feature-run

Name: feature-run
Availability: InStock
Author: Lukin

Automate unattended batch processing of pending tasks with structured result parsing.

247|20|Updated Nov 28, 2025

Search Tags:#automation #software engineering #task management #feature development #AI agent #batch processing #unattended

Ready to run

npx skills add https://github.com/mylukin/agent-foreman --skill feature-run

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: feature-run
Source: https://github.com/mylukin/agent-foreman/tree/main/plugins/agent-foreman/skills/feature-run
Command: npx skills add https://github.com/mylukin/agent-foreman --skill feature-run

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

AI agents often get stuck or require constant supervision when tackling multiple tasks. This Skill automates the entire backlog, ensuring continuous progress without human intervention.

Core Features & Use Cases

Unattended Batch Processing: Automatically processes all pending features in a loop until completion.
Autonomous Decision-Making: Makes decisions, handles errors, and continues without asking questions, even on failures.
Single Feature Mode: Can also focus on and complete a specific feature if provided.
Use Case: You've defined a project goal with 20 features. Use this Skill to let the AI agent work through all of them, marking progress and handling issues autonomously, so you can focus on other tasks.

Quick Start

Run all pending features automatically.

Frequently Asked Questions about feature-run

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

FAQPage Schema

How do I automate batch processing of multiple pending features without supervision?▼

Batch processing automates running all pending features in sequence through a complete workflow loop. This Skill processes your entire feature backlog continuously, making autonomous decisions and handling errors without requiring human intervention or questions, so progress continues unattended until all tasks complete.

Can I run a specific feature task instead of processing all pending features?▼

Yes, single feature mode lets you focus on and complete one specific task by providing its task ID. The Skill applies the same autonomous workflow—next, implement, check, done—to that individual feature, handling errors and verification independently.

What does the unattended mode do when errors occur?▼

Unattended mode handles failures autonomously without pausing or asking for input. The Skill continues processing remaining tasks, logs structured results including task_id, status, and verification outcome, and completes the entire workflow cycle regardless of individual task failures.

How do I know which tasks completed and what files were modified?▼

The Skill outputs structured result parsing for each task: task_id, status (pass or fail), verification_passed (boolean), files_modified (list), and notes (summary). You review the final report to see which features succeeded, what code changed, and whether verification passed.

What workflow sequence does this Skill enforce for each task?▼

The Skill enforces a strict four-step sequence: next (identify task), implement (write code), check (verify results), done (mark complete). This CLI-only workflow ensures consistent progress through your feature backlog with no deviation or manual approval gates.

Can I use this Skill to clear a backlog of 20+ features automatically?▼

Yes, unattended batch processing is designed exactly for this use case. Define your project goals and features, then run the Skill to let the AI agent work through your entire backlog autonomously, handling decisions and issues so you focus on other priorities.