bear-case

A devil's-advocate workflow for testing an investment's optimistic case against evidence that could disprove it. It treats a bearish case as a possible scenario, not a prediction.

In plain words
What is it for?
Use it to map each bullish assumption to opposing evidence, define mild and severe downside scenarios, identify warning triggers, and document facts separately from assumptions and inferences.
Why use it?
It helps expose weak assumptions, negative signals, valuation concerns, and missing evidence before relying on a bullish story.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/travisun/opptrix/bear-case
Any agent
npx skills add Travisun/Opptrix --skill bear-case
Clone the repo
git clone --depth 1 https://github.com/Travisun/Opptrix

Made for: Claude Code, Codex.

Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,014 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00060 $0.01014
Opus 5 $0.00030 $0.00507
Sonnet 5 $0.00012 $0.00203
Haiku 4.5 $0.00006 $0.00101

Measured 2d ago against content hash 77e22758866b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bear-case scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

packages/agent-skills/builtin/bear-case/SKILL.md · 69 lines

What it actually says

空头情景(Bear Case)

何时使用

用户要做 Devil’s advocate / 空头情景:系统性质疑多头叙事,列出可验证的攻击点与触发条件。边界:正面论点备忘用 @skill:thesis-memo;全面尽调用 @skill:equity-deep-dive。本技能强调 多头假设 ↔ 攻击一一对应,不是单纯罗列风险词。

分析架构(投研方法)

  • 问题/假设:若多头错了,最可能错在哪几条?何种证据会提前示警?
  • 证据清单:财务恶化信号、负面资讯、估值拥挤线索、用户或 workspace 中的多头假设
  • 多维交叉验证:每条多头支柱对照反向证据;区分已发生事实 vs 情景推演
  • 结论与不确定:空头路径为情景(假设驱动);不得写成「必然下跌」
  • 风险与缺口:无明确多头假设、资讯片面、缺财务
  • 事实 | 假设 | 推断 分栏强制

数据维度

维度 取数方向 缺失时
标的 search_instruments / ask_user 先确认
多头假设来源 用户陈述 / workspace_read / 会话 thesis ask_user 索要 2–5 条多头支柱
概况/财务 get_instrument_profile / get_instrument_financials 仅做定性攻击并降级
行情 get_instrument_snapshot 省略估值拥挤章
资讯 get_instrument_news 省略舆情攻击点
交付 list_web_vendorcreate_web 用户只要口头要点时可跳过

步骤

  1. 提取多头假设清单(编号);缺失则 ask_user
  2. 逐条取证攻击:财务/资讯/结构;每条攻击对应一条多头假设。
  3. 情景路径:温和承压 / 严重恶化;写清触发指标。
  4. 事实 | 假设 | 推断 分栏;标明哪些是已发生、哪些是推演。
  5. 交付网页(默认)list_web_vendorcreate_web;已有则 read_web / update_web

网页报告建议目录

  1. 标的与时效
  2. 多头假设清单(编号)
  3. 一一对应攻击表(假设 → 反证/机制)
  4. 空头情景路径与触发条件
  5. 事实 | 假设 | 推断分栏
  6. 观察清单与时间盒
  7. 风险:空头偏见与数据缺口
  8. 免责声明(无做空/买卖建议)

禁止

  • 荐股、鼓动做空;编造负面「爆雷」事实
  • 禁止无交付就结束(默认须有 web 产物,除非用户明确只要口头要点)
  • 只写笼统风险、不与多头假设一一对应
  • assumption / not-feasible 须诚实降级
  • 禁止把推断写成已坐实的舞弊结论
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 69 lines · 60 tokens per session scan A 77e22758866b

Subscribe to this mod's changes

bear-case is a skill published in the GitHub repository Travisun/Opptrix (224 stars, last pushed 5d ago), licensed Apache-2.0. It adds 60 tokens to every session and 1,014 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

national-team-position

估计中国 A 股"国家队"(中央汇金)的宽基 ETF 持仓变动趋势——追踪上交所沪深300/上证50/中证500/中证1000/中证A500/科创50 的 ETF 份额变化,叠加各自指数走势,生成六合一总图与各指数单图。Estimates China's "national team" (Central Huijin) broad-base ETF positioning by tracking Shanghai Stock Exchange ETF share changes. Use when the user asks about 国家队持仓 / 国家队仓位 / 中央汇金持仓 / 国家队加仓 / 国家队减仓 /…

Xiaoyuan-Liu/national-team-position · 161 tokens

caijing-ipo-hk

财经·港股打新——完整打新顾问 + 发行体检。回答"这只港股新股怎么打、打多少、破发统计风险多大"。内置:可配置用户档案(券商/资金/风险偏好)、主流券商费率预设、申请档位与历史配售证据、绝对孖展金额、因子体检(保荐人/基石/定价四分位/结构/热度/情绪/18A/18C)、三档条件性方案与执行清单。含招股期与数据时效 gate;默认自用模式可给条件性申购建议,对客输出仍按 compliance-rendering 降级。触发:"分析这个新股""XX招股了""怎么打""打多少手""港股打新""孖展""暗盘";命令 /caijing:ipo-hk。.

nekopunch11/rodya-caijing-studio · 209 tokens

caijing-fundamental

财经·基本面——产出一份分析师级、全面、详细、前瞻、论点驱动的深度研究文档。对 A股/港股上市公司:立核心论点与分歧视角(市场信什么、我哪里不同),在 2–3 个决定命运的胜负手上量化钻透(带估算区间与置信度),十四段全面框架每段有真分析与子项,配三情景前瞻盈利、估值矩阵、多投资哲学对撞、Pre-Mortem 反偏见与长期跟踪清单。默认产出研报级 docx;客户合规版按需。触发:"全面分析XX""XX基本面怎么样""这公司质地如何";命令 /caijing:fundamental。.

nekopunch11/rodya-caijing-studio · 188 tokens

rodya-caijing-studio

财经内容台——面向个人投资者、研究人员与券商投顾/客户经理的 A股+港股专业研究和内容生产工具包。用于全面分析公司基本面、点评财报、判断估值位置、排查财务风险、梳理产业链、体检 A股/港股新股;所有使用者默认获得同一专业研究内核和研报级 docx,客户合规版按需生成,卡片/文案/PPT 按用户点名触发。稳定命令:/caijing:fundamental、/caijing:earnings、/caijing:valuation、/caijing:risk、/caijing:industry、/caijing:ipo-a、/caijing:ipo-hk。.

nekopunch11/rodya-caijing-studio · 171 tokens

caijing-earnings

财经·财报——只回答"这季财报行不行/财报前该看什么"。财报发布后的事件驱动快评:最新期核验 gate、同比环比速览、超预期三层基准判定(一致预期优先于公司指引,公司指引优先于历史季节性)、扣非与现金流含金量验证、前瞻指标(合同负债/订单/资本开支)、对投资逻辑支柱的增强/削弱/中性影响;财报发布前可做 earnings preview(关键指标、三情景、催化清单)。默认产出专业版财报点评 docx;客户版财报速览卡+文案按需。触发:"XX出财报了""点评XX年报/中报/季报""这季业绩怎么样""财报前看什么""业绩预览";命令 /caijing:earnings。.

nekopunch11/rodya-caijing-studio · 215 tokens

caijing-valuation

财经·估值——只回答"现在贵不贵"。估值锚按行业适配(周期股低PE陷阱/银行PB-ROE/亏损成长PS)、历史分位 band(纵向)、同业四分位对标(横向)、估值中枢有效性检查(价值陷阱提示)、反向 DCF 隐含预期(不给目标价)、三情景变量敏感性。默认产出专业版估值分析 docx;客户版分位 band 卡+文案按需。触发:"XX贵不贵""现在什么位置""估值怎么样""能不能买"(只答贵不贵);命令 /caijing:valuation。.

nekopunch11/rodya-caijing-studio · 161 tokens