- Home
- Skills
- Research & Analysis
- RailPulse Vision Operator
RailPulse Vision Operator
A local-first skill for checking RailPulse health, reading crowd data and tickets, and writing local reports.
Free
Works with the AI Agents you already use
RailPulse Vision Operator
Example session with this skill installed
Check my local RailPulse backend, summarize the latest crowd readings and tickets, and save an operations report. Use only data returned by the API, and clearly state any missing or uncertain information.
- Read your context and instructions
- Compiled the railpulse vision operator
The fixture contains two crowd readings for Demo Platform: sector D1 is marked WARNING at 9/12, and D2 is marked CRITICAL at 16/12. These are RailPulse status labels, not confirmation of an emergency. The fixture contains one OPEN hazard ticket, DEMO1234, in D1. Its age is calculated from the fixture timestamp. No passenger name, phone number, image path, or ticket description is included.
Sector Count / capacity Status Reading time
D1 9 / 12 WARNING 2026-11-12 10:00 UTC
D2 16 / 12 CRITICAL 2026-11-12 10:01 UTC
Ticket Location Category Status
DEMO1234 Demo Platform / D1 HAZARD OPEN
The local report includes the returned readings, ticket status and age, and retrieval time. It does not infer missing sectors or trends. The API does not preserve reliable synthetic-data provenance, and the backend has no authentication.
Next steps: Connect to an authorized local RailPulse backend and review all operational interpretations with a qualified human.
Connects securely to your tools. The creator never sees your data.
About this skill
RailPulse Vision Operator helps an AI agent query an already-running RailPulse installation. It can check backend health, retrieve the latest crowd-density readings, list tickets returned by the API, and write a local Markdown report. The helper uses Python’s standard library and does not require a Gemini key or paid service.
You must install and run RailPulse separately. This skill does not host the backend, access cameras, start detectors, or verify whether readings came from real video. The audited backend has no authentication, so use it only on a trusted local network. Reports omit ticket descriptions and direct passenger identifiers. This is an operational support and demonstration tool, not a certified safety or emergency-response system. Human operators must assess readings and decisions.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Research & Analysis.
Requires an active RailPulse backend. Read-only access only. No support for ticket modification, emergency dispatch, or public announcements. Base URL defaults to localhost.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
1 use
Times used to date
Free to use
No account required to browse
Trust & safety
Security scan
Security scan passed 5 days ago
- Free with an Agensi account
- Software
Python
Permissions
Allowed Hosts