serve

Expose montaj project lifecycle and step execution over a local HTTP API.

25|10|Updated Apr 3, 2026
One-click install
npx skills add https://github.com/theSamPadilla/montaj --skill serve-thesampadilla
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: serve
Source: https://github.com/theSamPadilla/montaj/tree/main/skills/serve
Command: npx skills add https://github.com/theSamPadilla/montaj --skill serve-thesampadilla

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Provides a local HTTP API that lets agents and local tooling control montaj project lifecycle and editing steps so automated agents can fetch pending projects, execute steps, log progress, and update project state without manual CLI interaction.

Core Features & Use Cases

  • Project CRUD: Endpoints to list pending projects, read and update project JSON, and create new run requests.
  • Step Execution: POST endpoints to invoke named steps (probe, trim, transcribe, etc.) with support for single and batch inputs and background execution for long-running ffmpeg or transcription tasks.
  • Operational Logging & SSE: Append human-readable status logs for UI streaming and mark project status transitions (pending → draft → final) to trigger live updates and rendering.
  • Use Case: An agent polls /api/projects?status=pending, runs per-clip steps in parallel, logs progress to /api/projects/{id}/log, updates project state, and triggers a render when editing is complete.

Quick Start

Use the serve skill to poll http://localhost:3000/api/projects?status=pending, run required steps via POST to /api/steps/:name, and append short status messages to /api/projects/{id}/log while the agent orchestrates the edit.

Frequently Asked Questions about serve

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

FAQPage Schema
How do I automate video editing workflows over a local HTTP API?

Automating video editing over a local HTTP API involves exposing project lifecycle and step execution endpoints so agents can poll pending projects, invoke steps like trim or transcribe, and append logs without manual CLI interaction.

What is the best way to integrate an agent with a local video editing pipeline?

Integrating an agent with a local video editing pipeline uses a local HTTP API on localhost:3000, allowing the orchestrator to fetch pending project JSON, execute named steps via POST requests, and update project state transitions like pending to final.

How do I run long-running ffmpeg or transcription tasks in the background for video editing?

Running long-running ffmpeg or transcription tasks in the background is supported via POST endpoints for step execution, allowing batch inputs and asynchronous processing while the agent continues polling project status and logging progress.

How does Server-Sent Events streaming work for video editing project logs?

Server-Sent Events streaming for video editing project logs works by appending human-readable status messages to a logging endpoint, which triggers live UI updates and allows agents to monitor operational progress and status transitions in real time.

Can I trigger video renders automatically using JSON payloads?

Triggering video renders automatically using JSON payloads is supported by updating project state to final via the local HTTP API, which signals the editing pipeline to initiate rendering and complete the automated agent workflow.