stock-picks SKILL.md skillA
stock-picks from qusong0627/quantmind is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add qusong0627/quantmind/stock-picks@git:20261003.8b2ea6aPins 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/stock-picks/SKILL.md- Versions recorded
- 4
- Latest version
- git:20261003.8b2ea6a, committed Oct 3, 2026
- First version recorded
- Aug 29, 2026
- Size
- 11,448 bytes
- Repository stars
- 1,774
- License
- AGPL-3.0
每日复盘后的股票推荐（多维度选股）— 综合 A股每日复盘（市场方向/板块/资金/新闻情绪）+ 个股深度分析（9层），用多维度筛选条件（L2微观结构为主/模型融合分/仓位信号/板块强度/新闻情绪）从全市场挑出未来几天大概率走强的股票，支持跨多日聚合（--window），输出候选榜 + 综合复盘 + Top 个股深度分析，落盘 PDF 到股票报告目录。用户说「选股」「推荐股票」「每日推荐」「明日看好」「选股推荐」「复盘后选股」时使用：跑复盘取数 → pick_candidates 多维打分 → Top N 深分 → 综合报告 → PDF。触发词：选股、股票推荐、每日推荐、明日看好、推荐股票、今日选股.
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。 # stock-picks — 每日复盘后的股票推荐（多维度选股） 把「每日复盘」（市场广度）和「个股深度分析」（个股深度）两张皮缝起来：先用复盘产物定市场环境（该不该进场、主线在哪、资金方向），再用多维度筛选条件从全市场挑候选，对 Top N 做 9 层深分，最后输出**一份报告**：综合复盘 + 候选榜 + Top 个股深分。报告 Markdown + PDF，落盘前端「股票报告」页可见目录，聊天回复速览。 **定位**：`[[daily-review]]` 是广度（今天市场发生了什么），`[[stock-market-analysis]]` 是深度（某只股票值不值得看），本 skill 是**两者合一的推荐**——先选再深挖，产出可执行的候选池，不是复盘报告。 ## ⚠️ 铁律（先读，最高优先级） | 陷阱 | 正确口径 | |---|---| | **推荐不是承诺** | 所有候选是「多维信号合成的相对强势」，不是「明天必涨」。报告必须带风险声明 + 数据滞后声明 | | **ST 股默认排除** | ST/*ST/退 有 5% 涨跌幅限制 + 退市风险，`pick_candidates.py` 默认排除（`--keep-st` 才保留） | | **信号日取最近「全量」推理日** | 默认 = distinct symbol ≥ 1000 的那天（`engine_signal_scores`），避免最近只推理了几十只的残日；`--date` 可显式指定 | | **分数单位** | fusion_score 是模型预测分（非涨跌幅）；position_score 0~1 是半凯利仓位；pct_industry 是行业截面百分位 | | **L2 是 T+5/T+10 信号** | VPIN 族正 IC（高分偏多）、vol_persistence 等负 IC（高分偏空）——看状态分位，别当单日信号 | | **趋势不纳入** | 模型分数趋势维度按需求移除——打分只用 L2/融合/仓位/板块/新闻，不参与排名 | | **L2 主导** | L2 权重(40%) > 融合分(30%)：L2 是 T+5/T+10 信号，先看订单簿微结构，再看模型预测 | ## 执行流程（固定 6 步） ### 第 1 步：跑每日复盘取数（复用 [[daily-review]]） ```bash # ① 宿主机：daily_review.py 出 指数/广度/板块/资金/L1/L2 + 模型推理信号 + 次日方向 …
Read the whole file at its exact version.
How to install
mdr add qusong0627/quantmind/stock-picks@sha256:e76463878868c924The 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.
[](https://markdownregistry.com/a/art_vhs75au2hsszu55l)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 4 versions of this file, between Aug 29, 2026 and Oct 3, 2026, about one every 12 days. Its first recorded version is graded B and its latest A.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261003.8b2ea6a latest | 2026-10-03 | 8b2ea6a | 11,448 B | A | view · diff |
| git:20260919.a5c8006 | 2026-09-19 | a5c8006 | 11,450 B | A | view · diff |
| git:20260829.c9fd96c | 2026-08-29 | c9fd96c | 13,287 B | B | view · diff |
| git:20260829.cda0e48 | 2026-08-29 | cda0e48 | 13,293 B | B | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (11448 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
qusong0627/quantmind · 1,774 stars · license AGPL-3.0 · pushed 2026-10-22 · branch master
API
GET https://markdownregistry.com/api/v1/artifacts/art_vhs75au2hsszu55l GET https://markdownregistry.com/api/v1/resolve?ref=qusong0627/quantmind/stock-picks GET https://markdownregistry.com/api/v1/blob/e76463878868c92455c36c7b3d54e87888987fe9912752ea497066f3a5bad026
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.