sj-loop

Generates stateful loop prompts with verifiable stop conditions for AI-assisted development tasks.

1|Updated May 12, 2026
One-click install
npx skills add https://github.com/s0613/S-skills --skill sj-loop
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: sj-loop
Source: https://github.com/s0613/S-skills/tree/main/skills/sj-loop
Command: npx skills add https://github.com/s0613/S-skills --skill sj-loop

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Manually repeating the same AI-assisted development tasks across sessions is time-consuming and error-prone, with no consistent way to track progress, enforce safety rules, or stop when predefined goals are met.

Core Features & Use Cases

  • Structured Loop Prompts: Generates reusable loop prompts with machine-verifiable stop conditions, eliminating vague "keep trying until it works" instructions.
  • Persistent State Tracking: Saves iteration progress, best results, and next steps to a state file so loops can resume seamlessly across sessions.
  • Flexible Execution Modes: Supports dry runs for validation, in-session repeated execution, and cloud-scheduled runs for unattended overnight or recurring work.
  • Built-in Safety Guardrails: Enforces human approval gates for high-risk actions like PR merges or production deployments, and prevents loops from modifying critical project files or self-modifying their own prompts.
  • Use Case: A developer can create a loop to automatically fix failing unit tests, track the highest test score across iterations, and stop only when the full test suite passes with zero errors, without manual intervention for each run.

Quick Start

Use the sj-loop skill to create a loop that fixes all failing unit tests in your project and stops automatically when the test suite passes with no errors.

Frequently Asked Questions about sj-loop

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

FAQPage Schema
How do I automate recurring AI tasks to stop automatically when a goal is met?

To automate recurring AI tasks, you can use structured loop prompts with machine-verifiable stop conditions, ensuring the workflow halts automatically once predefined goals are met. This eliminates vague manual checks and provides consistent execution across sessions.

How does stateful workflow automation resume progress across different sessions?

Stateful workflow automation resumes progress by persisting iteration data, best results, and next steps to a disk-based state file. This allows the loop to seamlessly resume execution from its last saved state without losing context between sessions.

Can I run loop automation unattended overnight using cloud-scheduled execution?

Yes, you can run loop automation unattended using cloud-scheduled execution modes. This allows repetitive development workflows to operate overnight, while built-in safety guardrails enforce human approval gates for any high-risk actions like production deployments.

What are the best ways to add human-in-the-loop guardrails for test remediation automation?

The best way to add human-in-the-loop guardrails is to enforce approval gates for high-risk actions and prevent the automation from modifying critical project files. This ensures test remediation workflows remain safe and require human intervention before merging code.

Does dry run execution support validating stateful workflows before scheduled execution?

Yes, dry run execution supports validating stateful workflows before scheduled execution. It allows you to verify the loop automation logic and stop conditions without making actual changes, ensuring safe and accurate unattended runs later.

Why does manually repeating AI-assisted development tasks fail across multiple sessions?

Manually repeating AI-assisted development tasks fails because it lacks persistent state tracking and consistent safety enforcement. Without structured loop prompts, manual execution becomes error-prone and loses verifiable progress data across different sessions.