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.
npx skills add atorber/qmt-trading-skill --skill qmt-bridge-return-analysisgit clone --depth 1 https://github.com/atorber/qmt-trading-skillWrote 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.
[](https://agentmods.dev/skills/atorber/qmt-trading-skill/qmt-bridge-return-analysis)<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.
<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>- NVIDIA SkillSpector pass
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 | $0.00051 | $0.00821 |
| Sonnet 5 | $0.00020 | $0.00328 |
| Haiku 4.5 | $0.00010 | $0.00164 |
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 9d ago.
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.
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 |
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.
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.
- 9d ago First seen · 100 lines · 101 tokens per session scan A 13d2687c18a3
qmt-bridge-return-analysis is a skill published in the GitHub repository atorber/qmt-trading-skill (22 stars, last pushed 26d ago), licensed MIT. It adds 101 tokens to every session and 1,642 once invoked, about $0.0005 per session on Opus 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.
Other skills, from other repositories
sector-rotation
An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.
strategy-pivot-designer
Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
chenhao-limit-up
A framework for judging Chinese A-share stocks that have reached the daily price-rise limit, using market mood, sector leadership, and trading momentum.
trading-risk-gate
Unified pre-trade safety gate: Ruin check (Law #1), ergodicity audit, and win-rate dominance validation. Absorbs: ergodicity-check, law-of-ruin, win-rate-dominance.
vectorbt
High-performance vectorized backtesting with parameter optimization, portfolio simulation, and rich performance metrics.