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 position_sizing_decision_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/position_sizing_decision_skill)<a href="https://agentmods.dev/skills/chuancyzhang/deepseek-cowork/position_sizing_decision_skill"><img src="https://agentmods.dev/badge/skills/chuancyzhang/deepseek-cowork/position_sizing_decision_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/position_sizing_decision_skill"><img src="https://agentmods.dev/badge/skills/chuancyzhang/deepseek-cowork/position_sizing_decision_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 | $0.00063 | $0.01576 |
| Opus 5.5 | $0.00025 | $0.00630 |
| Sonnet 5.5 | $0.00013 | $0.00315 |
| Haiku 4.5 | $0.00006 | $0.00158 |
Grade A, and why
position_sizing_decision_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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Position Sizing Decision 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
本技能用于解决“方向大致看对了，但到底该下多大”的问题。输出重点不是鼓励重仓表达观点，而是把风险预算、价格波动、计划止损距离和组合承受能力连接起来，让仓位大小成为纪律结果，而不是情绪结果。
功能简介
本技能的核心功能是：按风险预算给出适合的仓位大小与分批建议。
它强调先量化可承受损失，再反推资金投入规模，帮助使用者避免因单笔交易仓位过大而破坏整体节奏。
使用场景
- 用户已经有交易方向，但不知道单笔应该下多少仓位。
- 多个候选交易同时存在，需要决定谁配大仓、谁只给试错仓。
- 市场波动加大后，用户想重新校准单笔风险暴露。
- 团队希望统一仓位语言，减少“一把梭”和随意加码。
工作原则
- 仓位大小必须由可承受风险反推，不能由主观信心正推。
- 单笔仓位决策要同时考虑标的波动、止损距离、流动性和组合相关性。
- 不确定性越高，首笔仓位应越克制，等待后续验证再决定是否放大。
- 仓位建议必须和具体计划绑定，脱离计划的仓位数字没有意义。
- 正文不描述内部实现方式，只输出判断依据与建议。
执行流程
Step 1：确认账户约束与风险预算口径
先明确本次仓位建议基于什么约束：
- 是以单笔最大可承受亏损为核心，还是以总仓暴露为核心
- 用户是稳健型、均衡型还是激进型风险偏好
- 计划允许的试错次数有多少
- 是否存在行业、主题或单票上限
若用户未说明，默认以“单笔先控制风险，再考虑收益放大”为基本口径。
Step 2：识别交易类型与不确定性等级
不同交易类型，不应套用同一仓位模板：
- 趋势确认型交易可以接受相对更完整的仓位表达
- 事件驱动型交易需要更重视跳空与失真风险
- 抄底、反转、左侧试错类交易应显著降低首笔权重
- 流动性不足或波动过大的标的，应额外加入折扣
Step 3：测量波动与止损距离
仓位建议必须建立在“输得起”的距离上：
- 当前价格波动是否处于常态区间
- 若计划止损位过远，仓位是否需要同步缩小
- 若计划止损位过近，是否容易因噪音被洗出
- 是否需要采用更分散的入场节奏来降低点位敏感度
Step 4：评估组合承受力与相关性
单笔仓位不能脱离现有持仓环境：
- 当前组合是否已经偏向同一板块或同一风格
- 新交易是否会明显提高相关性聚集
- 当前总仓是否已高，导致新增交易容错下降
- 若已有相似逻辑持仓，新仓是否应按“补充暴露”而不是独立仓位处理
Step 5：给出首笔仓位与后续分批框架
仓位建议至少分成两个层次：
- 首笔试错仓位
- 条件验证后的扩仓上限
同时明确：
- 在何种确认条件下允许加仓
- 在何种不利波动下必须停止追加
- 是否适合一次到位，还是必须分批
Step 6：压力测试仓位是否可被执行
把建议仓位放到真实波动环境里再看一遍：
- 若开盘跳空，仓位是否仍可接受
- 若出现连续不利波动，心理和资金是否都扛得住
- 若首笔即止损，是否会破坏后续执行纪律
- 若市场环境突变，仓位是否还能快速收缩
Step 7：形成仓位建议成稿
最终输出应让使用者清楚知道“这笔能配多大、为什么不是更大、什么时候可以加、什么时候必须收”。正文保留约束逻辑、建议数字与风险说明。
输出结构
仓位决策建议（{YYYY-MM-DD}）
一、30 秒结论
- 交易对象：{股票名称}
- 建议仓位等级：{轻仓 / 中等 / 偏重 / 仅观察}
- 首笔建议：{内容}
- 扩仓条件：{内容}
- 主要限制因素：{一句话}
二、仓位建议拆解
| 维度 | 判断 | 对仓位的影响 |
|---|---|---|
| 风险预算 | {内容} | {内容} |
| 波动水平 | {内容} | {内容} |
| 止损距离 | {内容} | {内容} |
| 组合相关性 | {内容} | {内容} |
| 流动性 | {内容} | {内容} |
三、执行框架
- 首笔仓位：{内容}
- 二次加仓条件：{内容}
- 最大总仓位上限：{内容}
- 停止追加条件：{内容}
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 · 159 lines · 63 tokens per session scan A 1a7236b1c5c2
position_sizing_decision_skill is a skill published in the GitHub repository chuancyzhang/deepseek-cowork (18 stars, last pushed today), licensed Apache-2.0. It adds 63 tokens to every session and 1,576 once invoked, about $0.0003 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 2026-09-04.
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.