Agent skill

Stock Advisor

by isjiamu in isjiamu/jiamu-skills

A股投资分析全自动流水线。触发场景:(1) 用户上传K线图或财报截图要求分析,(2) 用户提供A股股票代码或名称要求分析(如"分析一下平安银行"、"帮我看看000001"、"XX值得投资吗"),(3) 用户说"股票分析"、"投资分析"、"stock advisor"、"帮我分析股票"。

MITAuto-check passed

Install Stock Advisor

skills CLI
$ npx skills add isjiamu/jiamu-skills --skill stock-advisor -a claude-code

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

GitHub CLI
$ gh skill install isjiamu/jiamu-skills stock-advisor --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/isjiamu/jiamu-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/stock-advisor .claude/skills/stock-advisor && 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
stock-advisor
GitHub stars
139
Token cost
~1.1k tokens
SKILL.md length
264 words
Files
8 (incl. scripts, references)
Skills in repo
11
Repo updated
First seen
Licence
MIT

At a glance

A股投资分析全自动流水线。触发场景:(1) 用户上传K线图或财报截图要求分析,(2) 用户提供A股股票代码或名称要求分析(如"分析一下平安银行"、"帮我看看000001"、"XX值得投资吗"),(3) 用户说"股票分析"、"投资分析"、"stock advisor"、"帮我分析股票"。

  • Works in 4 steps: 风险偏好:保守 / 稳健 / 激进? → 投资周期:短线(1-2周)/ 中线(1-3月)/ 长线(3月以上)? → 关注行业:有没有特别关注的行业板块? → …
  • SKILL.md covers 流水线架构, 启动流程, 模块一:技术面分析 and 模块二:基本面分析, plus 6 more sections
  • Runs Python scripts from its folder; calls python

What it does

Stock Advisor is an agent skill from isjiamu/jiamu-skills. A股投资分析全自动流水线。触发场景:(1) 用户上传K线图或财报截图要求分析,(2) 用户提供A股股票代码或名称要求分析(如"分析一下平安银行"、"帮我看看000001"、"XX值得投资吗"),(3) 用户说"股票分析"、"投资分析"、"stock advisor"、"帮我分析股票"。

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 9 other files, including scripts and reference files (for example `references/advisory-board.md`, `references/image-prompts.md` and `references/report-structure.md`).

The repository describes itself as: 甲木常用的 Agent Skills 集合,包含日常工作流中积累的高效技能扩展。 / A curated collection of Agent Skills for daily productivity workflows. The licence is MIT.

Example prompts

  • “分析一下平安银行”
  • “帮我看看000001”
  • “XX值得投资吗”
  • “/stock-advisor”

Requirements

  • Python 3

Workflow steps

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

  1. 风险偏好:保守 / 稳健 / 激进?
  2. 投资周期:短线(1-2周)/ 中线(1-3月)/ 长线(3月以上)?
  3. 关注行业:有没有特别关注的行业板块?
  4. 仓位上限:单只股票最大仓位占比?

What it can do on your machine

Read from SKILL.md and the folder at commit 3c21371. 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

    Ships 4 files in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python

    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

Stock Advisor loads about 1.1k tokens when it runs, and up to ~3.4k if it reads all its reference files. Until then it costs about 39 tokens; SKILL.md has 264 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~39
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~3.4k

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 passed

The automated check found no risky patterns in SKILL.md.

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); the scripts in this folder are not scanned.

SKILL.md

The full file from isjiamu/jiamu-skills at commit 3c21371, republished under its MIT licence (© isjiamu). 264 words, ~1,099 tokens.

Download SKILL.mdSave it as .claude/skills/stock-advisor/SKILL.md (or your agent's skills folder). This skill also uses 7 other files; get the full folder from GitHub.
name
stock-advisor
description
A股投资分析全自动流水线。触发场景:(1) 用户上传K线图或财报截图要求分析,(2) 用户提供A股股票代码或名称要求分析(如"分析一下平安银行"、"帮我看看000001"、"XX值得投资吗"),(3) 用户说"股票分析"、"投资分析"、"stock advisor"、"帮我分析股票"。
author
甲木
version
v1.1

A股投资顾问 (Stock Advisor)

全自动编排型投资分析流水线。用户只需提供股票截图或代码,系统自动完成技术面分析、基本面分析、多维交叉验证、私董会决策讨论,最终输出精美排版的投资报告。

流水线架构

用户输入(截图 / 股票代码)
        │
        ▼
  ① 技术面分析 → ② 基本面分析 → ③ 多维交叉验证 → ④ 私董会讨论 → ⑤ 排版输出

启动流程

首次使用:投资风格档案

检查 memory 中是否存在用户投资风格档案。如不存在,提 3-4 个简短问题:

  1. 风险偏好:保守 / 稳健 / 激进?
  2. 投资周期:短线(1-2周)/ 中线(1-3月)/ 长线(3月以上)?
  3. 关注行业:有没有特别关注的行业板块?
  4. 仓位上限:单只股票最大仓位占比?

用户可选择跳过,后续在私董会环节自然补充。收集到的信息保存到 memory。

识别入口模式

根据用户输入自动判断:

  • 截图模式:用户上传了图片(K线图、财报截图)→ 图像识别 + AKShare 交叉验证
  • 代码模式:用户提供了股票代码或名称 → 纯 AKShare 数据驱动

两种模式均进入同一流水线,差异仅在数据获取方式。


模块一:技术面分析

截图模式
  1. 图像识别:从 K 线图中提取:

    • 股票名称和代码
    • 当前股价
    • K 线形态(近 5 日表现)
    • 均线排列状态(MA5/MA10/MA20)
    • MACD 状态(DIF/DEA 位置关系、柱状图趋势)
  2. AKShare 交叉验证:用识别出的股票代码调用脚本获取精确数据

    bash
    python scripts/technical_analysis.py --symbol <股票代码> --days 120
  3. 冲突处理:若图像识别与 API 数据有差异,以 API 数据为准,在报告中标注差异

代码模式

直接调用脚本获取数据并计算指标:

bash
python scripts/technical_analysis.py --symbol <股票代码> --days 120
输出:技术面速读表格
维度指标数值信号
趋势MA20/MA60—上升/震荡/下降
MACDDIF/DEA—金叉/死叉/多头/空头
KDJK/D/J—超买/超卖/中性
RSIRSI14—超买/超卖/中性
布林带上轨/中轨/下轨—突破/偏多/偏空
支撑压力支撑位/压力位——

模块二:基本面分析

截图模式
  1. 图像识别:从财报截图提取关键指标(营收、净利润、ROE、毛利率等)
  2. AKShare 补充:拉取 PE/PB/PS 估值数据、行业对比数据
    bash
    python scripts/fundamental_analysis.py --symbol <股票代码>
代码模式

直接调用脚本:

bash
python scripts/fundamental_analysis.py --symbol <股票代码>
合并输出

综合评级表格:

维度评分判断
技术面X/5趋势方向 + 关键信号
基本面X/5盈利能力 + 估值水平
资金面X/5成交量变化趋势
综合评级—强烈推荐/推荐/中性/谨慎/回避

操作建议:

  • 短期(1-2周)策略
  • 中期(1-3月)策略
  • 关键支撑位和压力位

模块三:多维交叉验证

使用内置 WebSearch 工具搜索以下信息:

  1. 研报观点:搜索 "<股票名称> 研报 <当前年份>" 获取机构评级和目标价
  2. 行业动态:搜索 "<所属行业> 行业趋势 <当前年份>" 了解上下游变化
  3. 重大新闻:搜索 "<股票名称> 最新消息" 排查重大利好/利空事件
  4. 政策影响:搜索相关产业政策、监管动态
交叉验证逻辑
  • 将搜索结果与模块一、二的分析进行对比
  • 如有矛盾信号(如技术面看涨但研报看空),明确标注分歧点并分析可能原因
  • 补充模块一二未覆盖的风险因素
输出:投资决策报告草稿

整合前三个模块的分析结果,生成结构化的投资决策报告草稿,作为私董会的讨论输入。


模块四:私董会决策讨论

调用 peers-advisory-group Skill 的核心机制,将投资决策报告草稿作为讨论议题。

详细指南见 references/advisory-board.md,包含幕僚阵容、5维度分析结构、观点碰撞模板、投资风格适配规则。

核心流程
  1. 通过 WebSearch 搜索四位幕僚(巴菲特/马斯克/盖茨/乔布斯)最新动态
  2. 将模块一~三的完整报告作为讨论议题
  3. 每位幕僚按 5维度结构 输出深度分析:核心判断 → 数据论据 → 类比案例 → 风险警示 → 最后一句话建议
  4. 输出 2-3 个观点碰撞(不同投资哲学的分歧与争论)
  5. 根据用户投资风格档案(如有)生成 个性化建议
  6. 综合四位幕僚观点,输出最终投资结论
自动化模式

默认由系统代替用户回答幕僚提问(基于分析数据 + 用户风格档案)。如用户主动发言,系统暂停自动代答,将对话权交给用户。


模块五:排版与输出

步骤一:整理报告 Markdown

将最终分析结果整理为以下结构:

markdown
# [股票名称]([代码]) 投资分析报告

> 报告日期:YYYY-MM-DD | 综合评级:XX

## 技术面分析
[模块一输出]

## 基本面分析
[模块二输出]

## 多维交叉验证
[模块三输出]

## 私董会纪要
### 巴菲特观点
[观点摘要]
### 马斯克观点
[观点摘要]
### 比尔·盖茨观点
[观点摘要]
### 乔布斯观点
[观点摘要]
### 最终结论
[综合结论]

## 操作建议
- 短期策略(1-2周)
- 中期策略(1-3月)
- 仓位建议
- 止损位

## 风险提示
投资有风险,以上分析仅供参考,不构成投资建议。据此操作,风险自担。
步骤二:杂志排版

调用 magazine-layout Skill,指定 "大胆社论"(Bold Editorial) 风格,将 Markdown 转为精美 HTML 文件。

保存 HTML 到本地:~/stock-reports/<股票代码>-<日期>.html

步骤三:转换 PDF

执行转换脚本:

bash
python scripts/html_to_pdf.py ~/stock-reports/<股票代码>-<日期>.html

输出 PDF 文件:~/stock-reports/<股票代码>-<日期>.pdf

步骤四:上传飞书云文档

调用 lark-doc Skill,将报告内容创建为飞书云文档:

  • 文档标题:[股票名称] 投资分析报告 - YYYY-MM-DD
  • 返回文档链接给用户
最终输出给用户
分析完成!

本地 PDF:~/stock-reports/<代码>-<日期>.pdf
飞书文档:<飞书链接>

综合评级:XX
核心结论:[一句话总结]

依赖

组件用途
AKShare (Python)A股行情、K线、财务数据获取
a-share-analyst scripts技术分析、数据获取基础脚本
WebSearch(内置)研报、行业、新闻搜索
peers-advisory-group Skill私董会决策讨论
magazine-layout Skill杂志风格 HTML 排版
lark-doc Skill飞书云文档上传
Playwright (Python)HTML 转 PDF

脚本清单

脚本功能
scripts/technical_analysis.py技术指标计算(复用 a-share-analyst)
scripts/fetch_market_data.py市场数据获取(复用 a-share-analyst)
scripts/fundamental_analysis.py基本面分析(新增)
scripts/html_to_pdf.pyHTML 转 PDF(新增)

参考文件

文件内容
references/report-structure.md报告结构模板
references/image-prompts.md图像识别提示词模板

© isjiamu, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 7 other files (scripts, references) in stock-advisor of isjiamu/jiamu-skills.

  • SKILL.md
  • references/advisory-board.md
  • references/image-prompts.md
  • references/report-structure.md
  • scripts/fetch_market_data.py
  • scripts/fundamental_analysis.py
  • scripts/html_to_pdf.py
  • scripts/technical_analysis.py

Open the folder on GitHubat commit 3c21371

Compare with similar skills

Stock Advisor 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.

Stock Advisor compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Stock Advisor this skillisjiamu/jiamu-skills139—~1.1kAutomated safety check: PassMIT
StockMagicCube/agentara516—~1.1kAutomated safety check: PassNone
Advisor Modecursor/plugins11k—~2.6kAutomated safety check: NotesNone
Stock Analysisalirezarezvani/claude-skills28k—~8.5kAutomated safety check: PassMIT
Xvary Stock Researchsickn33/agentic-awesome-skills47k2 repos~952Automated safety check: PassMIT
Odoo Upgrade Advisorsickn33/agentic-awesome-skills47k2 repos~1.3kAutomated safety check: PassMIT

Similar skills

  • Stock

    MagicCube/agentara

    Query stock quotes for US stocks, Hong Kong stocks, and A-shares.

    516 GitHub stars~1.1k tokensUpdated 5 mo ago
    Business, Finance & HRAuto-check passed
  • Advisor Mode

    cursor/plugins

    Official

    Adds a second, stronger model that the main agent consults before major decisions, when stuck and before finishing, controlled by /advisor commands.

    11k GitHub stars~2.6k tokensUpdated today
    Agent WorkflowsAuto-check: notes
  • Stock Analysis

    alirezarezvani/claude-skills

    Produce a rigorous, sector-relative, multi-factor fundamental analysis of a publicly listed company — Indian (NSE/BSE) or US/global.

    28k GitHub stars~8.5k tokensUpdated 1 mo ago
    Business, Finance & HRAuto-check passed
  • Xvary Stock Research

    sickn33/agentic-awesome-skills

    Thesis-driven equity analysis from public SEC EDGAR and market data; /analyze, /score, /compare workflows with bundled Python tools (Claude Code, Cursor, Codex).

    47k GitHub starsUsed in 2 repos~952 tokens
    Business, Finance & HRAuto-check passed
  • Odoo Upgrade Advisor

    sickn33/agentic-awesome-skills

    Step-by-step Odoo version upgrade advisor: pre-upgrade checklist, community vs enterprise upgrade path, OCA module compatibility, and post-upgrade validation.

    47k GitHub starsUsed in 2 repos~1.3k tokens
    DevelopmentAuto-check passed
  • Inventory Stock Reconciliation

    sickn33/agentic-awesome-skills

    Stock reconciliation register: count date, item, warehouse, book vs physical quantity, variance quantity and value, variance reason, damage and expiry, adjustment and approval.

    47k GitHub starsUsed in 1 repo~6.4k tokens
    Business, Finance & HRAuto-check passed

More from isjiamu/jiamu-skills

All 11 skills in this repo
  • Video Downloader

    isjiamu/jiamu-skills

    Download videos from 1000+ websites (YouTube, Bilibili, Twitter/X, TikTok, etc.) using yt-dlp.

    139 GitHub stars~1.2k tokensUpdated 2 mo ago
    Auto-check passed
  • Magazine Layout

    isjiamu/jiamu-skills

    将文本内容转换为精美的杂志风格HTML页面,支持专业排版和多种视觉风格。触发场景:(1) 用户想将文本/文章转换为杂志风格HTML,(2) 用户提到"杂志排版"、"杂志设计"、"文章排版"、"专业排版"、"文本美化"、"magazine layout",(3) 用户需要优雅排版的HTML页面,(4) 用户需要将设计内容导出为PDF。支持12种独特视觉风格,使用Tailwind CSS。

    139 GitHub stars~1.1k tokensUpdated 2 mo ago
    Auto-check passed
  • Gif Splitter

    isjiamu/jiamu-skills

    GIF动图切分工具,将超过指定帧数的GIF文件自动拆分成多个小文件。适用于微信公众号等平台上传GIF时遇到"帧数超限"的问题。

    139 GitHub stars~610 tokensUpdated 2 mo ago
    Auto-check passed
  • Sales AI Assistant

    isjiamu/jiamu-skills

    帮助销售人员将业务场景转化为AI提示词并自动生成销售内容(邮件、方案、分析等),无需学习如何编写提示词. An agent skill from isjiamu/jiamu-skills.

    139 GitHub stars~1.4k tokensUpdated 2 mo ago
    Auto-check passed
  • Peers Advisory Group

    isjiamu/jiamu-skills

    私董会专家助手,引导用户完成完整的私董会流程。通过四位顶级幕僚(巴菲特、比尔·盖茨、马斯克、乔布斯)的多轮提问和反馈,帮助用户深入剖析问题本质并获得可执行的解决方案。融合百度搜索和百度百科实时数据,让幕僚"带着数据聊"。触发场景:(1) 用户说"开始私董会"、"私董会"、"peers advisory",(2) 用户需要多角度分析复杂决策问题,(3) 用户希望获得不同商业领袖视角的建议,(4)…

    139 GitHub stars~1.2k tokensUpdated 2 mo ago
    Auto-check passed
  • Five Why

    isjiamu/jiamu-skills

    5Why 溯源顾问,通过连续追问"为什么"层层剥离问题表象,帮用户找到系统性的根本原因并制定根治对策. An agent skill from isjiamu/jiamu-skills.

    139 GitHub stars~803 tokensUpdated 2 mo ago
    Auto-check passed

Questions about Stock Advisor

What does Stock Advisor do?

A股投资分析全自动流水线。触发场景:(1) 用户上传K线图或财报截图要求分析,(2) 用户提供A股股票代码或名称要求分析(如"分析一下平安银行"、"帮我看看000001"、"XX值得投资吗"),(3) 用户说"股票分析"、"投资分析"、"stock advisor"、"帮我分析股票"。. Stock Advisor is an agent skill from isjiamu/jiamu-skills.

How do I install Stock Advisor in Claude Code?

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

How do I install Stock Advisor in Codex?

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

Can I use Stock Advisor 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 isjiamu/jiamu-skills --skill stock-advisor -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/stock-advisor, .gemini/skills/stock-advisor, .github/skills/stock-advisor and .opencode/skills/stock-advisor in your project.

What does Stock Advisor need to run?

Going by SKILL.md and its folder, Stock Advisor needs Python for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: Python 3.

Does Stock Advisor 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 Stock Advisor safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Stock Advisor use?

Stock Advisor is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Stock Advisor use?

About 1.1k tokens (SKILL.md is roughly 4.4k 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 2.3k tokens, read only when the agent opens those files.

What are the alternatives to Stock Advisor?

Skills that share tags, products or a category with Stock Advisor: Stock (MagicCube/agentara, 516 stars), Advisor Mode (cursor/plugins, 11k stars), Stock Analysis (alirezarezvani/claude-skills, 28k stars) and Xvary Stock Research (sickn33/agentic-awesome-skills, 47k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Stock Advisor?

isjiamu (a GitHub user) maintains it in isjiamu/jiamu-skills, which has 139 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on July 14, 2026.

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