agent-endpoint

Expose vCRO run intelligence through parameterized API endpoints.

Updated Mar 31, 2026
One-click install
npx skills add https://github.com/kamilseghrouchni/vcro-sourcing --skill agent-endpoint
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-endpoint
Source: https://github.com/kamilseghrouchni/vcro-sourcing/tree/main/.claude/skills/agent-endpoint
Command: npx skills add https://github.com/kamilseghrouchni/vcro-sourcing --skill agent-endpoint

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

After a vCRO pipeline run completes, the intelligence sits as JSON artifacts on disk. This skill defines the API that serves it.

Core Features & Use Cases

  • GET /api/runs → list available runs
  • GET /api/schema?run_id=X → dynamic parameter schema for run X
  • POST /api/query → parameterized query using run-specific params
  • Agent discovery flow: GET/POST interactions between external agents and vCRO API to retrieve and query run intelligence

Quick Start

Deploy the agent-facing API and start serving vCRO run intelligence by exposing GET /api/runs, GET /api/schema, and POST /api/query.

Frequently Asked Questions about agent-endpoint

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

FAQPage Schema
How do I expose vCRO run intelligence to external agents via an API?

You expose vCRO run intelligence by deploying an agent-facing API that serves JSON artifacts from disk, using endpoints like GET /api/runs, GET /api/schema, and POST /api/query for external agents to retrieve and query run data.

What is a dynamic API endpoint schema for run intelligence?

A dynamic API endpoint schema adapts per vCRO pipeline run, providing run-specific parameter definitions. It returns a self-describing _endpoint payload so external agents can discover exact query parameters for a given run.

Can I use custom query parameters when retrieving vCRO run results?

No, the API query interface enforces a fixed parameter surface consisting of run_id, top_k, include, and format. External agents must use these exact parameters to query run intelligence via the POST /api/query endpoint.

How do external agents discover available vCRO runs and query schemas?

External agents discover available runs by calling GET /api/runs to list completed pipelines, then retrieve the dynamic parameter schema for a specific run using GET /api/schema with the run_id parameter before querying.

What's the best way to serve vCRO pipeline artifacts to external agents?

The best way to serve pipeline artifacts is using a parameterized API that adapts per run, exposing a fixed query surface and returning a self-describing _endpoint payload for agent discovery and retrieval.