kli-workflow

Coordinate KLI framework development across research, planning, implementation, and reflection phases.

26|3|Updated Jul 3, 2026

Search Tags:#workflow #task management #ai development #development lifecycle #orchestration #kli

Ready to run

npx skills add https://github.com/kleisli-io/kli --skill kli-workflow

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: kli-workflow
Source: https://github.com/kleisli-io/kli/tree/main/plugin/skills/kli-workflow
Command: npx skills add https://github.com/kleisli-io/kli --skill kli-workflow

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill streamlines the KLI development lifecycle by coordinating the distinct phases of research, planning, implementation, and reflection, ensuring a structured and efficient workflow.

Core Features & Use Cases

Phase Coordination: Manages transitions between research, planning, implementation, and reflection stages.
Skill Loading: Automatically loads phase-specific skills (e.g., kli-research, kli-planning) for detailed guidance.
Observation-Driven Learning: Facilitates knowledge capture and playbook evolution through an event stream.
Use Case: When starting a new feature, use this Skill to guide the process from initial research and planning through coding and final reflection, ensuring all steps are covered and learnings are captured.

Quick Start

Use the kli-workflow skill to begin the research phase for a new feature.

Frequently Asked Questions about kli-workflow

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

FAQPage Schema

How do I orchestrate AI development lifecycle phases for research, planning, implementation, and reflection?▼

AI development lifecycle orchestration coordinates transitions between research, planning, implementation, and reflection phases while automatically loading phase-specific skills. It streamlines the workflow by ensuring structured progression through each development stage.

What is observation-driven learning for development lifecycle playbooks?▼

Observation-driven learning captures knowledge through an event stream during task execution, facilitating continuous playbook evolution. It processes event streams to improve development workflows based on real implementation observations.

Do I need a CLI and MCP server for task graph management and event stream processing?▼

Task graph management and event stream processing require a CLI and MCP server to coordinate the development lifecycle. These dependencies enable phase transitions, skill loading, and observation-driven learning loop functionality.

How do I start the research phase for a new feature using a structured workflow?▼

Starting the research phase for a new feature begins the lifecycle orchestration process, which then guides progression through planning, implementation, and reflection. The workflow automatically loads phase-specific skills for detailed guidance at each stage.

What's the best way to manage transitions between research and implementation phases in AI development?▼

Managing transitions between research and implementation phases uses lifecycle orchestration to coordinate stage changes and load appropriate phase-specific skills. This ensures all development steps are covered and learnings are captured for continuous improvement.

Can I use task management orchestration to capture and evolve development playbooks automatically?▼

Task management orchestration captures knowledge and evolves playbooks automatically through an observation-driven learning loop. It leverages event stream processing to facilitate continuous improvement of development playbooks across lifecycle phases.