← 返回
未分类 中文

Market Thesis Challenger

Adversarial review skill for challenging an existing market thesis, morning brief, close review, regime call, or positioning note. Use when the user asks to...
对抗性审查技能,用于挑战现有市场论点,包括早间简报、收盘复盘、形势判断及持仓提示。当用户提出相关要求时使用。
luckycatl
未分类 clawhub v1.0.0 1 版本 100000 Key: 无需
★ 0
Stars
📥 400
下载
💾 0
安装
1
版本
#latest

概述

Market Thesis Challenger

This skill does not generate the base market brief.

Its job is to attack an existing thesis.

Use it only after a base case already exists, whether from:

  • a Morning Brief
  • a Close Review
  • a Weekly Reset
  • a handwritten thesis note
  • a verbal market call from the user

Core purpose

The goal is not to be randomly contrarian.

The goal is to find the strongest serious objection to the current base case.

This skill should:

  • identify the weakest assumption in the thesis
  • surface missing events, proxies, or transmission links
  • check whether price action actually confirms the story
  • compare the current setup against the most relevant historical analogs
  • define what evidence would invalidate the base case fastest

This skill should not:

  • write a second full morning brief unless the user explicitly asks
  • manufacture a fake anti-consensus take just to sound smart
  • equal-weight both sides and end in mush
  • replace the human's final judgment

Operating mode

Treat the input thesis as the prosecution target.

You are the defense attorney for reality.

Always assume:

  • the base case may be partially right
  • your job is to find where it is most fragile
  • the most useful challenge is the one that changes sizing, confidence, or timing

Required output structure

Keep the challenge compressed and decision-relevant.

1. Strongest objection

One paragraph only.

State the single best reason the base case may be wrong.

2. Missing or underweighted factors

List 2-4 items max.

Each item should be one line only.

Prefer:

  • fresh events the base case omitted
  • missing proxy indicators
  • broken transmission links
  • crowding / positioning risk

3. Historical analog check

Name 1-2 analogs max.

For each analog, state:

  • what is similar
  • what is different
  • why that difference matters

Do not dump a history lesson.

Use analogs only when they sharpen the attack.

4. What would falsify the base case fastest

List the 2-4 most decisive signals.

These should be short, concrete, and near-term.

5. Final challenge verdict

Use one of these only:

  • Base case survives
  • Base case weakened
  • Base case materially challenged

Then add one sentence explaining whether sizing should stay the same, be reduced, or require re-checking.

Historical analog rule

Do not force historical analogs in every run.

Use them only when:

  • the current regime strongly resembles a prior episode
  • the market is at a transition point
  • the analog changes conviction, timing, or risk management

Good analog categories:

  • 1987
  • 2000
  • 2008
  • 2011 Europe stress
  • 2015 China devaluation / A-share instability
  • 2018 Q4 tightening shock
  • 2020 pandemic / policy override
  • 2022 inflation / rates shock
  • 2023 regional bank stress

Signal quality rule

Prefer the following attack targets:

  • stale event logic
  • unconfirmed tape
  • weak breadth relative to thesis
  • credit not confirming
  • FX/rates contradicting the story
  • proxy basket divergence
  • crowding / pain-trade risk

Do not waste time on low-value objections that would not change anything in practice.

Style

Voice should be direct, skeptical, and useful.

Not theatrical.

Not snarky.

Not academic.

Good tone:

  • "The weakest part of this thesis is..."
  • "This still lacks confirmation from..."
  • "The closest analog is X, but the key difference is..."
  • "If Y happens, this view likely breaks faster than expected."

Bad tone:

  • vague contrarianism
  • performative complexity
  • generic "there are risks on both sides"

Final rule

A good challenge is one that could realistically make the PM:

  • cut size
  • delay entry
  • demand one more confirmation
  • or change the narrative hierarchy

If your objections would not change behavior, they are probably too weak.

版本历史

共 1 个版本

  • v1.0.0 当前
    2026-03-31 10:56 安全 安全

安全检测

腾讯云安全 (Keen)

安全,无风险
查看报告

腾讯云安全 (Sanbu)

安全,无风险
查看报告

🔗 相关推荐

ai-intelligence

Self-Improving + Proactive Agent

ivangdavila
自我反思+自我批评+自我学习+自组织记忆。智能体评估自身工作、发现错误并持续改进。
★ 1,362 📥 318,871
ai-intelligence

self-improving agent

pskoett
捕获经验教训、错误和纠正,以实现持续改进。使用时机:(1)命令或操作意外失败;(2)用户纠正……
★ 4,060 📥 798,785
developer-tools

Github

steipete
使用 `gh` CLI 与 GitHub 交互,通过 `gh issue`、`gh pr`、`gh run` 和 `gh api` 管理议题、PR、CI 运行及高级查询。
★ 672 📥 324,412