What is qmt-bridge-return-analysis?

A read-only QMT Bridge analysis tool for Chinese stock price history. It calculates returns over several trading periods and estimates next-day rise probabilities from past price and volume patterns.

Checking 1-, 2-, 3-, 4-, 5-, 10-, and 30-day returns, comparing price and trading-volume patterns, estimating next-day outcomes, and reviewing selected stocks or account holdings.

It gathers several technical indicators and historical comparisons in one report, including a way to analyze current holdings. The results are statistical descriptions, not investment advice.

qmt-bridge-return-analysis — Skill by atorber/qmt-trading-skill

Install

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.

Any agent

npx skills add atorber/qmt-trading-skill --skill qmt-bridge-return-analysis

Clone the repo

git clone --depth 1 https://github.com/atorber/qmt-trading-skill

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/atorber/qmt-trading-skill/qmt-bridge-return-analysis/github.svg)](https://agentmods.dev/skills/atorber/qmt-trading-skill/qmt-bridge-return-analysis)

Your own site

<a href="https://agentmods.dev/skills/atorber/qmt-trading-skill/qmt-bridge-return-analysis"><img src="https://agentmods.dev/badge/skills/atorber/qmt-trading-skill/qmt-bridge-return-analysis/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/atorber/qmt-trading-skill/qmt-bridge-return-analysis"><img src="https://agentmods.dev/badge/skills/atorber/qmt-trading-skill/qmt-bridge-return-analysis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 101 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,642 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

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	$0.00101	$0.01642
Opus 5.5	$0.00040	$0.00657
Sonnet 5.5	$0.00020	$0.00328
Haiku 4.5	$0.00010	$0.00164

Measured 2mo ago against content hash 13d2687c18a3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

qmt-bridge-return-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 2mo ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/return_probability_analysis.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/qmt-bridge-return-analysis/SKILL.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

QMT Trading Skill · 累计涨幅与涨跌概率

实现状态：✅ return_probability_analysis.py 可用

目标

回答：

指定股票在 1、2、3、4、5、10、30 个交易日上的收盘累计涨幅（%）
基于 近 10 个交易日日 K 涨跌形态 + 更长历史回测，给出 下一交易日收涨的条件概率；样本不足时自动 缩短形态 / 放宽 1 位 / 小样本收缩估计
结合 连续多日成交量（相对 5 日均量、3 日量增、量价状态）评估涨跌概率（统计描述，非投资建议）

脚本

脚本	作用
`scripts/return_probability_analysis.py`	`--codes` 或 `--holdings`；缺 K 自动下载

# 当前持仓一键分析（需 API Key）
python skills/qmt-bridge-return-analysis/scripts/return_probability_analysis.py --holdings --host 127.0.0.1 --port 8080 --api-key YOUR_KEY

python skills/qmt-bridge-return-analysis/scripts/return_probability_analysis.py --codes 000001.SZ,600519.SH --host 127.0.0.1 --port 8080
python skills/qmt-bridge-return-analysis/scripts/return_probability_analysis.py \
  --codes 300394.SZ,688008.SH --json

参数	说明
`--codes`	逗号分隔股票代码（与 `--holdings` 二选一）
`--holdings`	从账户持仓读取标的；缺日 K 时自动 `download_batch`
`--download-start`	自动补 K 起始日（默认 `20240101`）
`--skip-download`	不自动下载日 K
`--count`	拉取日 K 根数（默认 150）
`--dividend-type`	复权：`front` / `none` / `back` 等
`--pattern-len`	形态匹配长度（默认 9 日）
`--json`	JSON 输出
`--no-detail`	不展示近 10 日逐日表
`--no-strategy`	不输出下一交易日策略与观察点

提示词示例（可复制）

优先引导 Agent 执行 skills/qmt-bridge-return-analysis/scripts/return_probability_analysis.py（--holdings 或 --codes）。

场景	提示词
持仓一键（推荐）	`评估当前持仓的 1/5/10/30 日累计涨幅、量价涨跌概率，并总结明日操作策略与观察点`
	`用 return-analysis skill 跑 --holdings，缺 K 线自动下载`
指定标的	`分析 300394.SZ、688008.SH 的阶段涨幅和近 10 日上涨概率`
	`这几只股票 1 日、5 日、30 日涨幅各多少，谁更强`
量价	`结合成交量看持仓明日收涨概率和放量确认度`
	`哪些持仓近 3 日量价形态偏强，历史次日统计如何`
形态	`用 9 日 K 线形态统计下一日收涨概率，样本不够就缩短形态`
明日计划	`根据持仓报告，给每只写明日观察点和一日策略（不荐股）`
	`组合层面：谁 30 日强、谁昨日回调大，明天优先盯什么`
机器可读	`持仓涨幅概率分析，输出 JSON`（加 `--json`）

Agent 执行要点：--holdings 需 --host 127.0.0.1 与 API Key；.env 里 QMT_BRIDGE_HOST=0.0.0.0 时客户端仍连 127.0.0.1。

主要 API

方法	路径	说明
GET	`/api/market/market_data_ex`	日 K（`period=1d`）
GET	`/api/utility/batch_stock_name`	中文名称

Read the full file on GitHub · 100 lines

Files

What ships with it

2 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.

Changes

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.

2mo ago First seen · 100 lines · 101 tokens per session scan A 13d2687c18a3

Subscribe to this mod's changes

qmt-bridge-return-analysis is a skill published in the GitHub repository atorber/qmt-trading-skill (26 stars, last pushed 1mo ago), licensed MIT. It adds 101 tokens to every session and 1,642 once invoked, about $0.0004 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.

Analytics and metrics Finance and fintech

qmt-bridge-return-analysis next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
qmt-bridge-return-analysisatorber/qmt-trading-skill	Skill	26	1mo ago	MIT	A	101	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