06-next

Recommend the next Compound Engineering skill from workflow artifacts and session history.

29|2|Updated Apr 17, 2026
One-click install
npx skills add https://github.com/leing2021/super-pi --skill 06-next
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: 06-next
Source: https://github.com/leing2021/super-pi/tree/main/skills/06-next
Command: npx skills add https://github.com/leing2021/super-pi --skill 06-next

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

It eliminates decision paralysis by inspecting your existing workflow artifacts and recommending the single best next skill to run in the Compound Engineering loop.

Core Features & Use Cases

  • Workflow-state inspection: Uses the workflow_state tool to read the current project runtime and artifact situation before deciding.
  • History-aware guidance: Uses session_history to avoid repeating already-completed phases.
  • Deterministic next-skill output: Recommends exactly one next skill, with a clear, short reason and an optional verbose full status report.
  • Context-first recommendation logic: Applies context-health and transition signals before using fallback artifact-count rules.

Quick Start

Ask for the next action by telling your agent: what should I do next, and it will suggest exactly one /skill:<id> based on the current artifacts.

Frequently Asked Questions about 06-next

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

FAQPage Schema
How do I decide what workflow step to run next in my project?

To determine the next workflow step, inspect existing project artifacts and runtime context to recommend a single best action. This approach prevents decision paralysis by analyzing current phase health and suggesting exactly one relevant skill to execute next.

Can I get a project status report with phase and health assessment automatically?

Yes, you can generate a project status report with phase and health assessment by requesting a full status update. The system analyzes your workflow artifacts and runtime context to provide a verbose report alongside a deterministic next-skill recommendation.

How does context-first priority logic work for workflow recommendations?

Context-first priority logic evaluates workflow state and health transition signals before applying fallback artifact-count rules. This ensures recommendations are driven by actual runtime context and current project phase rather than simple artifact quantities.

Does the next-step recommendation avoid repeating completed workflow phases?

Yes, next-step recommendations avoid repeating completed phases by using session history for disambiguation. This history-aware guidance checks previously executed steps to ensure the suggested action moves the workflow forward without duplication.

What are the limitations of using artifact inspection for workflow state analysis?

Artifact inspection for workflow state analysis is limited when context-health and transition signals are absent, forcing reliance on fallback artifact-count rules. It only outputs a recommendation without executing the skill, requiring manual user action to proceed.