flow-next-prospect

Generate ranked candidate ideas grounded in the repository for Flow-next planning.

674|52|Updated Dec 26, 2025
One-click install
npx skills add https://github.com/gmickel/flow-next --skill flow-next-prospect
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: flow-next-prospect
Source: https://github.com/gmickel/flow-next/tree/main/plugins/flow-next/codex/skills/flow-next-prospect
Command: npx skills add https://github.com/gmickel/flow-next --skill flow-next-prospect

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Flow-next:prospect generates upstream-of-plan ideas grounded in the repository to surface actionable work items before planning phases.

Core Features & Use Cases

  • Grounding snapshot-driven idea generation that respects the repository state.
  • Divergent generation using defined personas to explore a wide solution space.
  • Phase 3 critique, Phase 4 ranking, and Phase 5 artifact writing to deliver a decision-ready Prospect artifact.

Quick Start

Invoke /flow-next:prospect to generate a ranked set of candidate ideas for the repo and persist them as an artifact.

Frequently Asked Questions about flow-next-prospect

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

FAQPage Schema
How do I generate ranked candidate ideas for roadmap planning from a codebase?

Idea generation for roadmap planning uses divergent generation and grounding snapshots to produce ranked candidate records from your repository. It applies personas to explore the solution space and outputs decision-ready artifacts.

When do I need upstream-of-plan idea generation for software engineering workflows?

Upstream-of-plan idea generation is needed before entering planning phases to surface actionable work items. It discovers candidate epics and governs next steps by grounding generation in the current repository state.

What is the best way to discover candidate epics grounded in a repository snapshot?

Discovering candidate epics grounded in a repository snapshot requires applying defined personas for divergent generation, followed by critique and ranking. This structured process delivers a decision-ready Prospect artifact for Phase 3 workflows.

Does idea generation work without dependencies to produce a decision-ready artifact?

Yes, idea generation operates dependency-free to produce a decision-ready Prospect artifact. It leverages grounding snapshot awareness to respect the repository state and applies structured candidate records for critique.

How do I persist ranked ideas as an artifact after generating them from a codebase?

To persist ranked ideas as an artifact, the generation process writes structured candidate records through Phase 5 artifact writing. This follows divergent generation, Phase 3 critique, and Phase 4 ranking to finalize the output.

What are the limitations of using divergent generation for codebase idea generation?

Divergent generation for codebase idea generation is limited by its reliance on grounding snapshot awareness; if the repository state is outdated, candidate records may not accurately reflect actionable work items for roadmap planning.