360 Secure SkillHub
360 安全技能中心

Reality Check

核心功能:挖掘计划的显隐假设,逐一测试验证,评估可行性,输出viability评分(0-100)、关键缺陷、行动建议及1-3个下一步验证步骤。典型场景:计划看似美好却脆弱、用户盲目乐观无依据、决策存在重大下行风险时使用。输入需提供拟议计划/决策,可附带假设(无则自动提取),输出结构化评估结果助用户判断决策合理性。

mzfshark
mzfshark
热度 35.30
最近更新 2026-05-11 17:45:41
分类:数据依赖:纯提示词应用场景:市场分析 / 报告撰写 / 研究

安装技能

复制下面的话术发给你的 Agent,它会通过 secure-skills 检索并安装该技能。

执行命令安装此 skill: npx secure-skills-cli add reality-check
Metadata
name
reality-check
description
Prevent bad strategic decisions by surfacing assumptions, testing feasibility, and exposing critical flaws before execution.
metadata
{"author":"Morpheus","version":"2.0.0","owner":"Morpheus Agent","category":"validation"}

SKILL: reality-check

Purpose

Prevent bad strategic decisions by forcing assumptions into the open, testing them, and ranking feasibility before commitment.

When to Use

  • A plan sounds good but may be fragile or unrealistic
  • The user is optimistic without evidence
  • A decision has meaningful downside risk

Inputs

  • idea (required): the proposed plan/decision
  • assumptions (optional): stated assumptions; if missing, Morpheus must extract them

Steps

  1. List assumptions (explicit + implicit).
  2. For each assumption:
    • define what would make it true/false
    • define the cheapest test/experiment
    • define failure impact if wrong
  3. Identify the weakest links (highest impact × lowest evidence).
  4. Evaluate feasibility:
    • resources/time
    • constraints/governance
    • reversibility
  5. Produce:
    • viability score (0–100)
    • critical flaws
    • recommendation (proceed / revise / stop)
  6. Provide the next 1–3 validation steps.

Validation

  • Assumptions are explicit and testable.
  • Claims are labeled as evidence vs hypothesis.
  • Recommendation follows the evidence, not optimism.

Output

  • viability_score (0–100)
  • critical_flaws
  • recommendation
  • next_steps

Safety Rules

  • Prioritize truth over optimism.
  • No financial guarantees or claims of certainty without evidence.

Example

Idea: “Launch a new token feature in 48h.” Output: viability 35/100; critical flaw: no governance approval + no test coverage; next steps: scope reduction + emergency review + paper validation.