment, or review the upstream GitHub repo linked in SKILL.md before enabling. Also note the script makes outbound HTTPS requests (network access) and stores a cache file in /tmp (or your platform's temp dir).
Capability Analysis
Type: OpenClaw Skill Name: jlm-coffee Version: 2.1.0 The OpenClaw skill 'jlm-coffee' is a benign utility for searching Jerusalem coffee shops. It fetches data from a single, hardcoded public Google Docs URL (https://docs.google.com/document/d/1BfsXKQLbKjogfSebRr0Ixt4L4VJHqPqTfnWxkosvcuM/export?format=txt) using `urllib.request`. The `SKILL.md` provides clear instructions without any prompt injection attempts. The `jlm-coffee.py` script uses only Python standard libraries, stores temporary cache files in `tempfile.gettempdir()`, and processes user input safely without any shell injection vulnerabilities or dynamic code execution. There is no evidence of data exfiltration, persistence mechanisms, or other malicious behaviors.
Capability Assessment
✓ Purpose & Capability
The name/description (Jerusalem coffee finder) aligns with the included files and behavior. The script fetches a public JSON export, parses shop records, and implements list/search/filter/open-now commands as described. Required binary (python3) and OS restrictions are appropriate.
✓ Instruction Scope
SKILL.md instructs the agent to run the provided CLI with specific commands; the instructions are limited to searching/filtering/reading the public data source and formatting output. There are no instructions to read unrelated files, env vars, or send data to unexpected endpoints.
✓ Install Mechanism
No install spec; the skill is instruction-only plus a single Python script. No downloads or archive extraction are performed. This is the lowest-risk installation model and matches the declared 'no dependencies'.
✓ Credentials
The skill requests no environment variables, no credentials, and no config paths. It only performs outbound HTTPS GET to a Google Docs export URL (public) and uses the system temp directory for a best-effort cache, which is proportionate to its purpose.
✓ Persistence & Privilege
always is false and the skill does not modify other skills or system-wide settings. It writes a transient cache under the OS temp directory only (CACHE_DIR in tempfile.gettempdir()), which is expected and limited in scope.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install jlm-coffee
  3. After installation, invoke the skill by name or use /jlm-coffee
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v2.1.0
- Version updated to 2.1.0 (no other changes detected) - No file changes or feature additions in this release
v2.0.0
Major update: Complete rewrite and feature expansion. - Search, list, and filter Jerusalem specialty coffee shops by name, amenities, ratings, and opening hours. - New CLI with commands for listing, searching, filtering by amenity (wifi, dog-friendly, laptop-friendly, kosher, etc.), viewing open shops, and more. - Shop details now show community ratings, amenities, reviews, and Google-sourced opening hours. - Bilingual support for Hebrew and English names in search. - Improved usability: JSON output, no external dependencies, color options, and fast local caching. - Data now sourced directly from the public JSON export curated by coffee.amsterdamski.com.
Metadata
Slug jlm-coffee
Version 2.1.0
License —
All-time Installs 0
Active Installs 0
Total Versions 2
Frequently Asked Questions

What is Jlm Coffee?

Search Jerusalem specialty coffee shops by name, amenities, ratings, and opening hours. Use when user asks about "coffee in Jerusalem", "Jerusalem cafe", "בי... It is an AI Agent Skill for Claude Code / OpenClaw, with 435 downloads so far.

How do I install Jlm Coffee?

Run "/install jlm-coffee" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Jlm Coffee free?

Yes, Jlm Coffee is completely free (open-source). You can download, install and use it at no cost.

Which platforms does Jlm Coffee support?

Jlm Coffee is cross-platform and runs anywhere OpenClaw / Claude Code is available (darwin, linux).

Who created Jlm Coffee?

It is built and maintained by alexpolonsky (@alexpolonsky); the current version is v2.1.0.

More Skills
self-improving agent
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
⬇ 463283 · by pskoett
Skill Vetter
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
⬇ 259410 · by spclaudehome
Polymarket
Query Polymarket prediction markets. Check odds, find trending markets, search events, track price movements.
⬇ 232503 · by joelchance
Self-Improving + Proactive Agent
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...
⬇ 200423 · by ivangdavila
Github
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
⬇ 191115 · by steipete
ontology
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
⬇ 190156 · by oswalpalash

💬 Comments