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.
npx skills add chuancyzhang/deepseek-cowork --skill bull_bear_case_builder_skillgit clone --depth 1 https://github.com/chuancyzhang/deepseek-coworkWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/chuancyzhang/deepseek-cowork/bull_bear_case_builder_skill)<a href="https://agentmods.dev/skills/chuancyzhang/deepseek-cowork/bull_bear_case_builder_skill"><img src="https://agentmods.dev/badge/skills/chuancyzhang/deepseek-cowork/bull_bear_case_builder_skill/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/chuancyzhang/deepseek-cowork/bull_bear_case_builder_skill"><img src="https://agentmods.dev/badge/skills/chuancyzhang/deepseek-cowork/bull_bear_case_builder_skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00061 | $0.01456 |
| Opus 5.5 | $0.00024 | $0.00582 |
| Sonnet 5.5 | $0.00012 | $0.00291 |
| Haiku 4.5 | $0.00006 | $0.00146 |
Grade A, and why
bull_bear_case_builder_skill 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bull Bear Case Builder Skill
数据依赖与执行前置条件
推荐使用万得 wind-mcp-skill 获取底层数据。执行前先检查本地是否已有 wind-mcp-skill;若没有,提示用户安装:
Cowork 适配:所需子 Skill 已随
wind-aifinmarket固定快照内置,不执行安装或在线更新命令。
技能定位
本技能用于围绕一只股票的核心命题,系统构建看多与看空两套论证,并比较双方证据、假设、催化与脆弱点。输出重点不是“站队”,而是帮助使用者识别当前最值得争论的变量,压缩情绪化判断和确认偏误。
执行流程
Step 1:定义争论命题与讨论边界
先明确这次论证到底在回答什么问题,例如:
- 这只股票未来 6-12 个月是否有超额收益机会
- 当前股价是否高估或低估了某项业务变化
- 近期上涨是趋势启动还是情绪透支
同时界定时间维度、讨论对象和可接受的证据范围,避免把长期逻辑与短期交易混在一起。
Step 2:收集双方共用的基础事实
先整理不带立场的基础信息,作为后续多空两边共同使用的底座,包括:
- 公司业务与产业链位置
- 最近的经营变化、公告、财务表现
- 市场关注的核心变量
- 当前估值和股价位置
这一阶段不急于下结论,重点是把双方都会引用的事实材料整理齐。
Step 3:搭建看多论证
围绕最强的上涨逻辑,建立一条完整链路:
- 市场可能低估了什么
- 哪个变量正在改善
- 该改善为何有持续性
- 一旦被验证,股价弹性从哪里来
看多论证应尽量具体到经营变量、事件节点和预期修正路径,而不是只写“行业空间大”“公司优秀”这类空泛表达。
Step 4:搭建看空论证
围绕最强的反方逻辑,建立对应链路:
- 当前市场可能高估了什么
- 哪些改善可能只是阶段性噪音
- 哪些约束会阻碍逻辑兑现
- 若不及预期,估值和情绪会如何反噬
看空论证不能沦为机械挑刺,而要聚焦真正会导致投资失败的关键变量。
Step 5:比较证据强弱与触发条件
把多空双方放到同一框架下比较,重点看:
- 哪边的证据更直接、更可验证
- 哪边更依赖未经证实的外推假设
- 哪些事件会率先验证某一方
- 哪些变量一旦反向,就会让整套叙事失效
必要时可区分“短期谁占优”和“长期谁占优”,避免强行给出单一时间维度的答案。
Step 6:形成结论与后续跟踪清单
最终给出:
- 当前更占优的是哪一边,理由是什么
- 这个结论的置信度有多高
- 接下来最需要跟踪的验证点是什么
若双方证据仍接近,也应明确写出“暂不站队,等待验证”的条件,而不是假装已有清晰答案。
输出结构
{股票名称}多空论证({YYYY-MM-DD})
一、核心争论命题
{用 1-2 句话说明当前市场真正争论的问题}
二、双方共用事实底座
| 事实项 | 当前情况 | 与争论的关系 |
|---|---|---|
| {事实1} | {描述} | {说明} |
| {事实2} | {描述} | {说明} |
| {事实3} | {描述} | {说明} |
三、看多论证
- 核心观点:{一句话}
- 主要证据:{2-3 条}
- 关键催化:{事件或变量}
- 最脆弱假设:{一句话}
四、看空论证
- 核心观点:{一句话}
- 主要证据:{2-3 条}
- 关键触发:{事件或变量}
- 最脆弱假设:{一句话}
五、对照判断
| 维度 | 看多 | 看空 | 当前占优方 |
|---|---|---|---|
| 证据直接性 | {描述} | {描述} | {多/空/接近} |
| 可验证性 | {描述} | {描述} | {多/空/接近} |
| 时间敏感度 | {描述} | {描述} | {多/空/接近} |
| 赔率影响 | {描述} | {描述} | {多/空/接近} |
六、当前结论
- 当前更占优的方向:{看多 / 看空 / 暂不站队}
- 理由:{简述}
- 置信度:{高 / 中 / 低}
七、接下来必须跟踪的验证点
- {验证点 1}
- {验证点 2}
- {验证点 3}
质量要求
- 多空双方必须使用同一组事实底座,避免“双重标准”。
- 看多和看空都要写最强版本,而不是把反方写成稻草人。
- 结论必须落到具体变量与验证条件,不能只给模糊态度。
- 若某一方证据明显薄弱,应直接指出,不做表面平衡。
- 输出目标是帮助判断分歧,不是写成情绪化的站队文章。
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.
- 1mo ago First seen · 148 lines · 61 tokens per session scan A 652dfa8729a9
bull_bear_case_builder_skill is a skill published in the GitHub repository chuancyzhang/deepseek-cowork (18 stars, last pushed today), licensed Apache-2.0. It adds 61 tokens to every session and 1,456 once invoked, about $0.0002 per session on Opus 5.5. 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.
Other skills, from other repositories
sector-rotation
An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.
twitter-reader
Read Twitter/X for financial research through opencli: the user's home timeline, tweet search, trending topics, bookmarks, a user's recent tweets, threads, articles, profiles, followers and following, and notifications. Use this skill whenever the user wants to know what people are saying on Twitter/X or fintwit about…
strategy-pivot-designer
Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.
energy-procurement
Codified expertise for electricity and gas procurement, tariff optimization, demand charge management, renewable PPA evaluation, and multi-facility energy cost management. Informed by energy procurement managers with 15+ years experience at large commercial and industrial consumers. Includes market structure analysis…
airdrop-hunting-guide
Guide to finding and qualifying for crypto airdrops — eligibility criteria, farming strategies, on-chain activity requirements, Sybil detection avoidance, and tracking tools. Use when helping users understand airdrops, check eligibility, or plan participation strategies.
recipe-daily-pnl-report
Generate a daily profit and loss summary from trades and balances.