a-stock-orchestrator

a-stock-orchestrator is a skill for Claude Code, Codex from LeoYeAI/openclaw-master-skills. It costs 70 tokens per session (5,288 once invoked), scanned A, original, MIT.

A Chinese-language workflow that coordinates several stock-analysis skills for mainland Chinese A-share research. It combines market scans, sector analysis, individual-stock research, and portfolio checks into an investment brief.

In plain words
What is it for?
Use it to scan sectors, analyze a sector, investigate individual stocks, check holdings, identify leading companies, review fundamentals and price-volume data, and save the resulting brief to Feishu.
Why use it?
It organizes multiple research steps and combines their results, so the user does not have to run each analysis separately.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is exec: python3 skills/a-stock-kline-analyzer/scripts/kline_analyzer.py --code XXX --days 60 --report.

Good fit Use it to scan sectors, analyze a sector, investigate individual stocks, check holdings, identify leading companies, review fundamentals and price-volume data, and save the resulting brief to Feishu.

Compare 6 skills from other repositories ↓
About the project

OpenClaw Master Skills is a curated, regularly updated collection of skills that extends an AI personal assistant platform with capabilities such as research, browser automation, presentation creation, and prompt work. It is intended for people using OpenClaw or MyClaw.ai to give their agents additional tasks and workflows. The catalogue contains many skills and agents from this collection.

LeoYeAI/openclaw-master-skills · 2,141 stars · on GitHub · myclaw.ai

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills
agentmods
npx agentmods add skills/leoyeai/openclaw-master-skills/a-stock-orchestrator

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for a-stock-orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/skills/leoyeai/openclaw-master-skills/a-stock-orchestrator/github.svg)](https://agentmods.dev/skills/leoyeai/openclaw-master-skills/a-stock-orchestrator)
Your own site
<a href="https://agentmods.dev/skills/leoyeai/openclaw-master-skills/a-stock-orchestrator"><img src="https://agentmods.dev/badge/skills/leoyeai/openclaw-master-skills/a-stock-orchestrator/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.

agentmods 80×15 button for a-stock-orchestrator

Your own site · 80×15
<a href="https://agentmods.dev/skills/leoyeai/openclaw-master-skills/a-stock-orchestrator"><img src="https://agentmods.dev/badge/skills/leoyeai/openclaw-master-skills/a-stock-orchestrator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,288 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Agent Snooping · line 181
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00070 $0.05288
Opus 5 $0.00035 $0.02644
Sonnet 5 $0.00014 $0.01058
Haiku 4.5 $0.00007 $0.00529

Measured 12d ago against content hash 612a483bf441, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

a-stock-orchestrator 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 12d 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.

skills/a-stock-orchestrator/SKILL.md · 488 lines

How it starts

The opening of the file, as written. The whole thing — 488 lines — stays where its author put it; the contents beside it link to each section on GitHub.

A股投研指挥官

编排调度 8 个子 Skill,串联成完整投研流水线。不自己抓数据,只做调度 + 整合 + 输出

🎯 四种运行模式

模式一:板块扫描("今天有什么机会?")

触发词:今日机会、扫描市场、找机会、今天买什么、热点

流程

Step 1 - 热点扫描
  调用 a-stock-trading-assistant(fetch_stock.py --hot-sectors)
  → 获取当日涨幅前列板块 + 资金流向

Step 2 - 龙头识别
  对 Top 3-5 热点板块,调用 a-stock-leader-identification
  → 每个板块锁定 1-2 只龙头候选

Step 3 - 基本面排雷
  对候选个股,调用 a-stock-fundamental-screening
  → 排除 ST、亏损、减持等风险标的

Step 4 - 量价验证
  对通过排雷的个股,调用 a-stock-volume-price
  → 确认走势真实性,排除诱多

Step 4.5 - 技术面快速扫描(Top 3 候选)
  对 Top 3 候选执行技术面综合分析(同模式三 Step 4.5,简化版)
  → 三方交叉验证技术面强度,排序

Step 5 - 深度分析(Top 2-3)
  默认:stock-research-engine
  辅助(如有 Token):tradingagents-analysis
  → 输出完整研报

Step 6 - 汇总输出投资简报

模式二:板块分析("帮我分析 XX 板块")

触发词:分析XX板块、XX行业怎么样、板块摸底

流程

Step 1 - 板块概况
  调用 akshare-stock 获取板块行情数据
    → stock_board_industry_name_em() 或 stock_board_concept_name_em()
  调用 a-stock-trading-assistant 获取板块实时数据

Step 2 - 热点新闻与资金流向
  调用 akshare-stock 获取板块资金流向数据
  用 web_search 搜索板块近期热点新闻(最近3天)
  → 整理板块驱动因素

Step 3 - 龙头识别
  调用 a-stock-leader-identification
  → 板块内找真龙 + 跟风股对比

Step 4 - 成分股扫描与排雷
  调用 akshare-stock 获取板块成分股列表
    → stock_board_industry_cons_em(symbol="板块名")
  调用 a-stock-fundamental-screening 对主要成分股排雷
  → 输出风险标的清单

Step 5 - 量价验证(Top 3)
  调用 a-stock-volume-price
  → 确认龙头走势

Step 6 - 深度分析(龙头股)
  默认:stock-research-engine
  辅助(如有 Token):tradingagents-analysis

Step 7 - 输出板块分析报告

模式三:个股深度分析("帮我看看 600519")

触发词:分析XX、看看XX、XX怎么样、帮我看看这个票、股票代码

流程

Step 1 - 实时行情
  调用 a-stock-trading-assistant(fetch_stock.py --code XXX)
  → 当前价、涨跌幅、成交量、技术指标

Step 2 - 历史数据
  调用 akshare-stock 获取 K 线 + 财务数据
  → 近30日K线、PE/PB/ROE等

Step 3 - 基本面排雷
  调用 a-stock-fundamental-screening
  → 排雷检查

Step 4 - 量价验证
  调用 a-stock-volume-price
  → 量价关系判断

Step 4.5 - 技术面综合分析(三方交叉验证)
  同时执行三个技术面分析方案,交叉验证:
  
  4.5a - 方案A: a-stock-kline-analyzer
    exec: python3 skills/a-stock-kline-analyzer/scripts/kline_analyzer.py --code XXX --days 60 --report
    → K线形态识别 + 量能分析 + 技术评分(0-100)
    → 提取:趋势判断、MACD信号、RSI信号、支撑位/压力位、综合建议
  
  4.5b - 方案B: stock-kline-analysis
    exec: python3 -c "
      from scripts.fetch_kline import fetch_all_timeframes
      from scripts.indicators import add_indicators
      d, w, m = fetch_all_timeframes('XXX')
      d = add_indicators(d)
      # 输出最后3日指标 + 多时间框架判断
    " (在 skills/stock-kline-analysis/ 目录下执行)
    → 多时间框架分析(日线+周线+月线)
    → 提取:均线排列、MACD/RSI/ATR 数值、布林带位置
    → 图表生成:
      exec: plot_kline(d, code='XXX', name='名称', out_path='/tmp/kline-XXX.png')
      上传飞书:feishu_doc_media insert(需先 wiki_space_node get 获取 obj_token)
      wiki node token → obj_token 转换示例:
        feishu_wiki_space_node(action="get", token="wiki_node_token")
        → obj_token, obj_type
        然后 feishu_doc_media(action="insert", doc_id=obj_token, file_path="/tmp/kline-XXX.png", type="image")
  
  4.5c - 方案C: stock-daily-analysis(AI增强)
    exec (在 skills/stock-daily-analysis/ 目录下执行):
      python3 -c "
      from scripts.data_fetcher import get_daily_data
      from scripts.trend_analyzer import analyze_stock
      from scripts.ai_analyzer import AIAnalyzer
      import json
      df = get_daily_data('XXX', 60)
      # 列名转换(tushare 中文列名 → trend_analyzer 英文列名)
      df = df.rename(columns={'日期':'date','开盘':'open','最高':'high','最低':'low','收盘':'close','成交量':'volume','成交额':'amount'})
      df = df[['date','open','high','low','close','volume']]
      tech = analyze_stock(df, 'XXX')
      tech_data = {
        'current_price': tech.current_price,
        'ma5': tech.ma5, 'ma10': tech.ma10, 'ma20': tech.ma20,
        'bias_ma5': tech.bias_ma5, 'bias_ma10': tech.bias_ma10,
        'trend_status': tech.trend_status.value,
        'macd_status': tech.macd_status.value,
        'macd_signal': str(tech.macd_signal),
        'rsi_status': tech.rsi_status.value,
        'rsi_signal': str(tech.rsi_signal),
        'volume_status': tech.volume_status.value,
        'volume_trend': str(tech.volume_trend),
        'signal_score': tech.signal_score,
        'buy_signal': tech.buy_signal.value,
        'signal_reasons': tech.signal_reasons,
        'risk_factors': tech.risk_factors,
      }
      config = json.load(open('config.json'))
      ai = AIAnalyzer(config['ai'])
      result = ai.analyze('XXX', '名称', tech_data)
      print(json.dumps(result, ensure_ascii=False, indent=2))
      "
    → LLM 趋势判断 + 买入信号评分
    → 提取:sentiment_score、trend_prediction、operation_advice、confidence_level
  
  4.5d - 三方交叉验证汇总
    对比三个方案的核心指标,判断一致性:
    - 趋势方向:三方是否一致(看多/看空/分歧)
    - MACD:金叉/死叉一致性
    - RSI:超买/超卖/中性
    - 综合评分:取均值或加权
    - 输出"技术面综合分析"章节(见输出模板)

Step 5 - 深度研报
  主力:stock-research-engine(按其分析框架执行完整6步)
  辅助(如有 Token):tradingagents-analysis → 多智能体交叉验证

Step 5.5 - 多空辩论
  调用 stock-debate V2.1
  → 读取 skills/stock-debate/SKILL.md,按其7步流程执行
  → 数据采集:腾讯财经(直连)+ 东方财富(代理)+ AkShare
  → 代理:仅数据采集时按需启停(stock_start_proxy / stock_stop_proxy),采集完必须关闭
  → 输出多空辩论报告,写入飞书(节点:EhQ6w2F5yiC0DKkxlzlcEMvIn2f)

Step 6 - 输出个股投资简报

Read the full file on GitHub · 488 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 12d ago First seen · 488 lines · 70 tokens per session scan A 612a483bf441

Subscribe to this mod's changes

a-stock-orchestrator is a skill published in the GitHub repository LeoYeAI/openclaw-master-skills (2,141 stars, last pushed 1mo ago), licensed MIT. It adds 70 tokens to every session and 5,288 once invoked, about $0.0003 per session on Opus 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.

Related

Other skills, from other repositories

most-important-thing-in-investing-howard-marks

Apply Howard Marks investing judgment for second-level thinking, price versus value, risk control, cycles, contrarianism, and defensive investing.

simbajigege/book2skills · 39 tokens

outsiders-ceo-capital-allocation-thorndike

Apply The Outsiders CEO framework to assess capital allocation, per-share value creation, buybacks, decentralization, and rational leadership.

simbajigege/book2skills · 39 tokens

analyzing-financial-reports

Analyzes Chinese public company financial statements (balance sheet, income statement, cash flow) to assess asset quality, profit authenticity, cash flow health, solvency, and overall investment value. Use when the user provides financial data or a company name and asks whether financials are healthy, whether profits…

simbajigege/book2skills · 105 tokens

stock-picking-by-common-stocks-uncommon-profits

Apply Philip Fisher's growth stock investment framework from Common Stocks and Uncommon Profits. Use this skill whenever a user wants to evaluate whether a company is a worthy long-term growth investment, assess management quality, gather competitive intelligence via scuttlebutt, decide when to buy an outstanding…

simbajigege/book2skills · 161 tokens

tushare-finance

A Python connection to Tushare Pro, a service that provides data about Chinese financial markets through many data interfaces.

StanleyChanH/Tushare-Finance-Skill-for-Claude-Code · 74 tokens

polymarket-btc-up-down-trader

Trade Polymarket BTC daily and weekly UP/DOWN markets with empirically-anchored exit discipline. Enters on CEX momentum divergence; exits automatically on time cap, volume spike, or target capture. Use when the user wants to trade BTC direction markets (hours/days duration), not fast 5-minute markets.

SpartanLabsXyz/simmer-sdk · 75 tokens