Team Agent Orchestration
affaan-m/ECC
Run team-based orchestration for agent squads: work items with owners and scope, agent Kanban state, branch isolation, control pane visibility, and merge gates.
A股投研指挥官 - 编排调度多个股票分析Skill,串联成完整投研流水线。支持四种模式:板块扫描、板块分析、个股深度分析、持仓体检。最终输出结构化投资简报并自动存档飞书。
$ npx skills add LeoYeAI/openclaw-master-skills --skill a-stock-orchestrator -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills a-stock-orchestrator --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/a-stock-orchestrator .claude/skills/a-stock-orchestrator && rm -rf skills-srcUse ~/.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/
Install the "a-stock-orchestrator" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/a-stock-orchestrator into .claude/skills/a-stock-orchestrator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "a-stock-orchestrator", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/a-stock-orchestratorType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add LeoYeAI/openclaw-master-skills --skill a-stock-orchestrator -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills a-stock-orchestrator --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/a-stock-orchestrator .agents/skills/a-stock-orchestrator && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "a-stock-orchestrator" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/a-stock-orchestrator into .agents/skills/a-stock-orchestrator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "a-stock-orchestrator", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add LeoYeAI/openclaw-master-skills --skill a-stock-orchestrator -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills a-stock-orchestrator --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/a-stock-orchestrator .cursor/skills/a-stock-orchestrator && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "a-stock-orchestrator" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/a-stock-orchestrator into .cursor/skills/a-stock-orchestrator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "a-stock-orchestrator", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/LeoYeAI/openclaw-master-skills.git --path skills/a-stock-orchestrator--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add LeoYeAI/openclaw-master-skills --skill a-stock-orchestrator -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills a-stock-orchestrator --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/a-stock-orchestrator .gemini/skills/a-stock-orchestrator && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "a-stock-orchestrator" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/a-stock-orchestrator into .gemini/skills/a-stock-orchestrator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "a-stock-orchestrator", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install LeoYeAI/openclaw-master-skills a-stock-orchestratorInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add LeoYeAI/openclaw-master-skills --skill a-stock-orchestrator -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/a-stock-orchestrator .github/skills/a-stock-orchestrator && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "a-stock-orchestrator" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/a-stock-orchestrator into .github/skills/a-stock-orchestrator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "a-stock-orchestrator", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add LeoYeAI/openclaw-master-skills --skill a-stock-orchestrator -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills a-stock-orchestrator --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/a-stock-orchestrator .opencode/skills/a-stock-orchestrator && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "a-stock-orchestrator" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/a-stock-orchestrator into .opencode/skills/a-stock-orchestrator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "a-stock-orchestrator", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
a-stock-orchestratorA股投研指挥官 - 编排调度多个股票分析Skill,串联成完整投研流水线。支持四种模式:板块扫描、板块分析、个股深度分析、持仓体检。最终输出结构化投资简报并自动存档飞书。
A Stock Orchestrator is an agent skill from LeoYeAI/openclaw-master-skills. A股投研指挥官 - 编排调度多个股票分析Skill,串联成完整投研流水线。支持四种模式:板块扫描、板块分析、个股深度分析、持仓体检。最终输出结构化投资简报并自动存档飞书。
Its SKILL.md is about 2.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including reference files (for example `_meta.json`, `package.json` and `references/sub-skills.md`).
The repository describes itself as: 🧠 Curated collection of 1209+ best OpenClaw skills — weekly updated by MyClaw.ai. The licence is MIT.
3 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit e5199b5. It shows what the files ask for, not the result of running them.
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.
Shell commands in SKILL.md call:
pippython3aptFrom the folder's file list and the shell code blocks in SKILL.md.
Links to these hosts (documentation or services it may open):
vicyrpffceo.feishu.cnFrom URLs in SKILL.md, links to its own repository left out.
Names these keys or tokens, usually read from environment variables:
TRADINGAGENTS_TOKENFrom names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
A Stock Orchestrator loads about 2.9k tokens when it runs, and up to ~3.5k if it reads all its reference files. Until then it costs about 27 tokens; SKILL.md has 286 words of instructions outside code blocks.
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.
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); files beside SKILL.md are not scanned.
The full file from LeoYeAI/openclaw-master-skills at commit e5199b5, republished under its MIT licence (© LeoYeAI). 286 words, ~2,886 tokens.
.claude/skills/a-stock-orchestrator/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.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。
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 - 输出个股投资简报触发词:持仓、我的股票、体检、盈亏
流程:
Step 1 - 持仓汇总
调用 a-stock-portfolio-monitor(portfolio.py analyze)
→ 总盈亏、各股盈亏
Step 2 - 逐股体检
对每只持仓股执行模式三的 Step 1-5
→ 止损止盈建议
Step 3 - 调仓建议
综合所有持仓分析,输出:
- 建议卖出(触及止损/基本面恶化)
- 建议减仓(涨幅达标)
- 建议持有(趋势完好)
- 建议加仓(回调到位/基本面改善)
Step 4 - 输出持仓体检报告| 子 Skill | 用途 | 调用方式 |
|---|---|---|
| akshare-stock | 历史数据/财务/板块/资金流向 | 读取 SKILL.md 获取 API 调用方法,用 exec 执行 Python |
| a-stock-trading-assistant | 实时行情/热点板块 | exec 执行 scripts/fetch_stock.py |
| stock-research-engine | 深度研报(主力) | 读取 SKILL.md + references/analysis-framework.md,按框架执行 |
| stock-debate | 多空辩论(V2.1) | 读取 SKILL.md,按7步流程执行,采集时按需启停代理 |
| tradingagents-analysis | 多智能体分析(辅助) | 需 TRADINGAGENTS_TOKEN,exec 调用 API |
| a-stock-fundamental-screening | 基本面排雷 | 读取 SKILL.md 获取筛选规则 |
| a-stock-leader-identification | 龙头股识别 | 读取 SKILL.md 获取识别规则 |
| a-stock-volume-price | 量价关系验证 | 读取 SKILL.md 获取验证规则 |
| a-stock-kline-analyzer | 技术面A:K线形态+评分 | exec scripts/kline_analyzer.py --code XXX --days 60 --report |
| stock-kline-analysis | 技术面B:多时间框架+图表 | exec Python import fetch_kline + indicators + chart |
| stock-daily-analysis | 技术面C:LLM趋势判断 | exec Python import data_fetcher + trend_analyzer + ai_analyzer |
| a-stock-portfolio-monitor | 持仓管理 | exec 执行 scripts/portfolio.py |
| 场景 | 主数据源 | 说明 |
|---|---|---|
| 实时行情 | a-stock-trading-assistant | 东方财富/同花顺实时数据 |
| 历史 K 线 | akshare-stock | stock_zh_a_hist() |
| 财务指标 | akshare-stock | stock_financial_analysis_indicator() |
| 板块成分股 | akshare-stock | stock_board_industry_cons_em() |
| 资金流向 | akshare-stock | stock_individual_fund_flow() |
文档结构(2026-03-23 起):
写作原则:
# 📋 [股票名称](代码) 综合简报
> 生成时间:YYYY-MM-DD HH:MM | 数据截至:YYYY-MM-DD
## 🎯 一句话结论
[看多/看空/中性 + 理由,不超过30字]
## 💰 当前行情
| 项目 | 数值 | 什么意思 |
|------|------|----------|
| 最新价 | XX.XX | - |
| 今日涨幅 | +X.XX% | 涨了多少 |
| 成交额 | XX亿 | 交投是否活跃 |
## 📈 技术面分析(三家一起看,更靠谱)
### 三家观点对比
| 问题 | A方案(看K线) | B方案(多周期) | C方案(AI) | 一致吗? |
|------|-------|-------|-------|------|
| 什么趋势? | ... | ... | ... | ✅/⚠️/❌ |
| 动能如何? | ... | ... | ... | ✅/⚠️/❌ |
| 买还是卖? | ... | ... | ... | ✅/⚠️/❌ |
### 用人话解释
[每个方案用1-2段大白话总结核心观点]
[附带详细报告链接]
### 综合判断
[三方一致性分析 + 核心结论]
## 🛡️ 风险提示
| 风险等级 | 风险 | 说明 |
|----------|------|------|
| 🔴/🟡/🟢 | ... | ... |
## 💡 操作建议
| 项目 | 建议 | 说明 |
|------|------|------|
| 怎么做 | 买入/观望/卖出 | ... |
| 入场价 | XX元 | ... |
| 止损位 | XX元 | ... |
| 目标位 | XX元 | ... |
| 仓位 | XX% | ... |
**一句话操作指南**:[不超过40字的可执行建议]
## 📎 详细报告链接
- [方案A - K线形态分析](飞书链接)
- [方案B - 多时间框架分析](飞书链接)
- [方案C - AI趋势分析](飞书链接)
### 基本面
- ROE: XX%
- 营收增速: XX%
- ...
### 技术面综合分析(三方交叉验证)
#### 指标汇总
| 指标 | A方案(K线形态) | B方案(多时间框架) | C方案(AI趋势) | 共识 |
|------|-------|-------|-------|------|
| 趋势 | 多头/空头/震荡 | 日线/周线方向 | AI预测 | ✅/⚠️/❌ |
| MACD | 金叉/死叉 | 数值+方向 | - | ✅/⚠️ |
| RSI | 数值+区域 | 数值+区域 | - | ✅/⚠️ |
| 技术评分 | X分 | - | 情绪分X | 综合 |
| 买入信号 | 有/无 | - | 买入/观望/卖出 | ✅/⚠️ |
#### A方案要点(a-stock-kline-analyzer)
- 均线排列:MA5/MA10/MA20 排列状态
- MACD:DIF/DEA 数值及信号
- RSI:数值及区域判断
- 布林带:当前价格在布林带中的位置
- K线形态:锤子线/十字星/吞没等
- 量能分析:量比、换手率、量价关系
- 支撑位/压力位
#### B方案要点(stock-kline-analysis)
- 日线/周线/月线多时间框架共振
- ATR 波动率
- 布林带宽度
#### C方案要点(stock-daily-analysis AI分析)
- 趋势预测:上涨/下跌/震荡
- 操作建议:买入/持有/观望/卖出
- 置信度:高/中/低
- AI 核心判断
#### 综合判断
[三方一致性分析 + 核心结论]
## ⚠️ 免责声明
```markdown
## 🏭 板块概况
- 板块名称 / 概念
- 板块涨跌幅 / 资金净流入
- 近期热点新闻(3条以内)
## 🏆 龙头股
| 排名 | 股票 | 代码 | 涨幅 | 理由 |
|------|------|------|------|------|
## ⛔ 风险标的(排雷结果)
| 股票 | 代码 | 风险类型 | 原因 |
|------|------|----------|------|## 💼 持仓汇总
| 股票 | 成本 | 现价 | 盈亏 | 盈亏% |
|------|------|------|------|-------|
| **总计** | | | **+XX元** | **+X.X%** |
## 🔄 调仓建议
| 操作 | 股票 | 理由 |
|------|------|------|每次分析完成后,自动创建飞书文档存档。
EhQ6w2F5yiC0DKkxlzlcEMvIn2f(投研分析笔记)[日期] 个股分析 - 股票名称(代码)[日期] 每日板块扫描[日期] 板块分析 - 板块名称[日期] 持仓体检pip install tushare)Tushare Pro 作为主数据源(支持海外访问),Token 轮换配置在 config/tushare-tokens.json。
import tushare as ts
ts.set_token("从 config/tushare-tokens.json 读取")
pro = ts.pro_api()
# 日K线
pro.daily(ts_code='002460.SZ', start_date='20260101', end_date='20260322')
# 财务指标(需2000积分)
pro.fina_indicator(ts_code='002460.SZ')
# 资金流向(需5000积分)
pro.moneyflow(ts_code='002460.SZ')
# 板块成分股
pro.ths_member(ts_code='885756.TI')
# 每日行情
pro.daily(trade_date='20260322')备用数据源:a-stock-trading-assistant(腾讯财经,用于实时行情补充)
ta-sk-*# 可选,多智能体分析
export TRADINGAGENTS_TOKEN="ta-sk-xxx"
# 可选,自托管后端
# export TRADINGAGENTS_API_URL="https://your-server:8000"| 方案 | Skill | 核心能力 | 数据源 | 执行耗时 |
|---|---|---|---|---|
| A | a-stock-kline-analyzer | K线形态+量能+技术评分(-5~+5) | baostock | ~10s |
| B | stock-kline-analysis | 多时间框架+可视化图表 | tushare | ~8s |
| C | stock-daily-analysis | LLM趋势判断+情绪评分(0~100) | tushare+GLM | ~15s |
pip install baostock(方案A)pip install tushare(方案B/C),token 在 config/tushare-tokens.jsonconfig/stock-daily-analysis/config.json(方案C)apt install fonts-wqy-zenhei(方案B图表)pip install matplotlib(方案B图表)1. 生成图表 → /tmp/kline-{code}.png
2. feishu_create_doc 创建文档 → 获取 doc_id
3. 如果文档在 Wiki 中:
feishu_wiki_space_node(action="get", token="wiki_node_token") → obj_token
4. feishu_doc_media(action="insert", doc_id=obj_token, file_path="/tmp/...", type="image")© LeoYeAI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 3 other files (references) in skills/a-stock-orchestrator of LeoYeAI/openclaw-master-skills.
Open the folder on GitHubat commit e5199b5
A Stock Orchestrator 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| A Stock Orchestrator this skillLeoYeAI/openclaw-master-skills | 2.2k | — | ~2.9k | Automated safety check: Pass | MIT | |
| Team Agent Orchestrationaffaan-m/ECC | 277k | 1 repos | ~1.2k | Automated safety check: Pass | MIT | |
| Orca Orchestrationstablyai/orca | 89k | — | ~916 | Automated safety check: Pass | MIT | |
| Agent Orchestrator Taskruvnet/ruflo | 74k | 2 repos | ~1k | Automated safety check: Pass | MIT | |
| Orchestratesickn33/agentic-awesome-skills | 47k | 1 repos | ~692 | Automated safety check: Pass | MIT | |
| Swarm Orchestrationruvnet/ruflo | 74k | 1 repos | ~779 | Automated safety check: Pass | MIT |
affaan-m/ECC
Run team-based orchestration for agent squads: work items with owners and scope, agent Kanban state, branch isolation, control pane visibility, and merge gates.
stablyai/orca
Coordinate supervised Orca workers: threaded messages, blocking ask/reply, task dispatch, worker_done/escalation waits, task DAGs, decision gates, coordinator…
ruvnet/ruflo
Agent skill for orchestrator-task - invoke with $agent-orchestrator-task
sickn33/agentic-awesome-skills
Coordinate focused subagents on substantial work, keep their ownership non-overlapping, and integrate verified results.
ruvnet/ruflo
Coordinates a hierarchical swarm of specialized agents through the claude-flow CLI for work that spans several files or modules at once.
ruvnet/ruflo
Multi-agent swarm coordination for complex tasks. An agent skill from ruvnet/ruflo.
LeoYeAI/openclaw-master-skills
Manages pipelines on a DevOps quality and efficiency platform through its OpenAPI: list workspaces and templates, create, update, run and cancel pipelines, and read run records.
LeoYeAI/openclaw-master-skills
Patches OpenClaw's Feishu extension so an edited document triggers an isolated agent session that reads the doc and replies inline, turning it into a live chat space.
LeoYeAI/openclaw-master-skills
Multi-context memory management system for OpenClaw agents with group-isolated storage, global shared memory, workspace organization, and group-specific skills isolation.
LeoYeAI/openclaw-master-skills
Runs a brand's AI-search visibility work end to end: diagnosing how AI platforms represent it, repositioning it, producing AI-optimized content and monitoring ongoing mentions.
LeoYeAI/openclaw-master-skills
Installs and authenticates the gws CLI, then automates Gmail, Drive, Sheets, Calendar, Docs, Chat and Tasks with ready-made recipes, persona bundles and security audits.
LeoYeAI/openclaw-master-skills
Runs four advisor roles, a fitness coach, nutritionist, data analyst and TCM practitioner, to build a health profile and track workouts, diet and wellness over time.
A股投研指挥官 - 编排调度多个股票分析Skill,串联成完整投研流水线。支持四种模式:板块扫描、板块分析、个股深度分析、持仓体检。最终输出结构化投资简报并自动存档飞书。. A Stock Orchestrator is an agent skill from LeoYeAI/openclaw-master-skills.
Run `npx skills add LeoYeAI/openclaw-master-skills --skill a-stock-orchestrator -a claude-code`. Or copy the skill folder (skills/a-stock-orchestrator in LeoYeAI/openclaw-master-skills) into .claude/skills/a-stock-orchestrator in your project. Claude Code loads it when a task matches its description.
Run `npx skills add LeoYeAI/openclaw-master-skills --skill a-stock-orchestrator -a codex`. Or copy the skill folder (skills/a-stock-orchestrator in LeoYeAI/openclaw-master-skills) into .agents/skills/a-stock-orchestrator in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add LeoYeAI/openclaw-master-skills --skill a-stock-orchestrator -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/a-stock-orchestrator, .gemini/skills/a-stock-orchestrator, .github/skills/a-stock-orchestrator and .opencode/skills/a-stock-orchestrator in your project.
Going by SKILL.md and its folder, A Stock Orchestrator needs the command-line tools its instructions call (pip, python3 and apt) and credentials named TRADINGAGENTS_TOKEN. Our summary lists: Python 3; A credential in TRADINGAGENTS_TOKEN.
SKILL.md names 1 domain. As links in the text: vicyrpffceo.feishu.cn. This is read from the text; nothing was executed.
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. Review the folder before installing.
A Stock Orchestrator is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.9k tokens (SKILL.md is roughly 12k 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 635 tokens, read only when the agent opens those files.
Skills that share tags, products or a category with A Stock Orchestrator: Team Agent Orchestration (affaan-m/ECC, 277k stars), Orca Orchestration (stablyai/orca, 89k stars), Agent Orchestrator Task (ruvnet/ruflo, 74k stars) and Orchestrate (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.
LeoYeAI (a GitHub user) maintains it in LeoYeAI/openclaw-master-skills, which has 2,161 GitHub stars. The repository holds 1,235 skills in this directory. The repository was last updated on July 20, 2026.
Source: LeoYeAI/openclaw-master-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.