Agent skill

Pp Halal Gourmet Japan

by mvanhorn in mvanhorn/printing-press-library

Compare explicit food and prayer evidence across Japan with source dates and honest unknowns.

Apache-2.0Auto-check: notes

Install Pp Halal Gourmet Japan

skills CLI
$ npx skills add mvanhorn/printing-press-library --skill pp-halal-gourmet-japan -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install mvanhorn/printing-press-library pp-halal-gourmet-japan --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/mvanhorn/printing-press-library.git skills-src && mkdir -p .claude/skills && cp -r skills-src/cli-skills/pp-halal-gourmet-japan .claude/skills/pp-halal-gourmet-japan && rm -rf skills-src

Use ~/.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/

Facts

Skill name
pp-halal-gourmet-japan
GitHub stars
2.1k
Token cost
~3.7k tokens
SKILL.md length
1,553 words
Files
1
Skills in repo
506
Repo updated
First seen
Licence
Apache-2.0

At a glance

Compare explicit food and prayer evidence across Japan with source dates and honest unknowns.

  • Works in 3 steps: Install via the Printing Press… → Verify: halal-gourmet-japan-pp-cli… → Ensure the reported install directory is…
  • Phrases: find halal condition evidence in Tokyo
  • SKILL.md covers Prerequisites: Install the CLI, When to Use This CLI, Evidence contract and Unique Capabilities, plus 12 more sections
  • Calls go and npx

What it does

Pp Halal Gourmet Japan is an agent skill from mvanhorn/printing-press-library. Compare explicit food and prayer evidence across Japan with source dates and honest unknowns. Trigger phrases: find halal condition evidence in Tokyo, compare halal certification and prayer space facts, check HGJ prayer-space facilities, what is missing from my Muslim travel shortlist, use halal-gourmet-japan, run halal-gourmet-japan.

Its SKILL.md is about 3.7k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: Official library of CLIs generated by the CLI Printing Press. Endorsed, tested, and community-contributed. The licence is Apache-2.0.

When your agent uses it

  • Phrases: find halal condition evidence in Tokyo
  • Compare halal certification and prayer space facts
  • Check HGJ prayer-space facilities
  • What is missing from my Muslim travel shortlist

Example prompts

  • “/pp-halal-gourmet-japan”

Requirements

  • Node.js
  • Pre-approved tools (allowed-tools): Read, Bash

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. Install via the Printing Press installer. It defaults binaries to $HOME/.local/bin on macOS/Linux and…
  2. Verify: halal-gourmet-japan-pp-cli --version
  3. Ensure the reported install directory is on $PATH for the agent/runtime that will invoke this skill.

What it can do on your machine

Read from SKILL.md and the folder at commit d9a1696. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Read
    • Bash

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • go
    • npx

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use npx, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Pp Halal Gourmet Japan loads about 3.7k tokens when it runs. Until then it costs about 93 tokens; SKILL.md has 1,553 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~93
When it runs · the whole SKILL.md, loaded when a task matches
~3.7k

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.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Read, Bash

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.

SKILL.md

The full file from mvanhorn/printing-press-library at commit d9a1696, republished under its Apache-2.0 licence (© mvanhorn). 1,553 words, ~3,663 tokens.

Download SKILL.mdSave it as .claude/skills/pp-halal-gourmet-japan/SKILL.md (or your agent's skills folder).
name
pp-halal-gourmet-japan
description
Compare explicit food and prayer evidence across Japan with source dates and honest unknowns. Trigger phrases: `find halal condition evidence in Tokyo`, `compare halal certification and prayer space facts`, `check HGJ prayer-space facilities`, `what is missing from my Muslim travel shortlist`, `use halal-gourmet-japan`, `run halal-gourmet-japan`.
allowed-tools
Read, Bash
author
zjsng
license
Apache-2.0
argument-hint
<command> [args] | install cli|mcp
<!-- GENERATED FILE — DO NOT EDIT.
     This file is a verbatim mirror of library/travel/halal-gourmet-japan/SKILL.md,
     regenerated post-merge by tools/generate-skills/. Hand-edits here are
     silently overwritten on the next regen. Edit the library/ source instead.
     See the repository agent guide, section "Generated artifacts: registry.json, cli-skills/". -->

Halal Gourmet Japan — Printing Press CLI

Prerequisites: Install the CLI

This skill drives the halal-gourmet-japan-pp-cli binary. You must verify the CLI is installed before invoking any command from this skill. If it is missing, install it first:

  1. Install via the Printing Press installer. It defaults binaries to $HOME/.local/bin on macOS/Linux and %LOCALAPPDATA%\Programs\PrintingPress\bin on Windows:
    bash
    npx -y @mvanhorn/printing-press-library install halal-gourmet-japan --cli-only
  2. Verify: halal-gourmet-japan-pp-cli --version
  3. Ensure the reported install directory is on $PATH for the agent/runtime that will invoke this skill.

If the npx install fails (no Node, offline, etc.), fall back to a direct Go install (requires Go 1.26.6 or newer). This installs into $GOPATH/bin (default $HOME/go/bin), so add that directory to $PATH instead:

bash
go install github.com/mvanhorn/printing-press-library/library/travel/halal-gourmet-japan/cmd/halal-gourmet-japan-pp-cli@latest

If --version reports "command not found" after install, the runtime cannot see the binary directory on $PATH. Do not proceed with skill commands until verification succeeds.

Search restaurants, mosques and prayer spaces by destination. Inspect full conditions, then compare saved evidence, match explicit requirements, identify missing facts, pair food and prayer stops, and track factual changes. Certification labels remain separate from HGJ verification and other conditions.

When to Use This CLI

Use for Japan Muslim-travel decisions that depend on explicit restaurant conditions and mosque/prayer-space facilities. Discover candidates, inspect full details, then compare successful saved observations. This unofficial adapter reads public HGJ pages over ordinary HTTPS without an account or browser runtime.

Evidence contract

  • Keep certification.label_state, certification.certifier, certification.valid_until, verification.month and each food/facility condition separate. HGJ Verified is a platform badge with a month; it does not fill certification fields.
  • reported records an explicit source label. not_reported is missing full-detail evidence, not_visible_on_card means the card cannot establish the fact, inapplicable belongs to another entity family, and reported_negative retains an explicit source JSON-LD false value if supplied.
  • Search cards show limited icons and sometimes +; inspect details before deciding whether all requirements are reported. Repeated source filters are discovery semantics; plan match evaluates each requirement independently.
  • Source descriptions and labels do not establish religious acceptability, ingredient/allergy certainty, cross-contamination control, current certificate validity, current opening or permission to enter.
  • Prayer access notes retain explicit source text. Hours in notes remain source text; no schedule, prayer time or route is inferred. Pair distances are straight-line kilometres.

Unique Capabilities

These capabilities aren't available in any other tool for this API.

Evidence planning
  • plan compare — Align the source-reported food and prayer facts of selected saved places.

    Compare full facts before choosing from a shortlist.

    bash
    halal-gourmet-japan-pp-cli plan compare --restaurants 300739,949742 --prayer 838884 --agent
  • plan match — See which requested source labels are reported and which need confirmation.

    Test every explicit requirement without issuing a halal verdict.

    bash
    halal-gourmet-japan-pp-cli plan match --restaurants 300739 --require certified,meat,prayer --agent
  • plan gaps — List missing certifier, certificate validity, hours and access evidence.

    Prepare factual questions for selected food and prayer stops.

    bash
    halal-gourmet-japan-pp-cli plan gaps --restaurants 300739 --prayer 838884 --agent
  • plan pair — Pair selected restaurants and prayer places by straight-line distance.

    Assess proximity while preserving access and hours unknowns.

    bash
    halal-gourmet-japan-pp-cli plan pair --restaurants 300739 --prayer 838884 --max-km 5 --agent
Saved observations
  • plan changes — See factual changes between the latest two successful observations.

    Recheck a shortlist before visiting and inspect changed evidence.

    bash
    halal-gourmet-japan-pp-cli plan changes --restaurants 300739 --prayer 838884 --agent

Command Reference

WorkflowCommandInputs and behavior
Food discoveryrestaurants searchProvide --prefecture or --query; optional --genre, repeated/comma-separated --feature; --limit 1–50
Food inspectionrestaurants get IDFresh live detail by default; saves a successful factual observation; --data-source local reads saved detail
Prayer discoveryprayer searchProvide destination/keyword; optional --place-type spaces|mosques, repeated/comma-separated --prayer-feature; limit 1–50
Prayer inspectionprayer get IDFull facility and access evidence; saves two observations per source kind/ID
Fact comparisonplan compareSelected saved full-detail rows aligned by condition and evidence fields
Requirement matchingplan matchAdd --require source condition keys; result status says which requested labels are reported
Missing evidenceplan gapsConcrete questions about missing certifier, validity, hours, access, verification or coordinates
Proximity pairingplan pairSelect both kinds; optional --max-km greater than 0 up to 100; no route/access guarantee
Factual recheckplan changesCompares latest two successful observations; one observation gives baseline_missing and empty changes

All plan commands take --restaurants and/or --prayer as comma-separated or repeated numeric IDs, at most 20 per kind. They read local details only and reject --data-source live; save inspections first. Missing snapshots appear in missing_snapshots, never as invented rows. Plans bound output with --limit and pairing examines at most 400 candidate pairs.

Food keys: certified, owner, noAlcoholicDrinks, porkFree, meat, seasoning, tableware, meal, vegetarian, prayer. Prayer keys: wudu, wifi, hotWater, qibla. Missing card conditions do not satisfy any key.

Recipes

Narrow restaurant discovery
bash
halal-gourmet-japan-pp-cli restaurants search --prefecture Tokyo --query ramen --limit 5 --agent --select results.id,results.name,results.source_url

Cards discover candidates; missing card icons are not a requirement verdict.

Inspect food and prayer evidence
bash
halal-gourmet-japan-pp-cli plan compare --restaurants 300739 --prayer 838884 --agent

Load successful detail snapshots before comparing saved facts.

Clarify missing evidence
bash
halal-gourmet-japan-pp-cli plan gaps --restaurants 300739 --prayer 838884 --agent

List unreported certifier, validity, applicable hours/access and coordinates.

Compare proximity
bash
halal-gourmet-japan-pp-cli plan pair --restaurants 300739 --prayer 838884 --max-km 5 --agent

Straight-line distance is not a route, walking time or access guarantee.

Recheck saved observations
bash
halal-gourmet-japan-pp-cli plan changes --restaurants 300739 --agent

Run restaurants get --data-source live again before comparing two successful observations.

Auth Setup

The scoped public pages require no account or API key. Requests use ordinary HTTPS and never book, post or alter an account.

Run halal-gourmet-japan-pp-cli doctor to verify setup.

Agent Mode

Use --agent for JSON, compact, non-interactive, colour-free output. --json returns a plain result object; --agent adds meta.source and a results envelope. Search already has a results array; the agent wrapper preserves one envelope. Select fields before automatic wrapping: detail uses --select id,name,certification,verification; search uses --select results.id,results.name.

--select accepts dotted paths, --compact reduces optional content, --csv/--plain request tabular output, and --quiet requests identities. JSON stays on stdout and warnings stay on stderr. --dry-run performs no network or cache I/O.

Show full SKILL.md (670 more words)Show less

Paths and state

Use --home DIR or HALAL_GOURMET_JAPAN_HOME=DIR to relocate CLI state, or HALAL_GOURMET_JAPAN_DATA_DIR for the data kind. Inspection/planning accept --db PATH; use the same path for the corresponding gets and plans. --no-cache on live inspection suppresses detail-history writes. Successful full-detail snapshots retain two versions per source kind/ID, with a 1,000-place storage cap. Cards, failed fetches and failed parses never create a history baseline.

get with auto/live refreshes the public source; it does not silently fall back to stale data on a failed source read. Explicit local mode preserves the original observation timestamp and warns about old evidence (--max-age 24h by default; --max-age 0 disables the hint). Search has no local equivalent. Planning reads saved facts even when stale and carries observation dates, so recheck selected stops before relying on them.

Automatic learning

The generated recall, teach and playbook helpers maintain local command-learning state. Prefer runtime help when using them; they are separate from successful factual detail snapshots. Disable learning for deterministic or private prompts with --no-learn or HALAL_GOURMET_JAPAN_NO_LEARN=true. Learned hints and candidates never become source facts, certification or access evidence.

Health Check

bash
halal-gourmet-japan-pp-cli doctor --json
halal-gourmet-japan-pp-cli agent-context --pretty

Troubleshooting

Missing saved detail: run the corresponding restaurants get ID or prayer get ID with the same cache path. A plan changes row with baseline_missing needs a second successful live inspection.

A format-change, HTTP failure, timeout, oversized body or throttle is an error, distinct from a source-confirmed empty search. Use the canonical source URL from the output to inspect the current listing. A 429 has typed exit 7; wait before retrying.

Exit Codes

CodeMeaning
0Successful output, including explicit empty or missing-cache planning states
2Invalid usage or incompatible data source
3Source record or requested local detail not found
5Upstream request or parsing failure
7Source rate limit
10Configuration or local-cache failure

Argument Parsing

Empty/help arguments show CLI help. install refers to the prerequisites above. Otherwise choose the specific food, prayer or plan leaf command, inspect its help when unfamiliar, and pass user text as argv/MCP arguments rather than interpolated shell code.

MCP Server Installation

The server mirrors the working CLI commands over stdio. Install both sibling binaries using the public-library installer, or build them together from source:

bash
go build -o halal-gourmet-japan-pp-cli ./cmd/halal-gourmet-japan-pp-cli
go build -o halal-gourmet-japan-pp-mcp ./cmd/halal-gourmet-japan-pp-mcp

Register halal-gourmet-japan-pp-mcp with the MCP host. Keep the CLI sibling in the same directory, because mirrored tools call it. Relocation belongs in the host environment via HALAL_GOURMET_JAPAN_HOME; stdio has no listener or remote authentication surface.

Direct Use

Verify the binary, choose the narrow leaf command, inspect source results with --agent, and retain source URL, evidence scope and observation date in any answer. Describe reported facts and missing evidence without converting them into an assurance verdict.

Finish all concurrent inspections before local planning. Saved detail reads, plans and MCP SQL refuse a non-empty WAL or a database change during the read with cache_visibility_unavailable (CLI exit 10), rather than return an older checkpoint as current. A checkpointed but untruncated WAL can also trigger this conservative guard; close remaining database writers and retry. Returned facts retain their exact observed_at times. The framework's invalid --data-source value currently exits 1; domain input errors exit 2.

Readers and snapshot writers resolve symbolic links to one canonical database and verify selected-path identity. Databases with multiple hard links are rejected where the host exposes link-count metadata; use a database with one hard link. Keep database files in place until all writers close. Dry-run validates the same required inputs before source or snapshot work; standard framework learning can record command activity unless --no-learn is set.

Saved readers use private temporary immutable images copied from verified pinned descriptors, bounded at128 MiB and removed after each read. Larger cache files fail explicitly; use a smaller cache. Cache paths and resolved alias targets containing percent, question-mark or hash bytes are rejected before SQLite opening; choose a plain filesystem name.

The temporary-directory path and its resolved target also require plain filesystem names; use an ordinary TMPDIR path. Snapshot writers retain normal SQLite transaction/WAL semantics. External same-user file replacement during writing is unsupported; detected retargeting returns an explicit error.

© mvanhorn, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in cli-skills/pp-halal-gourmet-japan of mvanhorn/printing-press-library.

Open the folder on GitHubat commit d9a1696

Compare with similar skills

Pp Halal Gourmet Japan 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.

Pp Halal Gourmet Japan compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Pp Halal Gourmet Japan this skillmvanhorn/printing-press-library2.1k—~3.7kAutomated safety check: NotesApache-2.0
Food Orderingasgeirtj/system_prompts_leaks69k—~1.4kAutomated safety check: PassCC0-1.0
Geo Comparesickn33/agentic-awesome-skills47k1 repos~2.7kAutomated safety check: NotesMIT
Fda Food Safety Auditorsickn33/agentic-awesome-skills47k2 repos~759Automated safety check: PassMIT
Compare Python TypecheckersJetBrains/intellij-community21k—~617Automated safety check: PassCustom licence
Recipe Compare Sheet Tabsgoogleworkspace/cli31k—~182Automated safety check: PassApache-2.0

Similar skills

  • Food Ordering

    asgeirtj/system_prompts_leaks

    Prepare restaurant food orders for delivery or pickup; use for cart, checkout and tracking.

    69k GitHub stars~1.4k tokensUpdated yesterday
    Auto-check passed
  • Geo Compare

    sickn33/agentic-awesome-skills

    Monthly delta tracking and progress reporting for GEO clients.

    47k GitHub starsUsed in 1 repo~2.7k tokens
    Auto-check: notes
  • Fda Food Safety Auditor

    sickn33/agentic-awesome-skills

    Expert AI auditor for FDA Food Safety (FSMA), HACCP, and PCQI compliance.

    47k GitHub starsUsed in 2 repos~759 tokens
    Legal & ComplianceAuto-check passed
  • Compare Python Typecheckers

    JetBrains/intellij-community

    Official

    Compare Python type inference with ty, pyrefly, and basedpyright.

    21k GitHub stars~617 tokensUpdated today
    Auto-check passed
  • Recipe Compare Sheet Tabs

    googleworkspace/cli

    Read data from two tabs in a Google Sheet to compare and identify differences.

    31k GitHub stars~182 tokensUpdated 4 days ago
    Documents & OfficeAuto-check passed
  • Compare

    taishi-i/awesome-japanese-nlp-resources

    Compare several Japanese NLP libraries, models, or datasets for a keyword (a specific tool name, or a function/task like '形態素解析') across a handful of criteria chosen for that comparison, rendered as…

    1k GitHub stars~4.1k tokensUpdated 5 days ago
    AI & LLM EngineeringAuto-check: notes

More from mvanhorn/printing-press-library

All 506 skills in this repo
  • Agent Desktop

    mvanhorn/printing-press-library

    Desktop automation through the real Rust agent-desktop CLI, published in Printing Press through a small bridge.

    2.1k GitHub stars~2.3k tokensUpdated today
    Auto-check: notes
  • Gfonts

    mvanhorn/printing-press-library

    Search, browse, and download Google Fonts from the terminal via the gfonts CLI.

    2.1k GitHub stars~574 tokensUpdated today
    Auto-check passed
  • Pp 1688

    mvanhorn/printing-press-library

    The free, offline Trigger phrases: search 1688 for, find a factory on 1688 for, wholesale price on 1688 for, who is the cheapest supplier on 1688 for, compare 1688 suppliers for, use 1688, run 1688.

    2.1k GitHub stars~3k tokensUpdated today
    Auto-check: notes
  • Pp Activity Japan

    mvanhorn/printing-press-library

    Inspect known Activity Japan plan IDs or URLs, compare dated prices and sessions, check language-sitemap coverage, and hand off to canonical booking pages.

    2.1k GitHub stars~2k tokensUpdated today
    Auto-check: notes
  • Pp Adminbyrequest

    mvanhorn/printing-press-library

    Every Admin By Request portal action, plus a local SQLite mirror of audit, events, inventory and requests for ad-hoc...

    2.1k GitHub stars~3.3k tokensUpdated today
    Auto-check: notes
  • Pp Agent Capture

    mvanhorn/printing-press-library

    macOS screen capture, window recording, GIF conversion, and agent evidence bundles from the terminal.

    2.1k GitHub stars~1.6k tokensUpdated today
    Auto-check: notes

Questions about Pp Halal Gourmet Japan

What does Pp Halal Gourmet Japan do?

Compare explicit food and prayer evidence across Japan with source dates and honest unknowns. Pp Halal Gourmet Japan is an agent skill from mvanhorn/printing-press-library. Compare explicit food and prayer evidence across Japan with source dates and honest unknowns.

When should I use Pp Halal Gourmet Japan?

Pp Halal Gourmet Japan fits situations like: phrases: find halal condition evidence in Tokyo; compare halal certification and prayer space facts; check HGJ prayer-space facilities; what is missing from my Muslim travel shortlist.

How do I install Pp Halal Gourmet Japan in Claude Code?

Run `npx skills add mvanhorn/printing-press-library --skill pp-halal-gourmet-japan -a claude-code`. Or copy the skill folder (cli-skills/pp-halal-gourmet-japan in mvanhorn/printing-press-library) into .claude/skills/pp-halal-gourmet-japan in your project. Claude Code loads it when a task matches its description.

How do I install Pp Halal Gourmet Japan in Codex?

Run `npx skills add mvanhorn/printing-press-library --skill pp-halal-gourmet-japan -a codex`. Or copy the skill folder (cli-skills/pp-halal-gourmet-japan in mvanhorn/printing-press-library) into .agents/skills/pp-halal-gourmet-japan in your project. Codex loads it when a task matches its description.

Can I use Pp Halal Gourmet Japan in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add mvanhorn/printing-press-library --skill pp-halal-gourmet-japan -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/pp-halal-gourmet-japan, .gemini/skills/pp-halal-gourmet-japan, .github/skills/pp-halal-gourmet-japan and .opencode/skills/pp-halal-gourmet-japan in your project.

What does Pp Halal Gourmet Japan need to run?

Going by SKILL.md and its folder, Pp Halal Gourmet Japan needs the command-line tools its instructions call (go and npx). Our summary lists: Node.js. Its frontmatter pre-approves these tools: Read, Bash.

Does Pp Halal Gourmet Japan access the network?

SKILL.md contains no URLs. Its commands use npx, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Pp Halal Gourmet Japan safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Pp Halal Gourmet Japan use?

Pp Halal Gourmet Japan is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Pp Halal Gourmet Japan use?

About 3.7k tokens (SKILL.md is roughly 15k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Pp Halal Gourmet Japan?

Skills that share tags, products or a category with Pp Halal Gourmet Japan: Food Ordering (asgeirtj/system_prompts_leaks, 69k stars), Geo Compare (sickn33/agentic-awesome-skills, 47k stars), Fda Food Safety Auditor (sickn33/agentic-awesome-skills, 47k stars) and Compare Python Typecheckers (JetBrains/intellij-community, 21k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Pp Halal Gourmet Japan?

mvanhorn (a GitHub user) maintains it in mvanhorn/printing-press-library, which has 2,056 GitHub stars. The repository holds 506 skills in this directory. The repository was last updated on October 9, 2026.

Source: mvanhorn/printing-press-library on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.