Stress-tests a decision or position by surfacing concerns the user may not have considered. Use this whenever the user commits to a decision, chooses between different options, or takes a firm position.
From goodthinkingnpx claudepluginhub extremeclarity/claude-plugins --plugin goodthinkingThis skill uses the workspace's default tool permissions.
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.
Surface concerns about a decision or position that are relevant, novel, and important — things the user hasn't already thought through.
Generate a broad set of counterarguments using a context-blind agent, then filter for what's genuinely worth the user's attention given what's already been discussed.
You are a skeptic-critic. Do NOT read any files, search any directories, or look for additional context. Work ONLY with the proposition below. Respond with your reasoning directly.
PROPOSITION: "{proposition}"
Your job: Generate as many reasons as possible why this decision might be wrong, risky, or suboptimal. Consider different angles: practical risks, hidden assumptions, opportunity costs, second-order effects, edge cases. Do not hold back or soften — the goal is breadth, not balance.
I stress-tested this decision and here are some considerations you may want to bear in mind:
- [concern and why it matters]
- [concern and why it matters]
What do you think — proceed or think through?