autonomous-loops

Automate Gemini CLI into autonomous loop workflows with explicit stop conditions.

Updated Sep 13, 2025
One-click install
npx skills add https://github.com/llmh333/employee_management_spring --skill autonomous-loops-llmh333
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: autonomous-loops
Source: https://github.com/llmh333/employee_management_spring/tree/main/.gemini/skills/autonomous-loops
Command: npx skills add https://github.com/llmh333/employee_management_spring --skill autonomous-loops-llmh333

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It solves the challenge of turning interactive Gemini work into reliable, repeatable autonomous development and orchestration loops without losing context or control.

Core Features & Use Cases

  • Sequential pipeline loops: Chain non-interactive gemini -p steps for daily development, with isolated context per step and clear failure behavior.
  • Persistent interactive REPL: Use a session-aware loop that maintains conversation history across turns by appending to a session file.
  • Parallel, spec-driven agent waves: Orchestrate an “orchestrator + sub-agents” system that generates multiple unique outputs from a spec with assigned creative directions.
  • Continuous PR iteration loop: Automatically create PRs, wait for CI, recover from failures, and merge repeatedly with cost/time/run limits.
  • Add-on cleanup (“De-Sloppify”) pattern: Improve quality by running a dedicated cleanup/refactor pass after implementation rather than relying on negative instructions.
  • RFC-driven DAG orchestration: Decompose an RFC into dependency work units, run tiered quality pipelines per unit, and land changes via a merge queue with eviction recovery.

Quick Start

Use the autonomous-loops skill to run a continuous PR workflow by telling an AI to create, push, and merge iterative changes until CI passes or your configured limits are reached.

Frequently Asked Questions about autonomous-loops

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

FAQPage Schema
How do I automate Gemini CLI into autonomous loop workflows?

Automating Gemini CLI into autonomous loop workflows involves orchestrating sequential pipelines, persistent REPL sessions, and parallel spec-driven agent waves to reduce manual iteration. This ensures reliable ongoing development with context persistence across iterations.

What is a continuous PR iteration loop and how does it work with CI CD?

A continuous PR iteration loop automatically creates pull requests, waits for CI CD validation, recovers from failures, and merges repeatedly. It operates within explicit stop conditions like max runs, max cost, or completion signals.

Can I run parallel spec-driven agent waves with an orchestrator and sub-agents?

Yes, you can orchestrate parallel spec-driven agent waves by using an orchestrator and sub-agents system that generates multiple unique outputs from a spec with assigned creative directions. This enables deterministic execution where needed.

How do I maintain conversation history across turns in a persistent interactive REPL?

To maintain conversation history across turns in a persistent interactive REPL, use a session-aware loop that appends to a session file. This preserves context persistence across iterations for reliable ongoing development.

How do I break down an RFC into dependency work units for DAG orchestration?

RFC-driven DAG orchestration decomposes an RFC into dependency work units, runs tiered quality pipelines per unit, and lands changes via a merge queue with eviction recovery. This structures complex development into manageable automated phases.

What are the stop conditions for controlling autonomous agent orchestration loops?

Autonomous agent orchestration loops use explicit stop conditions like max runs, max cost, or completion signals to control execution. These limits prevent unbounded execution while ensuring deterministic behavior where needed.