Agent skill

Us Stock Prediction

by digoal in digoal/blog

美股个股次日走势预测 skill。当用户输入美股股票代码(如 AAPL、TSLA)或公司名称(如 "苹果"、"特斯拉"),并要求预测次日(T+1)走势、给出交易计划、评估盈亏概率时,触发本 skill。skill 会用 mcpMiniMaxwebsearch 搜证盘前 90…

GPL-2.0Auto-check: warningsProductivity & Automation

Install Us Stock Prediction

The automated check flagged lines worth reading first. See the safety section below.

skills CLI
$ npx skills add digoal/blog --skill us-stock-prediction -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install digoal/blog us-stock-prediction --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/digoal/blog.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/us-stock-prediction .claude/skills/us-stock-prediction && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
us-stock-prediction
GitHub stars
8.6k
Token cost
~1.9k tokens
SKILL.md length
280 words
Files
6 (incl. references)
Skills in repo
98
Repo updated
First seen
Licence
GPL-2.0

At a glance

美股个股次日走势预测 skill。当用户输入美股股票代码(如 AAPL、TSLA)或公司名称(如 "苹果"、"特斯拉"),并要求预测次日(T+1)走势、给出交易计划、评估盈亏概率时,触发本 skill。skill 会用 mcpMiniMaxwebsearch 搜证盘前 90…

  • Works in 4 steps: 基准概率:五维加权得分 ÷ 2.0 × 100%(线性映射)再 clamp 到… → 基础概率:55%(中性,因美股个股次日方向近乎 50/50) → 调整 → …
  • Tasks that involve Web search
  • SKILL.md covers 核心目标, 工作流(7 步,严格按顺序执行), 步骤 1:标的解析 and 步骤 2:信息搜证(盘前 90 分钟清单), plus 8 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Us Stock Prediction is an agent skill from digoal/blog. 美股个股次日走势预测 skill。当用户输入美股股票代码(如 AAPL、TSLA)或公司名称(如 "苹果"、"特斯拉"),并要求预测次日(T+1)走势、给出交易计划、评估盈亏概率时,触发本 skill。skill 会用 mcpMiniMaxwebsearch 搜证盘前 90 分钟的关键信息(财报、盘后走势、隔夜期货、期权异动、内部人交易、宏观日历等),按"五维分析框架"(基本面/技术面/资金面/情绪面/宏观面)交叉验证,产出可量化的方向预测(涨/跌/横盘 + 概率百分比 + 区间),并写入当前项目 markdown 目录下的 us-stock-{TICKER}-{YYYY-MM-DD}.md。输出必须有完整的逻辑推导链(每一维的打分过程与数据来源)、术语通俗解释、mermaid/ascii 流程图或可视化图表。适用场景:盘前/盘中想做次日的方向判断与交易计划;不适用:长线基本面估值(应改用 finance 领域其他 skill)、日内高频交易、加密货币/港股/A股。

Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files, including reference files (for example `agents/openai.yaml`, `references/five-dimension-framework.md` and `references/output-template.md`).

It sits in Productivity & Automation, covering Web search, Diagrams and Markdown. It works with MiniMax, Model Context Protocol and Mermaid. The repository describes itself as: AI,Opensource,Database,Business,Finance,Minds. git clone --depth 1 https://github.com/digoal/blog. The licence is GPL-2.0.

When your agent uses it

  • Tasks that involve Web search
  • Tasks that involve Diagrams
  • Tasks that involve Markdown

Example prompts

  • “五维分析框架”
  • “/us-stock-prediction”

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. 基准概率:五维加权得分 ÷ 2.0 × 100%(线性映射)再 clamp 到 35%-65% 区间
  2. 基础概率:55%(中性,因美股个股次日方向近乎 50/50)
  3. 调整
  4. 最终:基础 55% + 调整 = 最终概率;同时给出 80% 置信区间的价格上下界(用近期 5 日 ATR × 1.28 作为一倍标准差)

What it can do on your machine

Read from SKILL.md and the folder at commit ad6fcb7. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Us Stock Prediction loads about 1.9k tokens when it runs, and up to ~11k if it reads all its reference files. Until then it costs about 117 tokens; SKILL.md has 280 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~117
When it runs · the whole SKILL.md, loaded when a task matches
~1.9k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~11k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: warnings

The automated check found patterns that need a careful read before installing.

  • WarningContains zero-width charactersSKILL.md:224
    ⟨U+200B⟩```mermaid
  • WarningContains zero-width charactersSKILL.md:233
    ⟨U+200B⟩```

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from digoal/blog at commit ad6fcb7, republished under its GPL-2.0 licence (© digoal). 280 words, ~1,933 tokens.

Download SKILL.mdSave it as .claude/skills/us-stock-prediction/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.
name
us-stock-prediction
description
美股个股次日走势预测 skill。当用户输入美股股票代码(如 AAPL、TSLA)或公司名称(如 "苹果"、"特斯拉"),并要求预测次日(T+1)走势、给出交易计划、评估盈亏概率时,触发本 skill。skill 会用 mcp__MiniMax__web_search 搜证盘前 90 分钟的关键信息(财报、盘后走势、隔夜期货、期权异动、内部人交易、宏观日历等),按"五维分析框架"(基本面/技术面/资金面/情绪面/宏观面)交叉验证,产出可量化的方向预测(涨/跌/横盘 + 概率百分比 + 区间),并写入当前项目 markdown 目录下的 `us-stock-{TICKER}-{YYYY-MM-DD}.md`。输出必须有完整的逻辑推导链(每一维的打分过程与数据来源)、术语通俗解释、mermaid/ascii 流程图或可视化图表。适用场景:盘前/盘中想做次日的方向判断与交易计划;不适用:长线基本面估值(应改用 finance 领域其他 skill)、日内高频交易、加密货币/港股/A股。

美股个股次日走势预测

核心目标

把"次日走势"这一低信噪比问题转成可重复、可量化、可复盘的决策流程:

  • 风险锁死 — 单笔最大可承受亏损 ≤ 账户净值 1%
  • 赔率优先 — 只参与潜在盈利:潜在亏损 ≥ 2:1 的交易
  • 逻辑可追溯 — 每一条结论必须能反向定位到具体数据来源

工作流(7 步,严格按顺序执行)

[用户输入代码/名称]
        │
        ▼
[步骤 1: 标的解析] — 确认 ticker、公司全名、所在交易所、所属板块
        │
        ▼
[步骤 2: 信息搜证] — 用 mcp__MiniMax__web_search 拉取盘前 90 分钟关键数据
        │
        ▼
[步骤 3: 五维打分] — 基本面 30% / 技术面 25% / 资金面 20% / 情绪面 15% / 宏观面 10%
        │
        ▼
[步骤 4: 综合推演] — 五维加权 → 方向预测(看多/看空/中性) + 概率(%) + 价格区间
        │
        ▼
[步骤 5: 交易计划] — 入场价、止损价、目标价、仓位、时间止损、退出条件
        │
        ▼
[步骤 6: 写出 markdown] — 保存到 <项目>/markdown/us-stock-{TICKER}-{YYYY-MM-DD}.md
        │
        ▼
[步骤 7: 输出摘要] — 控制台/聊天框给出核心结论 + 文件路径

步骤 1:标的解析

收到用户输入(如 "AAPL" 或 "苹果"),先确认以下信息(必要时就近 24h 内的搜索补充):

字段说明来源
Ticker标准化代码(如 AAPL,BRK.B)用户输入 + 搜索
公司全名Legal Name搜索 "Apple Inc ticker"
交易所NYSE / NASDAQ / 其他搜索
板块GICS 一级行业(科技/金融/医疗等)搜索
关键宏观关联是否权重股(影响 SPY/NQ)、是否中概、是否有特殊风险推断

如果用户只给公司名(如"苹果"),用 mcp__MiniMax__web_search(query="苹果公司 股票代码 ticker") 之类查询,优先在结果里找 ticker。


步骤 2:信息搜证(盘前 90 分钟清单)

严格按以下优先级调用 mcp__MiniMax__web_search,每次查询都把 ticker + 关键词组合:

P0 必查(没查到则预测置信度降一级)
{ticker} earnings after-hours
{ticker} 8-K filing {最近一周}
{ticker} after-hours price reaction
ES NQ futures overnight
VIX index today
P1 强烈建议查
{ticker} unusual options activity
{ticker} call put ratio
{ticker} institutional holdings 13F change
{ticker} insider trading Form 4
{ticker} analyst upgrade downgrade {最近一周}
P2 视情境查
{板块} sector ETF performance today
{ticker} technical analysis support resistance
{宏观经济事件} CPI FOMC NFP date this week
US 10 year yield today
DXY dollar index today
搜证时一次只搜 1-2 个查询,不要一次塞太多关键词,搜出来的结果至少要读 3-5 个 source 链接,做交叉验证。

如果搜证失败(网络问题、结果太少),直接降级为"中低置信度"预测,并在 markdown 中明确标注"信息缺失"。


步骤 3:五维打分(详细规则见 references/five-dimension-framework.md)

每维给出 -2 ~ +2 的整数打分(代表强烈看空到强烈看多),并简述 1-3 条关键证据。

维度权重打分(举例)
基本面催化30%财报超预期 + 指引上修 → +2;无重大消息 → 0;业绩暴雷 + 指引下调 → -2
技术面结构25%突破前高 + 量能配合 → +2;区间震荡 → 0;跌破关键支撑 → -2
资金面20%大额回购 + 内部人增持 + OI 看涨 → +2;无明显异动 → 0;暗池出货 → -2
情绪面15%分析师一致上调 + 散户关注度适中 → +1;极端一致预期(反向风险)→ 0 或反向
宏观面10%期货涨 + VIX 跌 + 无大事件 → +1;FOMC 当天 → 0;宏观冲击 → -1~-2

加权求和 → 范围 -2.0 ~ +2.0。

  • > +1.0 = 强看多(置信度"高")
  • +0.3 ~ +1.0 = 弱看多(置信度"中")
  • -0.3 ~ +0.3 = 中性震荡(置信度"中低")
  • -1.0 ~ -0.3 = 弱看空(置信度"中")
  • < -1.0 = 强看空(置信度"高")

如果五维里出现对冲信号(如基本面 +2 但宏观 -2),把"置信度"强制降一级,并在 markdown 里明确写"对冲点"。


步骤 4:综合推演 → 概率量化

输出三个数值(必须同时给):

方向:        看多 / 看空 / 中性
方向概率:    55% (区间 50%-60%)
价格区间:    $185 - $192 (次日内最可能的运行区间)
期望波动幅度: ±2.3%(基于 ATR 估算或近期日均波幅)

概率估算方法(不要瞎编):

  1. 基准概率:五维加权得分 ÷ 2.0 × 100%(线性映射)再 clamp 到 35%-65% 区间
  2. 基础概率:55%(中性,因美股个股次日方向近乎 50/50)
  3. 调整:
    • 有清晰 P0 催化 + 五维同向:基准 ± 10%-15%
    • 财报/重大事件次日:概率区间扩到 30%-70%
    • 信息严重缺失:clamp 回 45%-55%
  4. 最终:基础 55% + 调整 = 最终概率;同时给出 80% 置信区间的价格上下界(用近期 5 日 ATR × 1.28 作为一倍标准差)

必须明说:任何"≥ 70% 的方向概率"都是过度自信,需要在 markdown 顶部加免责声明。


步骤 5:交易计划(标准模板)

只有置信度 ≥ "中" 才给完整交易计划;置信度 < "中" 只给"观望/小注试错"建议。

markdown
### 交易计划
- 入场触发价: $____ (理由:____)
- 止损价:    $____ (理由:跌破 ____ 支撑 / 形态破坏)
- 目标价 TP1: $____ (赔率 1:1,平 50%)
- 目标价 TP2: $____ (赔率 2:1,再平 30%)
- 跟踪止损: 剩余 20% 用 1×ATR 跟踪
- 仓位大小:  账户净值的 ____% (确保止损触发时亏损 ≤ 1%)
- 最大持仓: ____ 个交易日(时间止损)
- 不做条件: 开盘 30 分钟内若 VWAP 之下,放弃

仓位计算公式(必须用):

仓位(股数) = (账户净值 × 风险预算%) ÷ (入场价 − 止损价)

步骤 6:输出 markdown 文件

命名规范

<项目根目录>/markdown/us-stock-{TICKER}-{YYYY-MM-DD}.md

例:/Users/digoal/new/markdown/us-stock-AAPL-2026-06-08.md

必须包含的章节(顺序固定)
markdown
# {TICKER} {公司名} 次日走势预测

> 预测日期:2026-06-08 | 目标交易日:2026-06-09
> 免责声明:本预测基于公开信息与概率推断,非投资建议。次日方向本身就是低信噪比问题,任何 ≥70% 的方向概率都应视为过度自信。

## 一、核心结论(速读)

用 3 行说清楚:方向、概率、关键价位。
例:
- 方向:看多(置信度 中)
- 次日方向概率:58%(区间 50%-66%)
- 关键价位:支撑 $185 / 压力 $195

## 二、五维分析(详细推导)

### 2.1 基本面催化(权重 30%,打分 +1)
证据 1:____(附数据来源)
证据 2:____
证据 3:____

### 2.2 技术面结构(权重 25%,打分 0)
证据 1:____
…

(每维重复)

## 五维加权得分
| 维度 | 打分 | 权重 | 加权 |
|---|---|---|---|
| 基本面 | +1 | 30% | +0.30 |
| 技术面 | 0  | 25% | 0    |
| 资金面 | +2 | 20% | +0.40 |
| 情绪面 | +1 | 15% | +0.15 |
| 宏观面 | +1 | 10% | +0.10 |
| **合计** |   |     | **+0.95** |

→ 弱看多(置信度"中"),基础概率 55% + 调整 +3% = **58%**

## 三、价格区间与可视化

用 mermaid 画一根"价格刻度尺",标记入场/止损/目标位:

```mermaid
graph LR
    A[止损 $182] -->|6% 风险| B[入场 $185]
    B -->|5% 赔率| C[目标 TP1 $190]
    C -->|3% 赔率| D[目标 TP2 $195]
    style A fill:#ff6b6b,color:#fff
    style B fill:#4ecdc4,color:#fff
    style C fill:#95e1d3,color:#333
    style D fill:#95e1d3,color:#333

或者用 ascii:

$182 ----|---- $185 ----|---- $190 ----|---- $195 ----|---- $200
   止损          入场          TP1(50%平)   TP2(30%平)   跟踪止盈
   ↑ 风险6%      ↑ 赔率5%      ↑ 赔率10%    ↑ 赔率17%

四、交易计划

(填步骤 5 模板)

五、风险与陷阱

列出本次预测的 3-5 个最大风险点(用通俗语言 + 术语解释)。 例:"如果开盘 CPI 数据高于预期 0.3 个百分点,会触发系统性抛售,这个预测要立即废弃。"

六、术语通俗解释

列出本文用到的所有专业术语(财报超预期、VWAP、Put/Call、ATR、暗池、IV Rank…),每个用 1-2 句通俗话解释,默认读者是投资小白。

七、数据来源

每一条数据后面用 [n] 标注来源(链接或机构名)。

  1. SEC EDGAR 8-K 申报:URL
  2. CNBC 盘后报道:URL
  3. Bloomberg:URL
  4. 期权扫描平台:URL

### 写作风格硬性要求

1. **每个专业术语第一次出现时,立即用括号给出口语解释**
   - 正确: "财报超预期(EPS 实际比分析师平均预期高)"
   - 错误: "公司 Q2 EPS beats consensus"
2. **每个数字必须标注单位、时点、来源**
   - 正确: "盘后股价 $208(2026-06-07 18:00 ET,Bloomberg)"
   - 错误: "盘后涨到 208"
3. **必须用图示**(mermaid 或 ascii),至少 1 个;最好 2-3 个(五维雷达、概率饼图、价格刻度尺)
4. **逻辑链必须能逆向追溯**:每一条结论都能找到对应证据 + 来源

---

## 步骤 7:输出摘要

markdown 写完后,在聊天框给用户一个**不超过 10 行的摘要**:

✅ 已生成预测报告:markdown/us-stock-AAPL-2026-06-08.md

📊 核心结论:

  • 方向:看多(置信度 中)
  • 次日方向概率:58%
  • 关键价位:支撑 $185 / 压力 $195 / 止损 $182

⚠️ 重要风险:

  • 次日 14:30 ET 有 PCE 物价指数公布
  • 盘后期权 IV 异常,可能引发开盘大幅波动

💡 建议仓位:账户净值的 0.8%(基于止损触发最大亏损 1% 计算)


---

## 风险铁律(执行时必须严格遵守)

1. **永远不要给出"必涨/必跌"的判断**。即便五维全正向,也要给概率区间,留反手空间。
2. **任何"≥ 70% 的方向概率"自动 clamp 到 65%**。美股个股次日方向是低信噪比事件,过度自信是破产的最快路径。
3. **信息缺失必须明确标注**,并把置信度降级,而不是补全数据。
4. **不预测的具体情形**:
   - 长线估值(应改用 fundamental analysis skill)
   - 日内高频点位(预测频率与时窗不匹配)
   - 财报前 24h 内的方向博弈(信息已被 Price-in,IV Crush 风险)
5. **不要把"看起来很对"的逻辑直接当成"会发生的现实"**。每一步都要写明"如果这个证据错了,推理链怎么塌"。

---

## 反模式(出现这些情况要重做)

| 反模式 | 为什么错 | 正确做法 |
|---|---|---|
| 只看技术面就给方向 | 技术面滞后,被 price-in 的概率高 | 必须五维交叉验证 |
| 把"利多"翻译成"必涨" | 利多已被市场消化或被宏观对冲 | 给概率,不给定论 |
| 没有数据来源 | 等同于瞎猜 | 每条数据附 [n] 引用 |
| 概率写 80% / 90% | 过度自信 | 强制 clamp 到 ≤ 65% |
| 跳过步骤 2 直接打分 | 拍脑袋 | 必须先搜证,再打分 |
| 给出"目标 50%" 的赔率 | 赔率 1:1 不值得入场 | 只参与 ≥ 2:1 赔率 |
| 把日内波动当趋势 | 噪声被当成信号 | 区分 1 日 / 5 日 / 20 日的尺度 |

---

## 资源引用

- **五维分析详细规则**:见 `references/five-dimension-framework.md`(打分细则、典型证据、常见陷阱)
- **术语通俗解释词典**:见 `references/terminology.md`(小白友好的术语表,每写一个术语前先查)
- **输出模板完整版**:见 `references/output-template.md`(可直接复制的 markdown 骨架)
- **搜证查询模板库**:见 `references/search-queries.md`(针对不同情境的关键词组合)

> 编写预测时,如果用到某个参考文件,先 Read 它再继续 — 不要凭印象生成内容。

---

## 自检清单(交付前 30 秒过一遍)

- [ ] 标的解析完整(ticker、交易所、板块、宏观关联)
- [ ] 至少 3 条 P0 搜证查询已执行
- [ ] 五维打分有具体证据 + 数据来源
- [ ] 加权得分算式清晰、可验证
- [ ] 方向概率 ≤ 65%,并有区间
- [ ] 交易计划包含入场/止损/目标/仓位/时间止损
- [ ] 至少 1 个 mermaid 或 ascii 图
- [ ] 至少 5 个专业术语有通俗解释
- [ ] 数据来源在文末以 [n] 编号列出
- [ ] 文件命名符合 `us-stock-{TICKER}-{YYYY-MM-DD}.md` 规范
- [ ] 文件保存到 `<项目根目录>/markdown/` 下

**未通过任何一项 = 重新写,不能交付。**

© digoal, GPL-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. 2 hidden characters (zero-width or bidirectional) removed. Raw file

Files

SKILL.md and 5 other files (references) in skills/us-stock-prediction of digoal/blog.

  • SKILL.md
  • agents/openai.yaml
  • references/five-dimension-framework.md
  • references/output-template.md
  • references/search-queries.md
  • references/terminology.md

Open the folder on GitHubat commit ad6fcb7

Compare with similar skills

Us Stock Prediction next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Us Stock Prediction compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Us Stock Prediction this skilldigoal/blog8.6k—~1.9kAutomated safety check: WarnGPL-2.0
Bm Mdmiantiao-me/bm.md617—~2.1kAutomated safety check: PassLGPL-3.0
Feishu Doc Creatorop7418/CodePilot6.5k1 repos~3.1kAutomated safety check: PassCustom licence
Markdown Syntax Guideantdigital-ai/agentic-ui224—~3.1kAutomated safety check: PassMIT
Chatbot Mvp Distillationpdsuwwz/chatgpt-vue3-light-mvp579—~722Automated safety check: PassMIT
Markdown Report WritingNeuroAIHub/BrainPilot1.1k—~2.6kAutomated safety check: WarnAGPL-3.0

Similar skills

  • Bm Md

    miantiao-me/bm.md

    使用 bm.md 写作、改写、排版或渲染 Markdown;生成 Mermaid 与 AntV Infographic,设置图片尺寸、高亮重点,以及执行 HTML/纯文本转换和 Markdown lint

    617 GitHub stars~2.1k tokensUpdated 11 days ago
    Media & CreativeAuto-check passed
  • Feishu Doc Creator

    op7418/CodePilot

    Creates a new Feishu cloud document from Lark-flavored Markdown through the create-doc MCP tool, in a folder, wiki node or knowledge space.

    6.5k GitHub starsUsed in 1 repo~3.1k tokens
    Productivity & AutomationAuto-check passed
  • Markdown Syntax Guide

    antdigital-ai/agentic-ui

    指导用户使用 @ant-design/agentic-ui 的 Markdown Editor / Renderer 扩展语法。图表场景优先使用内置 chart(HTML 注释 chartType + 表格),只有当内置 chartType 都不能表达诉求时才回退 Mermaid。Triggers on keywords like 表格, 视频, 图表, 卡片, 提示块, 流程图, 语法…

    224 GitHub stars~3.1k tokensUpdated yesterday
    Documents & OfficeAuto-check passed
  • Chatbot Mvp Distillation

    pdsuwwz/chatgpt-vue3-light-mvp

    Distill the chatgpt-vue3-light-mvp project into reusable architecture for building similar ChatGPT-style web products in other repositories.

    579 GitHub stars~722 tokensUpdated 2 mo ago
    DevelopmentAuto-check passed
  • Markdown Report Writing

    NeuroAIHub/BrainPilot

    Guide AI agents to write beautifully formatted, well-illustrated Markdown reports with proper structure, diagrams, and compatibility across GitHub and Obsidian.

    1.1k GitHub stars~2.6k tokensUpdated 8 days ago
    Documents & OfficeAuto-check: warnings
  • Chatbot Mvp Distillation Zh

    pdsuwwz/chatgpt-vue3-light-mvp

    将 chatgpt-vue3-light-mvp 项目蒸馏为可迁移到其他项目的中文架构指南。适用于设计或实现类似 ChatGPT 的 Web 对话产品,包括 SSE/fetch 流式响应、模型适配器契约、打字机渲染、Markdown/代码/KaTeX/Mermaid 渲染、推理过程展示,以及从本 Vue 3 MVP 迁移到其他项目的方案规划。

    579 GitHub stars~414 tokensUpdated 2 mo ago
    DevelopmentAuto-check passed

More from digoal/blog

All 98 skills in this repo
  • 三层审查模型,逐段逐句验证文章真伪、证据链与逻辑结构。Use when the user asks to fact-check, verify, audit, or evaluate the credibility of an article, essay, report, opinion piece, social-media post, or any written claim —…

    8.6k GitHub stars~939 tokensUpdated 2 days ago
    Auto-check passed
  • Find latent bugs in a local PostgreSQL source tree (RELxxSTABLE branch or HEAD) the way a core hacker does: build a heavily-poisoned debug instance (cassert + cache-discard + -O0/-ggdb3 + core…

    8.6k GitHub stars~4k tokensUpdated 2 days ago
    Auto-check passed
  • Digoal

    digoal/blog

    Portable digital employee distilled from digoal's personal blog for PostgreSQL, PolarDB, DuckDB, AI+database, vector/RAG, database operations, source-code reading, technical content creation…

    8.6k GitHub stars~2.2k tokensUpdated 2 days ago
    Auto-check passed
  • 从论文 PDF 文件或论文 PDF URL 生成通俗易懂、图文并茂、带批判性评估的中文 Markdown 解读,并保存到当前项目的 markdown 目录。Use when the user asks to interpret,精读,解读,summarize,explain,analyze, or write an article from an academic paper PDF…

    8.6k GitHub stars~1.5k tokensUpdated 2 days ago
    Auto-check passed
  • Analyze a product from documentation, websites, PDFs, articles, release notes, pricing pages, app listings, reviews, filings, or related links; save separate intermediate analyses from seven roles…

    8.6k GitHub stars~1.8k tokensUpdated 2 days ago
    Auto-check passed
  • Turn a blog post, article, notes, or any source material into a set of vertical poster images — one cover plus several coherent content slides that explain the core points.

    8.6k GitHub stars~1.4k tokensUpdated 2 days ago
    Auto-check passed

Questions about Us Stock Prediction

What does Us Stock Prediction do?

美股个股次日走势预测 skill。当用户输入美股股票代码(如 AAPL、TSLA)或公司名称(如 "苹果"、"特斯拉"),并要求预测次日(T+1)走势、给出交易计划、评估盈亏概率时,触发本 skill。skill 会用 mcpMiniMaxwebsearch 搜证盘前 90…. Us Stock Prediction is an agent skill from digoal/blog.

When should I use Us Stock Prediction?

Us Stock Prediction fits situations like: tasks that involve Web search; tasks that involve Diagrams; tasks that involve Markdown.

How do I install Us Stock Prediction in Claude Code?

Run `npx skills add digoal/blog --skill us-stock-prediction -a claude-code`. Or copy the skill folder (skills/us-stock-prediction in digoal/blog) into .claude/skills/us-stock-prediction in your project. Claude Code loads it when a task matches its description.

How do I install Us Stock Prediction in Codex?

Run `npx skills add digoal/blog --skill us-stock-prediction -a codex`. Or copy the skill folder (skills/us-stock-prediction in digoal/blog) into .agents/skills/us-stock-prediction in your project. Codex loads it when a task matches its description.

Can I use Us Stock Prediction in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add digoal/blog --skill us-stock-prediction -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/us-stock-prediction, .gemini/skills/us-stock-prediction, .github/skills/us-stock-prediction and .opencode/skills/us-stock-prediction in your project.

What does Us Stock Prediction need to run?

SKILL.md names no scripts, command-line tools or credentials: Us Stock Prediction is instructions for the agent only.

Does Us Stock Prediction access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Us Stock Prediction safe to install?

Our automated static check of SKILL.md flagged 2 warning(s): contains zero-width characters. Read the flagged lines before installing; the check is not a guarantee either way.

What licence does Us Stock Prediction use?

Us Stock Prediction is published under the GPL-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Us Stock Prediction use?

About 1.9k tokens (SKILL.md is roughly 7.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 9.4k tokens, read only when the agent opens those files.

What are the alternatives to Us Stock Prediction?

Skills that share tags, products or a category with Us Stock Prediction: Bm Md (miantiao-me/bm.md, 617 stars), Feishu Doc Creator (op7418/CodePilot, 6.5k stars), Markdown Syntax Guide (antdigital-ai/agentic-ui, 224 stars) and Chatbot Mvp Distillation (pdsuwwz/chatgpt-vue3-light-mvp, 579 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Us Stock Prediction?

digoal (a GitHub user) maintains it in digoal/blog, which has 8,588 GitHub stars. The repository holds 98 skills in this directory. The repository was last updated on October 9, 2026.

Source: digoal/blog on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.