model-train-infer-backtest-report
Skill1.8k starsChanged 30 days agoAGPL-3.0View on GitHub
模型训练-推理-组合回测-专业报告 全流程 — 提交T+N周期模型训练（13种模型类型：lightgbm/xgboost/catboost/random_forest/linear/mlp/gru/lstm/alstm/transformer/tabnet/tcn/nativetft，GPU训练+GPU推理）、批量推理全年、自定义组合策略回测(分数阈值+大盘MA+止损)、导出研报级MD+PDF报告。在 QuantBot / Claude Code 中训练模型、推理历史、回测策略、对比T+N周期、止损、大盘过滤、出报告、效益分析时使用。触发词：训练模型、模型训练、13种模型、推理全年、回测策略、T+3、T+5、周期对比、止损、大盘过滤、出报告、效益分析
- Sends data out
Trending
More talk lately.thin dataabout the whole repository
Who's talking about qusong0627/QuantMind
- Anto-30/aurelia-trading“Research intake: triage 26 trading-agent, quant, MCP and architecture repositories”GitHub · Oct 18, 2026
- sudosubin/agents.nix“agent-skills.github.qusong0627.quantmind: init at 1.0.0”GitHub · Oct 14, 2026
- conversun/fnos-apps“[App Request]”GitHub · Aug 28, 2026
The biggest 3 of 3 mentions linking to the repository that our crawl found. Each line is their own headline.
In this repository31 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- ai-ide-strategy-writingSkill
- backtest-centerSkill
- batch-inference-analysisSkill
- daily-reviewSkill
- futuapiSkill
- install-futu-opendSkill
- market-analysisSkill
- model-training-configSkill
- news-sentiment-finbertSkill
- news-sentiment-researchSkill
- quantdb-data-structureSkill
- quantdb-fieldsSkill
- quantdb-sdkSkill
- quantmind-deploySkill
- quantmind-operationsSkill
- rd-agent-factor-miningSkill
- simulation-tradingSkill
- smart-strategy-stock-pickingSkill
- stock-deep-researchSkill
- stock-market-analysisSkill
- stock-picksSkill
- stock-researchSkill
- tigeropen-cppSkill
- tigeropen-csharpSkill
- tigeropen-goSkill
- tigeropen-javaSkill
- tigeropen-rustSkill
- tigeropenSkill
- tigeropen-typescriptSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.