skills.rest
Citrus-bit
Citrus-bitCOMMUNITY
Explore all skills by this author →
GitHub

claude-to-medrix_flow

Send messages to MedrixFlow agents over HTTP to manage conversation threads.

135|12|Updated Mar 30, 2026
Search Tags:#langgraph#file-upload#http-api#agent-orchestration#thread-management#sse-streaming#medrixflow
One-click install
npx skills add https://github.com/Citrus-bit/medrix-flow --skill claude-to-medrix-flow
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: claude-to-medrix_flow
Source: https://github.com/Citrus-bit/medrix-flow/tree/main/skills/public/claude-to-medrixflow
Command: npx skills add https://github.com/Citrus-bit/medrix-flow --skill claude-to-medrix-flow

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires curl, python3, and includes scripts (resource) components.

What problem does it solve?

MedrixFlow integrations require manual HTTP calls and SSE parsing to start agent threads, stream responses, upload files, and manage memory; this Skill packages those operations into clear helper scripts and API guidance so developers can reliably interact with a running MedrixFlow instance.

Core Features & Use Cases

  • Health and status checks: validate service availability before sending requests to avoid failed runs.
  • Create and stream threads: start a LangGraph thread and stream run events (values, messages-tuple) to collect incremental AI outputs and metadata.
  • Thread lifecycle and asset management: continue conversations with existing thread IDs, upload documents to threads, list models/skills/agents, and convert virtual artifact paths into downloadable URLs.
  • Use Case: Run a pro-mode research task that uploads reference files, invokes subagents for specialized analysis, and retrieves generated artifacts from the thread outputs.

Quick Start

Use the chat.sh helper to send a question to MedrixFlow which will create a thread, stream the run, and print the final agent response.

Frequently Asked Questions about claude-to-medrix_flow

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I stream LangGraph agent responses from an HTTP API?▼

You can stream LangGraph agent responses by sending HTTP requests to the MedrixFlow gateway and parsing the Server-Sent Events (SSE) output. This Skill provides helper scripts that connect to configurable endpoints to stream incremental run events and collect AI outputs.

What is the best way to manage conversation threads for AI agents over an HTTP API?▼

Managing conversation threads over an HTTP API involves creating thread IDs, sending follow-up messages, and retrieving artifacts. This Skill packages these thread lifecycle operations into clear scripts for reliable interaction with a running MedrixFlow instance.

Can I upload files to an existing LangGraph thread via HTTP requests?▼

Yes, you can upload files to an existing LangGraph thread via HTTP requests. This Skill supports thread asset management, allowing you to upload documents to threads and convert virtual artifact paths into downloadable URLs for analysis workflows.

Does this Skill require Python to parse SSE streaming outputs?▼

Yes, parsing SSE streaming outputs requires Python 3 and curl. The Skill includes helper scripts written in Python that handle SSE stream parsing and artifact URL resolution to interact with the MedrixFlow HTTP API endpoints.

How do I check if a MedrixFlow service is available before starting an agent run?▼

To check if a MedrixFlow service is available, perform a health and status check via the HTTP API before sending requests. This validates service availability to avoid failed runs and ensures the gateway and LangGraph endpoints are reachable.

Related Skills

Explore More Software Engineering Skills→
zhayujiezhayujie
46.4k

openai-image-vision

Analyze images via OpenAI Vision API using Bash and curl.

Community
Intermediate
kendreadityakendreaditya

gemini-convo

Parse Gemini conversation JSON files into readable Markdown transcripts.

Community
Intermediate
anukkrit149anukkrit149

deep-agents-core

Build deep agent applications with structured planning, subagent delegation, and persistent memory.

Community
Advanced
syusamasyusama
4

claude-to-deerflow

Send messages and manage threads via the DeerFlow HTTP API.

Community
Advanced