Quantdb Data Structure

What it does

When your agent uses it

• Tasks that involve DataFrames

Example prompts

• “/quantdb-data-structure”

Requirements

• Docker
• A credential in QUANTDB_API_KEY

Workflow steps

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

1. 1分区型：<数据集>/dt=YYYYMMDD/data.parquet。dt 是 Hive 分区列，整数（如 20260828），DuckDB 过滤 WHERE dt BETWEEN 20260101 AND 20260828 可走谓词下推，不要写字符串。
2. 2单文件型：<数据集>/{symbol}.parquet（财务报表、分钟K）或整表单文件（instrument_detail.parquet），用 pd.read_parquet 直读。
3. 3混合格式：6_ml_datasets/l1_factors/ 同时存在平铺 l1_factors_YYYYMMDD.parquet 与 dt=YYYYMMDD/ 分区——只读 dt=* 分区目录，避免混入平铺文件。
4. 4北向资金特殊：2_base_sector/hsgt_north/ 日频在 daily_freq/*.parquet（无分区），季度快照用 quarter=YYYYQN Hive 分区（2024-08 起季度披露）。

What it can do on your machine

Read from SKILL.md and the folder at commit 17c9e29. 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

  Shell commands in SKILL.md call:

  • docker

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md. Its commands use docker, which can reach the network depending on how they are called.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names these keys or tokens, usually read from environment variables:

  • QUANTDB_API_KEY

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Quantdb Data Structure loads about 1.3k tokens when it runs. Until then it costs about 108 tokens; SKILL.md has 234 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~108

When it runs · the whole SKILL.md, loaded when a task matches

~1.3k

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

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.

SKILL.md

The full file from qusong0627/QuantMind at commit 17c9e29, republished under its AGPL-3.0 licence (© qusong0627). 234 words, ~1,282 tokens.

name

quantdb-data-structure

description

QuantDB 服务器数据结构与读取口径 — 数据目录组织（1_kline_data~6_ml_datasets）、Hive 分区规律（dt=YYYYMMDD 整数）、单文件 {symbol}.parquet、parquet 后缀式代码 600519.SH 与 PG 前缀式 SH600519 的转换口径、quantdb_hub.py 单一读取入口与 DuckDB 视图清单、服务器路径映射（/opt/quantmind/data/quantdb → 容器 /data/quantdb）。凡需要读写/探查/补数/验证 QuantDB 本地 parquet 数据、查目录结构、写 DuckDB 查询、排查查不到数据问题时使用。触发词：quantdb 结构、数据目录、dt 分区、hive 分区、parquet 路径、数据在哪里、600519.SH、代码格式、qdb_ 视图、quantdb_hub、增量同步、数据缺失排查

SELECT * FROM read_parquet('/data/quantdb/1_kline_data/daily_forward/dt=20260828/data.parquet')
WHERE symbol = '600519.SH';

# 目录与体量
ls /opt/quantmind/data/quantdb && du -sh /opt/quantmind/data/quantdb/*

# 容器内可见性
docker exec quantmind ls /data/quantdb

# 某交易日数据是否到位（以日K为例）
ls /opt/quantmind/data/quantdb/1_kline_data/daily_forward/dt=20260828/

© 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

Files

Just SKILL.md in skills/quantdb-data-structure of qusong0627/QuantMind.

Open the folder on GitHubat commit 17c9e29