Ensures problem-first framing before solutioning. Use when defining work, discussing features, handling requests that sound like solutions, or when someone says "we should add" or "let's build".
From genienpx claudepluginhub elmmly/genie-team --plugin genieThis skill is limited to using the following tools:
Designs and optimizes AI agent action spaces, tool definitions, observation formats, error recovery, and context for higher task completion rates.
Enables AI agents to execute x402 payments with per-task budgets, spending controls, and non-custodial wallets via MCP tools. Use when agents pay for APIs, services, or other agents.
Compares coding agents like Claude Code and Aider on custom YAML-defined codebase tasks using git worktrees, measuring pass rate, cost, time, and consistency.
Reframe solution-loaded requests as problems before proceeding.
"What is true?" before "What should we do?"
| Input Pattern | Response |
|---|---|
| "We should add caching" | "What performance problems are users experiencing?" |
| "Let's build a dashboard" | "What decisions do users need to make? What data do they need?" |
| "Add a button for X" | "What task are users trying to accomplish?" |
| "We need microservices" | "What scaling or development problems are we facing?" |
When the request involves users, apply Jobs-to-be-Done:
"When [situation], [user] wants to [motivation] so they can [outcome]."
Example:
When reframing, structure as:
## Original Request
[What was asked]
## Reframed Problem
[Problem-focused version]
## Assumptions to Validate
- [Assumption 1]
- [Assumption 2]
## Questions to Answer
- [Question 1]
- [Question 2]
## Suggested Next Step
[Discovery, clarification, or proceed if problem is clear]