Technical Analyst
tradermonty/claude-trading-skills
This skill should be used when analyzing weekly price charts for stocks, stock indices, cryptocurrencies, or forex pairs.
QuantDB 字段单位速查手册 — 全部数据集实测验证的单位、口径与陷阱(个股 volume=股/amount=万元、指数 volume=手、L2原始逐笔 l2data/tickdata、technical % vs l1 小数、dividendrate 百分数、PG 前缀 symbol)。用 QuantDB…
$ npx skills add qusong0627/QuantMind --skill quantdb-fields -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install qusong0627/QuantMind quantdb-fields --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/qusong0627/QuantMind.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/quantdb-fields .claude/skills/quantdb-fields && 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 "quantdb-fields" agent skill from https://github.com/qusong0627/QuantMind/tree/master/skills/quantdb-fields into .claude/skills/quantdb-fields/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "quantdb-fields", 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/qusong0627/QuantMind/tree/master/skills/quantdb-fieldsType 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 qusong0627/QuantMind --skill quantdb-fields -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install qusong0627/QuantMind quantdb-fields --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/qusong0627/QuantMind.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/quantdb-fields .agents/skills/quantdb-fields && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "quantdb-fields" agent skill from https://github.com/qusong0627/QuantMind/tree/master/skills/quantdb-fields into .agents/skills/quantdb-fields/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "quantdb-fields", 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 qusong0627/QuantMind --skill quantdb-fields -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install qusong0627/QuantMind quantdb-fields --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/qusong0627/QuantMind.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/quantdb-fields .cursor/skills/quantdb-fields && 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 "quantdb-fields" agent skill from https://github.com/qusong0627/QuantMind/tree/master/skills/quantdb-fields into .cursor/skills/quantdb-fields/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "quantdb-fields", 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/qusong0627/QuantMind.git --path skills/quantdb-fields--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 qusong0627/QuantMind --skill quantdb-fields -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install qusong0627/QuantMind quantdb-fields --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/qusong0627/QuantMind.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/quantdb-fields .gemini/skills/quantdb-fields && 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 "quantdb-fields" agent skill from https://github.com/qusong0627/QuantMind/tree/master/skills/quantdb-fields into .gemini/skills/quantdb-fields/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "quantdb-fields", 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 qusong0627/QuantMind quantdb-fieldsInstalls 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 qusong0627/QuantMind --skill quantdb-fields -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/qusong0627/QuantMind.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/quantdb-fields .github/skills/quantdb-fields && 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 "quantdb-fields" agent skill from https://github.com/qusong0627/QuantMind/tree/master/skills/quantdb-fields into .github/skills/quantdb-fields/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "quantdb-fields", 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 qusong0627/QuantMind --skill quantdb-fields -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install qusong0627/QuantMind quantdb-fields --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/qusong0627/QuantMind.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/quantdb-fields .opencode/skills/quantdb-fields && 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 "quantdb-fields" agent skill from https://github.com/qusong0627/QuantMind/tree/master/skills/quantdb-fields into .opencode/skills/quantdb-fields/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "quantdb-fields", 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.
quantdb-fieldsQuantDB 字段单位速查手册 — 全部数据集实测验证的单位、口径与陷阱(个股 volume=股/amount=万元、指数 volume=手、L2原始逐笔 l2data/tickdata、technical % vs l1 小数、dividendrate 百分数、PG 前缀 symbol)。用 QuantDB…
Quantdb Fields is an agent skill from qusong0627/QuantMind. QuantDB 字段单位速查手册 — 全部数据集实测验证的单位、口径与陷阱(个股 volume=股/amount=万元、指数 volume=手、L2原始逐笔 l2data/tickdata、technical % vs l1 小数、dividendrate 百分数、PG 前缀 symbol)。用 QuantDB 数据做分析/回测/报告、判断成交量/成交额/股息率/换手率单位、读逐笔委托/成交/十档盘口、排查数据口径不一致时使用。触发词:字段单位、成交量单位、成交额单位、股还是手、万元、股息率、数据口径、L2、逐笔、委托、成交明细、十档盘口、tickdata、wind
Its SKILL.md is about 3.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Business, Finance & HR. The repository describes itself as: QuantMind(量化大脑)开源版是一款面向个人开发者与投研团队的 AI 原生多市场量化交易平台。深度集成微软 Qlib、RD-Agent 因子演化与 QuantBot全能工作台,提供从 300+ 维因子挖掘、13 种机器学习与深度学习模型工场、Qlib 高性能回测、截面批量推理、7x24… The licence is AGPL-3.0.
3 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit 17c9e29. 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:
pythonFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Quantdb Fields loads about 3.1k tokens when it runs. Until then it costs about 76 tokens; SKILL.md has 1,019 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 qusong0627/QuantMind at commit 17c9e29, republished under its AGPL-3.0 licence (© qusong0627). 1,019 words, ~3,150 tokens.
.claude/skills/quantdb-fields/SKILL.md (or your agent's skills folder).⚙️ 本技能遵循公共运行环境契约(最高优先级,先于本文其余内容执行): 详见 _shared/env-contract.md,执行前先读它。
用 QuantDB 数据做任何分析/回测/报告前必读。所有单位均为 2026-08 直接读本地 parquet 实测验证(不是照抄文档)。 单位搞错的后果:成交额差 1 万倍、股息率差 100 倍、换手率差 100 倍—— 分析结论全部作废。
| 规则 | 说明 |
|---|---|
| 个股 OHLC = 元 | 开高低收统一为人民币元(与市值同量纲) |
| 个股成交量 = 股 | A 股 1 手 = 100 股,但 QuantDB 个股 kline 的 volume 单位就是股,不是手 |
| 个股成交额 = 万元 | amount = 5828.37 表示 5828.37 万元(约 5828 万),不是元 |
| 指数成交量 = 手 | index_daily.volume 单位是手(1 手 = 100 股),与个股相反! |
| 市值 = 元 | valuation 的 total_mv/float_mv 单位是元(工业富联 float_mv ≈ 1.31 万亿) |
| 比例字段 ≈ 小数或 % | 没有统一约定,按数据集查下表;% 的字段值 = 百分数(4.06 即 4.06%) |
| symbol 格式按数据源分 | parquet 用后缀 601138.SH;PG 的 stock_daily_latest 用前缀 SH601138 |
| 验证公式 | 个股 close*volume/amount ≈ 1e4(股+万元);指数 ≈ 2e4(手+万元) |
| 字段 | 单位 | 实测依据 |
|---|---|---|
volume | 股 | 601138 20260814 volume=4704920 股,amount=5828.37 万元,close*volume/amount≈1e4 |
amount | 万元 | 同上(close 66.19 × 470 万股 ≈ 3.1 亿 ≈ 31163 万元,与 amount 同量级吻合) |
open/high/low/close | 元(forward=前复权,backward=后复权,unadjusted=不复权) | |
| 单位切换传闻 | 不存在。20260721 前后 amount 均为万元、volume 均为股。曾有记忆说 20260721 切换到"手/元",实测已无此切换,按股/万元统一处理 |
min1/min5:同单位(volume=股、amount=万元),但数据停滞在 2026-07-24,用前先查最新日期。
万得(Wind) L2 数据,backend/scripts/wind_l2_import.py 从逐日 7z 压缩包(20260511.7z)导入。
当前实测只有 1 个交易日 20260511(order 1950 + trade 1721 = 3671 文件,部分标的仅其一),
用前先查日期覆盖:ls data/quantdb/1_kline_data/l2_data/ | grep -oE '[0-9]{8}' | sort -u。
文件命名:order_{code}_{date}.parquet / trade_{code}_{date}.parquet,code 为下划线格式
000001_SZ(对应后缀 000001.SZ)。time 单位统一为 UTC 毫秒(万得 hhmmssmmm 转 UTC,
北京 09:15:00 = 01:15:00 UTC),覆盖 09:15 集合竞价到 15:00 收盘。
| 字段 | 单位/格式 | 说明 |
|---|---|---|
time | UTC ms | 09:15 集合竞价 → 15:00 收盘 |
order_id | int | 交易所委托号(可与 trade_.ask_order_id/bid_order_id 配对) |
channel | str | 委托编号 |
order_type | str | '0'=普通委托、'U'=撤单、'1'=其余 |
direction | str | 'B'=买 / 'S'=卖 |
price | 元 | 万得 ×10000 → 元(已归一);集合竞价未定价委托 price=0 |
volume | 股 |
| 字段 | 单位/格式 | 说明 |
|---|---|---|
time | UTC ms | 同上 |
trade_id | int | 成交编号 |
trade_type | str | 'C'=集合竞价成交 / '0'=连续竞价 |
direction | str | 'B'/'S'/' '(集合竞价段=空格) |
price | 元,未复权 | 与 daily_unadjusted 对齐(实测 000001.SZ 20260511 末笔 11.28 = unadjusted close 11.28);与 daily_forward 前复权 close 有除权差(有分红送转者差数十%) |
volume | 股 | ⚠️ 沪≈日线量、深≈2×日线量(见坑1) |
ask_order_id / bid_order_id | int | 叫卖/叫买序号 → 配对逐笔↔委托 |
| 列 | 单位 | 说明 |
|---|---|---|
lastPrice/open/high/low/lastClose | 元 | |
amount | 混源 | ⚠️ 见坑2 |
volume | 混源 | 当日累计成交量 |
pvolume | 笔 | 连续竞价成交笔数(wind 导入有值);旧导入=0(可作来源判据) |
askPrice/bidPrice | array(10) | 十档价,元 |
askVol/bidVol | array(10) | 十档量,股 |
stockStatus | int | BS 标志 |
openInt/settlementPrice/lastSettlementPrice | — | 期货占位字段,A股多为 0 |
pvolume(0=旧/手·元,>0=wind/股·万元)区分。python backend/scripts/wind_l2_import.py --archive /path/to/20260511.7z # 全市场
python backend/scripts/wind_l2_import.py --archive ... --symbols 000001.SZ,600519.SH # 指定标的
python backend/scripts/wind_l2_import.py --archive ... --force # 覆盖重导文件名即日期(20260511.7z → 20260511),流式逐股解压导入、可断点续跑(已存在三件套自动跳过)。
容器内 7z 默认 /opt/p7zip-legacy/bin/7z,数据目录自动探测 /data/quantdb 或本地 data/quantdb。
| 字段 | 单位 | 实测依据 |
|---|---|---|
volume | 手(×100=股) | 上证 000001.SH 20260814 volume=499525600 手 = 499.5 亿股(合理);close*volume/amount=19808≈2e4 |
amount | 万元 | 99037192 万元 = 9903.7 亿元 ≈ 上证单日成交额 ✓ |
close | 点位 | 3927.18 |
反推:指数平均股价 = close×100/(close×volume/amount) = close×100/19808 ≈ 19.8 元/股,符合 A 股平均股价,故 volume 必为手。
| 字段 | 单位 | 注意 |
|---|---|---|
close | 元,不复权 | 601138 close=66.19(与 technical_indicators 的后复权 close=70.05 不同) |
total_mv / float_mv | 元 | float_mv=1313480468277.96 ≈ 1.31 万亿 ✓ |
total_capital / circulating_capital | 股 | 19844092284 股 ≈ 198.4 亿股 |
net_profit_ttm / revenue_ttm / equity / annual_net_profit | 元 | |
pe_ttm / pe_static / pb / ps_ttm | 倍 | |
dividend_rate | %(百分数值) | 0.148 = 0.148%!公式 = 近一年每10股派息/10/close×100。601138: 0.98/10/66.19×100=0.1481 ✓;600519: 51.98/10/1341.99×100=0.3873 ✓。把它当小数会差 100 倍 |
dividend_rate 口径切换 | 20260814 起 | 此前为小数口径(每10股派息/不复权close,如 0.98/65.60=0.01494);20260814 起切换为百分数口径(×100)。同字段历史不连续,跨 20260814 分析需 ×10 归一 |
| 字段 | 单位 | 陷阱 |
|---|---|---|
close | 后复权 | 601138=70.05,与不复权 66.19 不同;凡基于 close 算的指标都是后复权口径 |
volume_ma_3/5 | 股 | |
amount_ma_5 | 万元 | |
pct_change | % | 1.4717 = 1.47% |
future_return_1d / future_return_20d | 未来 N 日收益(标签) | 2026-09 由 return_Nd 改名;勿当历史动量或过滤条件(标签泄漏)。历史动量用 pct_change / l1 mom_ret_* |
vol_std_20 | % | 4.0578 = 4.06%(l1 里同名字段是小数 0.0406,差 100 倍!) |
vol_atr_14 | 元 | 3.58 元(l1 同名字段也是元,一致) |
macd_hist / rsi_14 / kdj_* | 原始指标值 | 与 l1 一致 |
| 字段 | 单位 |
|---|---|
close | 不复权 |
turnover_rate 等比率 | 小数(0.02 = 2%) |
momentum_* | %(百分数值) |
基础 46 个数值列单位与 technical_indicators / valuation 一致;新增 30 列全部以字符串存储,用前先转数值:
| 字段 | 单位 | 实测/注意 |
|---|---|---|
dividend_rate | 小数口径(无 ×100) | 与 valuation 不同!公式 = 每10股派息/不复权close(0.98/66.19=0.0148),从未切换口径。valuation 20260814 起是它的 10 倍。特征快照 generate_feature_snapshots.py 已 ×10 归一到百分数口径 |
total_mv / float_mv / pe / pb 等 | 与 valuation 完全一致 | 实测 601138 全部 ✓ |
total_cap_yi / float_mv_yi | 亿元 | 实测 ×1e8/total_mv=1.000、×1e8/float_mv=1.000(与本表 total_mv/float_mv(元)差 1e8) |
free_float_shares | 万股(自由流通股本) | ×1e4 转股;000001.SZ=816056.58 万股≈81.6 亿股(自由流通 < 流通股本,勿与 circulating_capital 混用) |
hs_turnover | %(换手率) | 如 0.43 / 1.71,max≈76 |
zaf | %(当日涨跌幅) | 与 pct_change 高度一致(corr=0.986,-0.93 vs -0.928) |
seal_strength | 无量纲(封板强度,≈1.0 封住) | 如 1.02 |
ever_zt_count / year_zt_days | 计数(整数) | 曾涨停次数 / 年内涨停天数 |
ipo_price | 元 | 发行价 |
zt_price / dt_price | 元(基于不复权价) | 涨停价/跌停价;⚠️ 与表内前复权 close 不同口径(勿直接比;000001.SZ: zt=13.04/dt=10.67 vs 前复权 close=18.16) |
beta_now | 无量纲(beta) | 与 beta_20 corr≈0.71(窗口/口径不同) |
dyna_pe / static_pe_ttm | 倍 | ⚠️ 含负哨兵(实测 -686 / -897),亏损股勿直接用 |
div_yield | %(百分数值) | 5.14=5.14%;与本表 dividend_rate(小数 0.0508)差 100 倍 |
pb_mrq | 倍 | ≈pb(pb_mrq/pb median=1.000) |
list_date | 字符串 YYYYMMDD | 如 '19910403' |
industry_code / industry_name | 字符串 | 128 细分行业(X5001 / 全国性银行) |
sector_code | 字符串 | 如 881386 |
region_area_code / region_area_name | 字符串 | 32 地区板块(18 / 深圳板块) |
main_business | 中文文本 | 主营业务 |
in_hs300 / is_hsgt / is_margin / is_kcb_creatable / is_st / is_quit_risk / is_hk | 字符串 '0'/'1' | 标记位(转 int 后再过滤/统计) |
| 字段 | 单位 |
|---|---|
收益率类 mom_ret_* | 小数(0.0147 = 1.47%) |
vol_std_* | 小数(0.0406 = 4.06%;与 technical_indicators 的 % 版本差 100 倍) |
vol_atr_14 | 元(3.55 元) |
fun_total_mv | ln(市值元) —— 用时要 exp() |
| 分位数/percentile 字段 | 0~1 小数 |
liq_* / fun_turnover / fun_mv | 部分日期为 None,注意补缺 |
| 字段 | 单位 | 实测依据 |
|---|---|---|
flow_net_amount / flow_buy/sell / flow_super/large/medium/small_net | 万元(2026-09 起) | 与同表 amount 同量纲:flow_net_amount/amount≈flow_net_ratio;此前为元(flow/(amount×1e4)≈ratio) |
flow_*_ratio | 小数 | |
vol_turnover_total | 股 | 与 kline volume 完全相等 ✓ |
| 分区 | 已恢复日更 | ⚠️ top 少数净流入可能厂商同值封顶 |
读入归一:backend/shared/quantdb_flow_units.py 自动把万元→元(兼容旧分区),下游再 /1e8→亿、×1e-6→百万元。
flow 灌入口径(update_sdl_complete_pipeline.py):假定源为元时 /1e6→百万元;新版万元源须先 ×1e4。
| 列 | 单位 / 格式 | 实测依据 |
|---|---|---|
symbol | 前缀格式 SH601138(不是 601138.SH) | suffix 查询 0 行,prefix 查询 1072 万行 |
volume | 股 | 601138 max_volume=633217088 股 |
amount | 万元 | 601138 amount=5828.37,max_amount=3306339(万元) |
float_mv / total_mv | 元 | float_mv=7095151630 元 |
turnover_rate / flow_net_amount / main_flow | NULL(未灌) | 风险评分里"缺少换手率"由此而来 |
volume_ratio_5 | 倍(0.934) |
API 层 _UNIT_SCALES 把部分字段缩放后输出(L2 金额先归一为元):
| 输出字段 | 缩放 | 输出单位 | 例 |
|---|---|---|---|
totalMv / floatMv | ×1e-8 | 亿元 | |
mainFlow / flowNetAmount / flowLargeNet / flowMediumNet / flowSmallNet / flowSuperNet | ×1e-6 | 百万元 | 统一口径 |
turnoverRate | — | % 小数 |
| 数据集 | 字段 | 单位 |
|---|---|---|
balance / income / cashflow | 各科目 | 元 |
capital | 股本 | 股 |
holder_num | 股东户数 | 户 |
dividend_factors | interest | 每10股派息(元)——600519 每10股派 51.98 元,601138 派 0.98 元。算每股股息要 /10 |
dividend_factors | stockBonus / stockGift / allotNum | 每10股送/转/配股数 |
dividend_factors | dr | 除权因子(复权用) |
| 数据集 | 字段 | 单位 | 注意 |
|---|---|---|---|
instrument_detail | Symbol | 后缀 601138.SH | HqDate 停滞 20260720,市值/估值滞后 |
J_zgb / FreeLtgb | 万股(1984409.25 万股 = 198.4 亿股) | 与 valuation 的 circulating_capital(股) 差 1e4 | |
J_yysy / J_jly / J_zzc 等 J_* | 万元(25107808 万 = 251 亿) | 与 financials 的元差 1e4 | |
Zsz / Ltsz | 亿元(11211.91 亿 ✓) | ||
J_mgsy | 元(2.14 元/股) | ||
fHSL | 不明(0.56,非换手率%,与自算 0.74% 不符),别当换手率用 | ||
TotalBVol | 不明(43555,量级像手,但远小于全天量) | L2 快照字段,非全天 | |
DYRatio | 不可靠(600519=4.15 vs 真实 0.39%),别当股息率,用 valuation.dividend_rate | ||
Yield | 不明(6078.44),勿用 | ||
index_weights | Weight | % | 文件名 000300.SH.parquet 不是 000300.parquet |
trading_calendar | TradingDate | YYYYMMDD int |
| 数据集 | 字段 | 单位 | 状态 |
|---|---|---|---|
margin_trading | finance_* | 万元 | |
slo_volume / slo_net | 股 | ||
hsgt_north | holding_quantity 股 / holding_value 元 / 比率 % | 停滞 2024-08(北向改季度披露后) |
future_return_*(旧 return_*)是未来收益标签,勿当历史动量过滤wind_l2_import.py),非自动日更© qusong0627, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in skills/quantdb-fields of qusong0627/QuantMind.
Open the folder on GitHubat commit 17c9e29
Quantdb Fields 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 |
|---|---|---|---|---|---|---|
| Quantdb Fields this skillqusong0627/QuantMind | 1.7k | — | ~3.1k | Automated safety check: Pass | AGPL-3.0 | |
| Technical Analysttradermonty/claude-trading-skills | 3k | 5 repos | ~4.6k | Automated safety check: Pass | MIT | |
| Creating Financial ModelsChen-zexi/open-ptc-agent | 730 | 4 repos | ~1.3k | Automated safety check: Pass | MIT | |
| Theme Detectortradermonty/claude-trading-skills | 3k | 2 repos | ~4.9k | Automated safety check: Pass | MIT | |
| Stock APIzhangxiangliang/stock-api | 2k | — | ~507 | Automated safety check: Pass | MIT | |
| Itr Walakaranb192/itr-wala | 871 | — | ~3.6k | Automated safety check: Pass | MIT |
tradermonty/claude-trading-skills
This skill should be used when analyzing weekly price charts for stocks, stock indices, cryptocurrencies, or forex pairs.
Chen-zexi/open-ptc-agent
This skill provides an advanced financial modeling suite with DCF analysis, sensitivity testing, Monte Carlo simulations, and scenario planning for investment decisions
tradermonty/claude-trading-skills
Detect and analyze trending market themes across sectors. An agent skill from tradermonty/claude-trading-skills.
zhangxiangliang/stock-api
Fetch real-time stock quotes, K-line (candlestick) history, and search symbols for China A-shares, Hong Kong, and US markets.
karanb192/itr-wala
File Indian income tax returns (ITR) for FY 2025-26 / AY 2026-27.
zillionare/zillionare
面向中文自然语言的 Tushare 数据研究技能。用于把“看看这只股票最近怎么样”“帮我查财报趋势”“最近哪个板块最强”“北向资金在买什么”“给我导出一份行情数据”这类请求,转成可执行的数据获取、清洗、对比、筛选、导出与简要分析流程。适用于 A 股、指数、ETF/基金、财务、估值、资金流、公告新闻、板块概念与宏观数据等研究场景。
qusong0627/QuantMind
Produces a post-market review report for the China A-share market from local QuantDB data, news sentiment and model signals, ending in a next-day direction call.
qusong0627/QuantMind
Queries Futu quotes, options, fundamentals and accounts and places orders through the Futu OpenAPI Python SDK, defaulting to simulated trading.
qusong0627/QuantMind
Turns a plain-language model training request into a validated QuantMind training config file that can be imported from the Model Training page.
qusong0627/QuantMind
Covers the Tiger Brokers OpenAPI Python SDK for market data, stock, futures and options trading, push subscriptions, a CLI and an MCP server, defaulting to paper trading.
qusong0627/QuantMind
Guides an agent through the Tiger Brokers OpenAPI C++ SDK for build setup, market data, orders and real-time push, defaulting to paper trading.
qusong0627/QuantMind
Guides building C# and .NET apps on the Tiger Brokers OpenAPI SDK: setup, market data, orders, accounts, options and real-time push, defaulting to paper trading.
Categories
QuantDB 字段单位速查手册 — 全部数据集实测验证的单位、口径与陷阱(个股 volume=股/amount=万元、指数 volume=手、L2原始逐笔 l2data/tickdata、technical % vs l1 小数、dividendrate 百分数、PG 前缀 symbol)。用 QuantDB…. Quantdb Fields is an agent skill from qusong0627/QuantMind.
Quantdb Fields fits situations like: business, Finance & HR work in your project.
Run `npx skills add qusong0627/QuantMind --skill quantdb-fields -a claude-code`. Or copy the skill folder (skills/quantdb-fields in qusong0627/QuantMind) into .claude/skills/quantdb-fields in your project. Claude Code loads it when a task matches its description.
Run `npx skills add qusong0627/QuantMind --skill quantdb-fields -a codex`. Or copy the skill folder (skills/quantdb-fields in qusong0627/QuantMind) into .agents/skills/quantdb-fields 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 qusong0627/QuantMind --skill quantdb-fields -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/quantdb-fields, .gemini/skills/quantdb-fields, .github/skills/quantdb-fields and .opencode/skills/quantdb-fields in your project.
Going by SKILL.md and its folder, Quantdb Fields needs the command-line tools its instructions call (python). Our summary lists: Python 3.
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.
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.
Quantdb Fields is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 3.1k tokens (SKILL.md is roughly 13k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Quantdb Fields: Technical Analyst (tradermonty/claude-trading-skills, 3k stars), Creating Financial Models (Chen-zexi/open-ptc-agent, 730 stars), Theme Detector (tradermonty/claude-trading-skills, 3k stars) and Stock API (zhangxiangliang/stock-api, 2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
qusong0627 (a GitHub user) maintains it in qusong0627/QuantMind, which has 1,711 GitHub stars. The repository holds 27 skills in this directory. The repository was last updated on October 6, 2026.
Source: qusong0627/QuantMind on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.