Skip to content
Back to search

dsh-stock-probability-chart

股票概率图 — DeepSeek Harness 技能插件

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/tomcatle--dsh-stock-probability-chart/badge.svg)](/listings/tomcatle--dsh-stock-probability-chart)

HTML

<a href="/listings/tomcatle--dsh-stock-probability-chart"><img src="/api/listings/tomcatle--dsh-stock-probability-chart/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

本插件通过 **GitHub 分发**,无 npm 包。按你的环境选一种:

方式 A:不需要本机装 Git(推荐)

从 GitHub Release 下载打包好的 `.tgz`,本地安装:

dsh plugin --profile web add ./dsh-stock-probability-chart-0.1.0.tgz

> 国内网络若 GitHub Release 直链被重置,可先把 `.tgz` 下载到本地再用上面的本地路径命令——零网络依赖,最可靠。

方式 B:需要本机装过 Git

dsh plugin --profile web add github:tomcatle/dsh-stock-probability-chart

钉版本(推荐,避免后续推送悄悄改变运行内容):

dsh plugin --profile web add github:tomcatle/dsh-stock-probability-chart#v0.1.0

> pnpm 会调用 `git ls-remote` 解析地址。本机没装 Git 会报 `ERR_PNPM_GIT_RESOLVE_FAILED` 或「'git' 不是内部或外部命令」——遇到就改用方式 A。

> 桌面版若提示 `profile "desktop" is managed exclusively by the Electron application`,请在 DSH 应用的插件管理界面内添加。

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 124 lines
  1. # 股票概率图(dsh-stock-probability-chart)
  2. [English](#english) | 中文
  3. 为 DeepSeek Harness 增加「股票概率图」技能:评估单只股票未来短周期(1 周至 1 个月)的上涨/下跌情景概率,输出红涨绿跌的四情景概率分布图。
  4. > 产出是**结构化主观概率估计**,不是统计回测、不是量化信号、没有历史胜率支撑。仅供研究参考,不构成投资建议。
  5. ## 功能
  6. - 固定六步法:锁口径 → 取六类信号 → 信号定级 → 多空加权 → 贝叶斯校准 → 四情景映射
  7. - 四档互斥完备情景(强势上涨 / 温和收阳 / 收阴整理 / 破位下跌),概率之和严格 100%
  8. - 概率用 5% 步长整数,不制造虚假精度;数据缺失标注「数据未覆盖」,不编造
  9. - 图内标注「主观估计,非统计回测」,遵守 A 股红涨绿跌惯例
  10. - 零依赖、零构建脚本——安装时无需任何授权
  11. ## 安装
  12. 本插件通过 **GitHub 分发**,无 npm 包。按你的环境选一种:
  13. ### 方式 A:不需要本机装 Git(推荐)
  14. 从 GitHub Release 下载打包好的 `.tgz`,本地安装:
  15. ```sh
  16. dsh plugin --profile web add ./dsh-stock-probability-chart-0.1.0.tgz
  17. ```
  18. > 国内网络若 GitHub Release 直链被重置,可先把 `.tgz` 下载到本地再用上面的本地路径命令——零网络依赖,最可靠。
  19. ### 方式 B:需要本机装过 Git
  20. ```sh
  21. dsh plugin --profile web add github:tomcatle/dsh-stock-probability-chart
  22. ```
  23. 钉版本(推荐,避免后续推送悄悄改变运行内容):
  24. ```sh
  25. dsh plugin --profile web add github:tomcatle/dsh-stock-probability-chart#v0.1.0
  26. ```
  27. > pnpm 会调用 `git ls-remote` 解析地址。本机没装 Git 会报 `ERR_PNPM_GIT_RESOLVE_FAILED` 或「'git' 不是内部或外部命令」——遇到就改用方式 A。
  28. > 桌面版若提示 `profile "desktop" is managed exclusively by the Electron application`,请在 DSH 应用的插件管理界面内添加。
  29. ## 使用
  30. 安装后重开会话,直接说:
  31. - 「用股票概率图评估 TCL 科技下周」
  32. - 「XX 股下周上涨概率多大」
  33. 也可用 `/stock-scenario-probability` 手动触发。
  34. ## 兼容性
  35. - DeepSeek Harness `>=0.2.0-rc.2 <0.3.0-0`
  36. - Node `^22.19.0 || >=24.0.0`
  37. ## 限制
  38. - 概率是主观估计,不是统计结论,不同权重假设会得出不同结果
  39. - 需要当前环境具备联网取数能力;无联网时技能只提供方法论框架、不给概率
  40. - 概率图能否内联渲染取决于宿主环境;无内联能力时退化为生成 SVG 文件预览
  41. ## 许可
  42. MIT
  43. ---
  44. <a name="english"></a>
  45. ## English
  46. # Stock Probability Chart
  47. A DeepSeek Harness skill that estimates short-horizon (1 week to 1 month) up/down scenario probabilities for a single stock and renders a four-scenario probability chart using the A-share red-up/green-down convention.
  48. > Output is a **structured subjective probability estimate**, not a statistical backtest, not a quant signal, with no historical win-rate support. For research only; not investment advice.
  49. ### Features
  50. - Fixed six-step method: lock baseline → gather six signal types → grade signals → weight bull/bear → Bayesian calibration → four-scenario mapping
  51. - Four exhaustive scenarios (strong up / mild up / sideway down / breakdown) summing exactly to 100%
  52. - Probabilities in 5% integer steps; no false precision; missing data marked "not covered"
  53. - Chart labels "subjective estimate, not statistical backtest"; red = up, green = down
  54. - Zero dependencies, zero build scripts — no install-time authorization required
  55. ### Install
  56. Distributed via GitHub (no npm package). Choose by your environment:
  57. **No local Git required (recommended):** download the `.tgz` from GitHub Releases and install locally:
  58. ```sh
  59. dsh plugin --profile web add ./dsh-stock-probability-chart-0.1.0.tgz
  60. ```
  61. **Requires local Git:**
  62. ```sh
  63. dsh plugin --profile web add github:tomcatle/dsh-stock-probability-chart#v0.1.0
  64. ```
  65. ### Usage
  66. After install, restart the session and say: "Use the stock probability chart to evaluate TCL Tech next week", or trigger `/stock-scenario-probability`.
  67. ### Compatibility
  68. - DeepSeek Harness `>=0.2.0-rc.2 <0.3.0-0`
  69. - Node `^22.19.0 || >=24.0.0`
  70. ### Limitations
  71. - Probabilities are subjective estimates, not statistical conclusions; different weight assumptions yield different results
  72. - Requires network access for data; without it, the skill provides the framework only
  73. - Inline chart rendering depends on host capabilities; falls back to SVG file preview
  74. ### License
  75. MIT

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.