Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add bobby1129/stock-analysis-pro --skill stock-analysis-progit clone --depth 1 https://github.com/bobby1129/stock-analysis-proWrote 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.
[](https://agentmods.dev/skills/bobby1129/stock-analysis-pro/stock-analysis-pro)<a href="https://agentmods.dev/skills/bobby1129/stock-analysis-pro/stock-analysis-pro"><img src="https://agentmods.dev/badge/skills/bobby1129/stock-analysis-pro/stock-analysis-pro/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.
<a href="https://agentmods.dev/skills/bobby1129/stock-analysis-pro/stock-analysis-pro"><img src="https://agentmods.dev/badge/skills/bobby1129/stock-analysis-pro/stock-analysis-pro.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00037 | $0.02870 |
| Opus 5.5 | $0.00015 | $0.01148 |
| Sonnet 5.5 | $0.00007 | $0.00574 |
| Haiku 4.5 | $0.00004 | $0.00287 |
Grade A, and why
chinese-stock-analysis 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.
chinese-stock-analysis (stock-analysis-pro)
A股全维度分析 + ETF 期权分析工具,覆盖个股深度分析、概念板块扫描、宏观市场概览、每日复盘、ETF 期权扫描五大核心功能。
首次安装
# 1. 克隆到 ~/.hermes/skills/ 下
git clone https://github.com/bobby1129/stock-analysis-pro.git ~/.hermes/skills/stock-analysis-pro
cd ~/.hermes/skills/stock-analysis-pro
# 2. 安装依赖
pip install -r requirements.txt
# 3. 安装 Playwright 浏览器 (用于东财F10/股吧/研报采集, 概念板块用HTTP API不需要)
playwright install chromium
# 4. 配置
cp config/config.example.yaml config/config.yaml
# 编辑 config.yaml,填入东财 Cookie (见下方说明)
# 如有代理需求,配置 proxy.https 或设置 HTTPS_PROXY 环境变量
Cookie 获取步骤:
- 浏览器打开 https://quote.eastmoney.com/bk/
- F12 → Network → 刷新页面
- 找到
push2.eastmoney.com请求 - 复制 Request Headers 中的 Cookie 值
⚠️ Cookie 有效期 1-7 天,过期后概念板块功能降级为离线缓存模式。
验证安装
# 1. 验证基本功能(不需要Cookie)
python core/cli.py analyze 600519 --brief
# 预期输出:贵州茅台 实时价格 + PE/PB/市值
# 2. 验证概念板块(需要有效Cookie)
python core/cli.py concept
# 预期输出:Top10概念列表 + 成分股分析
# 如果提示Cookie过期,按提示重新获取
# 3. 验证HTML报告
python core/cli.py analyze 600519 --html
# 预期输出:output/stock_600519.html 生成
如果第1步就失败,检查:
playwright install chromium是否执行成功pip install -r requirements.txt是否完整config/config.yaml是否存在(从config.example.yaml复制)
命令参考
所有命令在项目根目录下执行:
# ── 每日复盘 ──
python core/cli.py review # 文本输出
python core/cli.py review --html # HTML 报告(推荐,微信/浏览器查看)
# ── ETF 期权扫描 ──
python core/cli.py options # 全合约扫描(卖方+买方机会)
python core/cli.py options --top 10 # 取前10个
python core/cli.py options --symbol 510050 # 指定标的(默认自动检测)
# ── 持仓管理 ──
python core/cli.py portfolio # 查看持仓(默认list)
python core/cli.py portfolio --action list # 查看持仓
python core/cli.py portfolio --action add --code 603893 --name 瑞芯微
python core/cli.py portfolio --action rm --code 603893
python core/cli.py portfolio --action update --code 603893 --cost 120 --shares 100
# ── 个股分析 ──
python core/cli.py analyze 600519 # 全维度分析 (文本)
python core/cli.py analyze 600519 --html # HTML 报告
python core/cli.py analyze 600519 --json # JSON 输出
python core/cli.py analyze 600519 --brief # 简要模式
# ── 概念板块扫描 ──
python core/cli.py concept # 资金流入 Top10
python core/cli.py concept --html # HTML 报告
# ── 宏观市场概览 ──
python core/cli.py market # 文本输出
python core/cli.py market --html # HTML 报告
# ── 自选股 ──
python core/cli.py add 600519 # 加入自选
python core/cli.py rm 600519 # 移除
python core/cli.py list # 查看列表
python core/cli.py analyze-all # 批量分析自选股
What ships with it
54 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.
- data/daily_content/sentiment_20260918.json 366 B
- data/economic_calendar.json 7.9 KB
- data/em_concept_list.json 40 KB
- data/stock_concept_map.json 411 KB
- data/ths_concept_885_mapping.json 10 KB
- data/ths_industry_881_mapping.json 2.5 KB
- scripts/build_ths_885_mapping.py 2.2 KB runs code
- scripts/build_ths_industry_mapping.py 1.2 KB runs code
- scripts/check_concept_mapping.py 5.9 KB runs code
- scripts/daily_content/cache_dates.py 2.9 KB runs code
- scripts/daily_content/CONCEPT_RESEARCH.md 3.2 KB
- scripts/daily_content/generate_anomaly.py 11 KB runs code
- scripts/daily_content/generate_concept_html.py 15 KB runs code
- scripts/daily_content/generate_ignition_html.py 13 KB runs code
- scripts/daily_content/generate_ignition.py 39 KB runs code
- scripts/daily_content/generate_matrix.py 31 KB runs code
- scripts/daily_content/generate_new_top50.py 18 KB runs code
- scripts/daily_content/generate_review_cards.py 13 KB runs code
- scripts/daily_content/generate_stock_amount.py 16 KB runs code
- scripts/daily_content/llm_industry.py 8.4 KB runs code
- scripts/daily_content/llm_label_filter.py 8.7 KB runs code
- scripts/daily_content/measure_layout.py 1.5 KB runs code
- scripts/daily_content/prototype_market_heatmap.py 10 KB runs code
- scripts/daily_content/prototype_ruler3_top10.py 12 KB runs code
- scripts/daily_content/prototype_treemap.py 12 KB runs code
- scripts/daily_content/render_frames.py 1.4 KB runs code
- scripts/daily_content/render_one.py 869 B runs code
- scripts/daily_content/run_all.py 7.4 KB runs code
- scripts/daily_content/stock_short_names.py 545 B runs code
- scripts/daily_content/test_p1_worst.py 2.0 KB runs code
- scripts/daily_content/verify_4zone.py 2.2 KB runs code
- scripts/daily_content/verify_flow_quality.py 3.0 KB runs code
- scripts/daily_content/verify_normalized.py 3.0 KB runs code
- scripts/daily_content/verify_quadrant.py 3.2 KB runs code
- scripts/test_extreme_mode.py 13 KB runs code
- scripts/test_llm_interpret.py 10 KB runs code
- scripts/test_sentiment_cycle.py 6.4 KB runs code
- scripts/test_verify_guidance.py 9.6 KB runs code
- scripts/verify_881_mainforce.py 1.2 KB runs code
- scripts/verify_kline_fallback.py 8.0 KB runs code
- scripts/verify_similar_pattern.py 4.8 KB runs code
- templates/base.html 6.0 KB
- templates/components/collapsible.html 611 B
- templates/components/data_table.html 406 B
- templates/components/metric_grid.html 496 B
- templates/components/progress_bar.html 892 B
- templates/components/score_gauge.html 1.2 KB
- templates/components/signal_badge.html 568 B
- templates/concept_report.html 18 KB
- templates/global_macro.html 11 KB
- templates/industry_screener.html 20 KB
- templates/options_report.html 10 KB
- templates/review_report.html 44 KB
- templates/stock_report.html 28 KB
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.
- 1mo ago Changed · +1 lines 303acf54df1b
- 1mo ago Changed 946f513ab57e
- 2mo ago Changed ccfba65c2c26
- 2mo ago First seen · 248 lines · 37 tokens per session scan A 6ca611892fde
chinese-stock-analysis is a skill published in the GitHub repository bobby1129/stock-analysis-pro (25 stars, last pushed yesterday), licensed MIT. It adds 37 tokens to every session and 2,870 once invoked, about $0.0001 per session on Opus 5.5. 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.
chinese-stock-analysis compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| chinese-stock-analysisbobby1129/stock-analysis-pro | Skill | 25 | yesterday | MIT | A | 37 | Claude Code, Codex |
| sector-rotationHKUDS/Vibe-Trading | Skill | 38k | yesterday | MIT | A | 39 | Claude Code, Codex |
| twitter-readerhimself65/finance-skills | Skill | 3.5k | 2d ago | MIT | A | 110 | Claude Code |
| strategy-pivot-designertradermonty/claude-trading-skills | Skill | 3.7k | 2d ago | MIT | A | 28 | Claude Code, Codex |
| energy-procurementhashgraph-online/awesome-codex-plugins | Skill | 1.5k | yesterday | Apache-2.0 | A | 93 | Claude Code, Codex |
| airdrop-hunting-guidenirholas/three.ws | Skill | 269 | yesterday | Apache-2.0 | A | 54 | Claude Code, Codex |
| multi-expert-analyzerdigoal/blog | Skill | 8.6k | 2d ago | GPL-2.0 | A | 292 | Codex |