daily-review SKILL.md skillA

daily-review from qusong0627/quantmind is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add qusong0627/quantmind/daily-review@git:20261003.8b2ea6a

Pins git:20261003.8b2ea6a in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
qusong0627/quantmind
Path
skills/daily-review/SKILL.md
Versions recorded
5
Latest version
git:20261003.8b2ea6a, committed Oct 3, 2026
First version recorded
Aug 29, 2026
Size
13,991 bytes
Repository stars
1,774
License
AGPL-3.0

A股每日复盘(专业版)— 基于 QuantDB 本地数据 + 当日新闻情绪 + 模型推理信号 + L1/L2 因子截面 + 板块资金流的盘后复盘:指数、涨跌结构与涨停梯队、量能、行业/概念轮动、资金面、L2 微观结构、当日有新闻股票匹配、模型推理信号复盘(昨日推理命中率 + 明日信号Top5)、次日走势方向研判(六维信号加权 → 明确方向+置信度)。用户说「复盘」「每日复盘」「复盘某天」时使用:跑取数脚本(daily_review + news_review)→ 按模板写复盘报告 → 转 PDF → 落盘股票报告目录 → 聊天回复速览。触发词:复盘、每日复盘、今日复盘、盘后复盘、复盘20260814.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

> ⚙️ 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](../_shared/env-contract.md),执行前先读它。

# daily-review — A股每日复盘(专业版)

盘后固定动作:把 QuantDB 当天数据 + 当日新闻情绪 + L1/L2 因子截面变成一份结构固定的复盘报告(Markdown + PDF),落盘到前端「股票报告」页可见目录,并在聊天里回复速览。**报告末必含「次日走势研判」——给出明确方向(强烈看多/看多/震荡/看空/强烈看空)+ 置信度星级 + 每维依据。**

## ⚠️ 单位铁律(先查 [[quantdb-fields]],最高优先级)

| 陷阱 | 正确口径 |
|---|---|
| 个股 volume=**股**、amount=**万元** | 指数 volume=**手**、amount=万元 |
| 复盘报告里金额一律换算为**亿元**(万元÷1e4) | 脚本输出的 `*_yi` 字段单位已是亿元 |
| `technical_indicators.pct_change` = **%**;未来收益用 `future_return_*`(标签,勿当历史动量);历史动量用 pct_change / mom_ret | 涨跌家数/涨停/连板全用它 |
| `index_daily.preClose` **全 NULL** | 指数涨跌幅用 close 序列自算(脚本已处理) |
| l2_factors 已恢复日更(202608+ 当日有数据,L1 主力资金可用);两融通常滞后 1 日(偶与当日对齐,以 facts 为准);北向只有季度快照 | 必须带「数据滞后声明」,滞后数据集禁止当当日数据写 |

## 执行流程(每次复盘固定 5 步)

### 第 1 步:跑取数脚本(两条:daily_review 取 L1/L2/方向 + 模型推理信号,news_review 取当日新闻情绪)

```bash
# ① 宿主机:daily_review.py 出 指数/广度/板块/资金面 + L1/L2 因子透视 + 板块资金流 + 模型推理信号 + 次日方向
cd <repo>/skills/daily-review/scripts
python3 daily_review.py --date 20260814              # 指定日;不带 --date 则取最新交易日
python3 daily_review.py --watch 601138.SH,600519.SH  # 可选:自选/持仓股必带
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add qusong0627/quantmind/daily-review@sha256:f67346a2bc106f01

The line at the top of this page pins the label git:20261003.8b2ea6a, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_fifto636442qj2v2.svg)](https://markdownregistry.com/a/art_fifto636442qj2v2)

2 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 5 versions of this file, between Aug 29, 2026 and Oct 3, 2026, about one every 9 days. Its first recorded version is graded B and its latest A.

versioncommittedcommitsizeaudit
git:20261003.8b2ea6a latest2026-10-03 8b2ea6a 13,991 BA view · diff
git:20260919.a5c80062026-09-19 a5c8006 13,994 BA view · diff
git:20260919.401b4a82026-09-19 401b4a8 15,831 BB view · diff
git:20260829.c9fd96c2026-08-29 c9fd96c 15,756 BB view · diff
git:20260829.cda0e482026-08-29 cda0e48 15,766 BB view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (13991 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

qusong0627/quantmind · 1,774 stars · license AGPL-3.0 · pushed 2026-10-22 · branch master

API

GET https://markdownregistry.com/api/v1/artifacts/art_fifto636442qj2v2
GET https://markdownregistry.com/api/v1/resolve?ref=qusong0627/quantmind/daily-review
GET https://markdownregistry.com/api/v1/blob/f67346a2bc106f01b5f71f5062bc110db92e57207312042b5e3fbe3c7ec688ec

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from qusong0627/quantmind

AGENTS.md AGENTS.md file
qusong0627/quantmind · AGENTS.md
git:20261021.501dee8 · audit B · 1,774 stars
CLAUDE.md CLAUDE.md file
qusong0627/quantmind · CLAUDE.md
git:20261003.8b2ea6a · audit A · 1,774 stars
AGENTS.md@config/qwenpaw AGENTS.md file
qusong0627/quantmind · config/qwenpaw/AGENTS.md
git:20261003.8b2ea6a · audit A · 1,774 stars
AGENTS.md@rd-agent/rdagent/scenarios/rl/autorl_bench/agents/claude AGENTS.md file
qusong0627/quantmind · rd-agent/rdagent/scenarios/rl/autorl_bench/agents/claude/AGENTS.md
git:20260605.d7f99db · audit A · 1,774 stars
AGENTS.md@rd-agent/rdagent/scenarios/rl/autorl_bench/agents/codex AGENTS.md file
qusong0627/quantmind · rd-agent/rdagent/scenarios/rl/autorl_bench/agents/codex/AGENTS.md
git:20260605.d7f99db · audit A · 1,774 stars
AGENTS.md@rd-agent/rdagent/scenarios/rl/autorl_bench/agents/gemini AGENTS.md file
qusong0627/quantmind · rd-agent/rdagent/scenarios/rl/autorl_bench/agents/gemini/AGENTS.md
git:20260605.d7f99db · audit A · 1,774 stars
ai-ide-strategy-writing SKILL.md skill
qusong0627/quantmind · skills/ai-ide-strategy-writing/SKILL.md · AI-IDE 写策略与执行 — 用 AI 生成 Qlib 量化策略代码、Docker 容器执行策略/回测、自然语言条件选股、策略落库。在 QuantBot / Claude Code 中让 AI 写策略、生成 Qlib…
git:20260919.a5c8006 · audit B · 1,774 stars
backtest-center SKILL.md skill
qusong0627/quantmind · skills/backtest-center/SKILL.md · 回测中心 — 快速回测、专家模式、回测历史、策略对比、参数优化、策略管理、高级分析。在 QuantBot / Claude Code 中运行 Qlib…
git:20260919.a5c8006 · audit B · 1,774 stars
batch-inference-analysis SKILL.md skill
qusong0627/quantmind · skills/batch-inference-analysis/SKILL.md · 批量推理结果分析 — 用 QuantMind 选股策略方法论分析每日信号、行业轮动、个股分数区间、负分参考。在 QuantBot / Claude Code…
git:20260919.a5c8006 · audit B · 1,774 stars
futuapi SKILL.md skill
qusong0627/quantmind · skills/futuapi/SKILL.md · 富途 OpenAPI 交易与行情助手。查询行情、K线、报价、快照、买卖盘、逐笔成交、分时数据;搜索标的与资讯;解析期权代码、查询期权链/到期日/IV/行权概率;执行买入/卖出/下单/撤单/改单;查询持仓/资金/账户/订单;订阅实时推送;加密…
v0.1.1 · audit A · 1,774 stars
install-futu-opend SKILL.md skill
qusong0627/quantmind · skills/install-futu-opend/SKILL.md · Futu OpenD 安装助手。自动下载安装Futu OpenD 并升级 Python SDK。支持 Windows、MacOS、Linux。用户提到安装、下载、启动、运行、配置 OpenD、开发环境、升级 SDK、futu-api…
v0.1.1 · audit A · 1,774 stars
market-analysis SKILL.md skill
qusong0627/quantmind · skills/market-analysis/SKILL.md · 市场分析报告(大盘快照版)— 复用市场分析页面全部数据能力:核心指数、市场广度与情绪温度、行业板块/热门概念热力图、行业多日涨跌幅对比(1/3/5日)、板块资金流(1日/5日/10日)、个股主力资金…
git:20261003.8b2ea6a · audit A · 1,774 stars

Every file in qusong0627/quantmind

Other files named daily-review

daily-review SKILL.md skill
geekwls/stock-prompt · .agents/skills/daily-review/SKILL.md · 用于A股交易日收盘后的每日复盘,或盘中大盘走势与板块异动快照;分析市场情绪、主线板块、产业链共振、资金延续及龙头中军状态。不适用于盘前预测或近5日轮动复盘。
git:20260928.ef22fcb · audit A · 38 stars

Browse by kind, by grade A, or by owner.