ankitjh4ankitjh4/indic-ai-skills/skills/rapido/SKILL.md

rapido

Skill65 starsChanged 7 months agoMITView on GitHub

Rapido ride-booking API integration for India — location search, geocoding, fare estimates, ride booking, tracking, and wallet management. Reverse-engineered from Rapido PWA. Use when the user wants to search locations via Rapido, geocode Indian addresses, book a Rapido ride, check Rapido fares, or interact with the Rapido platform.

In this repository22 other files it gives its agents.
- bhagavad-gitaSkill
- cashfreeSkill
- covid-indiaSkill
- gurbaniSkill
- ifsc-apiSkill
- indian-constitutionSkill
- indian-newsSkill
- railradarSkill
- mutual-fundSkill
- namma-yatriSkill
- ondc-buyerSkill
- ondc-sellerSkill
- phonepeSkill
- pincodeSkill
- razorpaySkill
- sarvam-aiSkill
- shiprocketSkill
- thirukkuralSkill
- uber-indiaSkill
- vedic-astrologySkill
- vedic-textsSkill
- zohoSkill

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Distinctive:
Enter OTP: when prompted — receives JWT token and userId
line 32

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.

Files

SKILL.md

Rapido Ride Booking

API integration for Rapido — India's largest bike taxi service.

Status (March 2026): Location search and geocoding work. Fare estimates and booking return encoded binary due to a protobuf schema change — a new HAR capture is needed to restore full functionality.

Working Features

Location Search

# Autocomplete
bun scripts/rapido.ts autocomplete --query "Horamavu"

# Geocode place ID to coordinates
bun scripts/rapido.ts geocode --place-id "ChIJ99zGooERrjsRzoxiOwCEUhQ"

Authentication Flow

Generate OTP — bun scripts/rapido.ts auth --mobile "9876543210"
Enter OTP when prompted — receives JWT token and userId
Use token — all authenticated requests need header x-consumer-username: {userId}:

Full Command Reference

# Install dependencies
bun init -y && bun add axios

# Fare estimate (currently returns encoded response)
bun scripts/rapido.ts fare-estimate \
  --from-lat "13.0401" --from-lng "77.6635" \
  --to-lat "12.9756" --to-lng "77.6027"

# Book a ride
bun scripts/rapido.ts book \
  --from-lat "13.0401" --from-lng "77.6635" --from-name "Horamavu" \
  --to-lat "12.9756" --to-lng "77.6027" --to-name "Church Street"

# Track / cancel / wallet
bun scripts/rapido.ts track --order-id "ORDER_ID"
bun scripts/rapido.ts cancel --order-id "ORDER_ID"
bun scripts/rapido.ts wallet

Key API Endpoints

Endpoint	Auth	Purpose
`POST /unup/autocomplete/location`	No	Location search
`POST /unup/location/geocode/placeId`	No	Geocode place ID
`POST /auth/generateOtp`	No	OTP generation
`POST /auth/verifyOtp`	No	OTP verification
`POST /pricing/getFareEstimate`	Yes	Fare estimates
`POST /order/book`	Yes	Book ride
`POST /order/cancel`	Yes	Cancel ride
`POST /location/riderEta`	Yes	Live tracking
`POST /wallet/balance`	Yes	Wallet balance

Base URL: https://m.rapido.bike/pwa/api

SDK

See scripts/rapido.ts for the complete TypeScript SDK covering authentication, fare estimation, booking, tracking, cancellation, and wallet management.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

It worked
Partly
It didn't

What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free