pp-rappi
The first agent-native CLI for Rappi Mexico — read-only catalog browsing with offline SQLite snapshots, cross-city... Trigger phrases: `find restaurants in Mexico City`, `rappi sushi roma norte`, `what's new on rappi this week`, `top rated burgers in CDMX`, `pharmacy near supermarket guadalajara`, `use rappi`, `run rappi`.
What this skill does
<!-- GENERATED FILE — DO NOT EDIT.
This file is a verbatim mirror of library/food-and-dining/rappi/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/". -->
# Rappi (Mexico) — Printing Press CLI
## Prerequisites: Install the CLI
This skill drives the `rappi-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 `$HOME/.local/bin` on macOS/Linux and `%LOCALAPPDATA%\Programs\PrintingPress\bin` on Windows:
```bash
npx -y @mvanhorn/printing-press-library install rappi --cli-only
```
2. Verify: `rappi-pp-cli --version`
3. Ensure the reported install directory is on `$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 1.26.3 or newer):
```bash
go install github.com/mvanhorn/printing-press-library/library/food-and-dining/rappi/cmd/rappi-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.
## When to Use This CLI
Reach for rappi-pp-cli when a user or agent needs Rappi Mexico catalog data in a structured, repeatable, proxy-free shape: discovering restaurants by city or category, comparing store coverage across CDMX/GDL/MTY, snapshotting a neighborhood's catalog to track newcomers and closures, or finding restaurants open at a non-current time. Do not use this CLI for ordering, cart, payment, or account flows — it is read-only by design.
## When Not to Use This CLI
Do not activate this CLI for requests that require creating, updating, deleting, publishing, commenting, upvoting, inviting, ordering, sending messages, booking, purchasing, or changing remote state. This printed CLI exposes read-only commands for inspection, export, sync, and analysis.
## Unique Capabilities
These capabilities aren't available in any other tool for this API.
### Local state that compounds
- **`restaurants diff`** — See newcomers and closures in any city + cuisine between two snapshots — answers "what's new in Roma Norte sushi this week" in one command.
_Pick this over a raw list when the user asks 'what's new' — the diff is the answer; you don't have to compute it._
```bash
rappi-pp-cli restaurants diff --city ciudad-de-mexico --category sushi --since 2026-04-01 --agent
```
- **`restaurants top`** — Top-rated restaurants with both a minimum rating AND a minimum review-count floor — the listicle-grade filter Rappi UI hides.
_Reach for this when a user asks 'best burgers in Polanco' — it weeds out new restaurants with three perfect ratings._
```bash
rappi-pp-cli restaurants top --city ciudad-de-mexico --category hamburguesas --min-rating 4.5 --min-reviews 100 --limit 10 --agent
```
- **`stores coverage`** — Cross-city, cross-store-type coverage matrix (CDMX × markets × pharmacies × liquor × express, all in one table) for the cities you sync.
_Best command for retail analysts asking 'where is Rappi expanding'; one query gives the whole MX picture._
```bash
rappi-pp-cli stores coverage --cities ciudad-de-mexico,guadalajara,monterrey --agent
```
- **`stores coverage-diff`** — Delta-vs-last-snapshot of the (city, store_type) coverage matrix — see store openings and store-type expansions over time.
_Pair with weekly sync to spot expansion trends; agents can flag 'new pharmacy zone added in GDL'._
```bash
rappi-pp-cli stores coverage-diff --since 2026-04-01 --agent
```
- **`restaurants by-neighborhood`** — Group restaurants by neighborhood within a city (Polanco vs Condesa vs Roma Norte) and rank by count or top-rated per neighborhood.
_When the question is 'which neighborhood has the most sushi options' or 'top-rated pizza per neighborhood' — this is the answer._
```bash
rappi-pp-cli restaurants by-neighborhood --city ciudad-de-mexico --category pizza --agent
```
- **`restaurants multi-category`** — Restaurants listed under two or more cuisine categories — surfaces fusion places and mis-categorized spots in one query.
_Pick this when a user wants 'fusion sushi-mexicana' or to disambiguate a chain with multiple cuisine listings._
```bash
rappi-pp-cli restaurants multi-category --city ciudad-de-mexico --agent
```
- **`restaurants brand`** — Find every city × category where a restaurant brand (e.g., "Sushi Itto") appears in the synced catalog.
_Reach for this on chain-coverage questions and multi-city expansion analysis._
```bash
rappi-pp-cli restaurants brand --name "Sushi Itto" --agent
```
### Agent-native plumbing
- **`restaurants open`** — Restaurants open at an arbitrary local time (e.g., "23:30 on Sunday") parsed from schema.org openingHours — beyond Rappi's "open now" view.
_Use this for late-night-eat queries and Sunday-morning planning where the live Rappi view is misleading._
```bash
rappi-pp-cli restaurants open --city ciudad-de-mexico --at "23:30" --category sushi --agent
```
- **`restaurants near`** — Restaurants within a Haversine radius of a lat/lng with optional category filter — sorted by distance.
_Best for proximity questions when the user has coordinates (address geocoded externally) and needs a precise radius._
```bash
rappi-pp-cli restaurants near --lat 19.4216 --lng -99.1700 --radius-km 2 --category tacos --agent
```
- **`stores adjacency`** — Stores of type A within a Haversine radius of stores of type B (e.g., pharmacies within 1km of supermarkets) — for concierge-style "one-stop trip" planning.
_Concierge agents picking a single trip route should reach for this over two independent radius queries. Requires `--fetch-detail` because list pages do not include store coordinates._
```bash
rappi-pp-cli stores adjacency --type farmatodo --within-km 1 --of-type market --city ciudad-de-mexico --fetch-detail --agent
```
## Discovery Signals
This CLI was generated with browser-observed traffic context.
- Capture coverage: 10 API entries from 11 total network entries
## Command Reference
**catalog** — Alphabetized product catalog index
- `rappi-pp-cli catalog` — Browse the product catalog indexed by initial letter and page number
**promotions** — Public promotions and active campaigns
- `rappi-pp-cli promotions` — Public promotions landing page
**restaurants** — Restaurant catalog browsing via SSR list and detail pages
- `rappi-pp-cli restaurants get` — Fetch the restaurant detail page (name, cuisine, address, hours, geo, rating)
- `rappi-pp-cli restaurants list-category` — List restaurants in a city filtered by cuisine category (hamburguesas, pizza, sushi, tacos, etc.)
- `rappi-pp-cli restaurants list-city` — List restaurants in a Mexican city (e.g. ciudad-de-mexico, guadalajara, monterrey)
**stores** — Supermarket, pharmacy, liquor, and convenience store catalog
- `rappi-pp-cli stores get` — Fetch a store detail page (name, type, address, branding)
- `rappi-pp-cli stores list-by-type` — List stores by type (market for supermarkets, farmatodo for pharmacy, liquor, express, rappimall-parent)
### Finding the right command
When you know what you want to do but not which command does it, ask the CLI directly:
```bash
rappi-pp-cli which "<capability in your own words>"
```
`which` resolves a natural-language capability query to the best matching command from this CLI's curated feature index. Exit code `0` means at least one match; exit code `2` means no confident match — fall back to `--help` or use a narrower query.
## Recipes
### Weekly newcomers in a neighborhood
```bash
rappi-pp-cli restaurants diff --city ciudad-de-mexico --category sRelated in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.