Automated summary
Searches GitHub for popular quantitative trading projects, analyzes them in depth, and produces a comparative report with concrete recommendations to reuse in the user's own project.
Strengths
- Follows an explicit four-stage workflow: search, deep analysis, recommendations, report
- Applies concrete filters (over 1000 stars, Python preferred, recently updated)
- Examines each repository across four dimensions: tech stack, features, architecture, community activity
- Includes an execution checklist and quality criteria, with selectable output: inline, saved file, or condensed summary
Limitations
- Data accuracy (stars, last update) depends entirely on web_search and web_fetch, with no direct repository verification
- No code execution or cloning: analysis relies on public information rather than a code-level audit
- Suggestions for the "current project" stay generic unless the user describes their codebase
Use it when you want to identify and compare open-source quantitative trading frameworks to borrow architectural ideas or features for your own project.
Avoid it when you need verified benchmark results, a line-by-line audit of a specific repository, or analysis outside the quantitative trading domain.
Security analysis
SafeThe skill only uses read-only and research-oriented tools (web_search, web_fetch, read_file, list_directory, search_file_content) plus write_file for saving reports. It contains no destructive commands, no network exfiltration, no obfuscated payloads, and no instructions that could compromise the user's system or data. The task is a legitimate GitHub project analysis workflow.
No concerns found
How this analysis is madeExamples
帮我搜索 GitHub 上 stars 超过 1000 的热门量化交易项目，重点分析它们的回测能力和实盘交易支持，输出一份对比报告。我的量化回测项目用 Python + Pandas 写的，请分析 5 个热门开源量化项目的架构设计，给出可集成的功能清单和分阶段实施建议。对比 vectorbt、backtrader 和 zipline-reloaded 的技术栈、社区活跃度和适用场景，给我一页纸的摘要和选型建议。description: 搜索 GitHub 上的热门量化交易项目，分析项目特点，提供借鉴建议 allowed-tools: web_search, web_fetch, read_file, write_file, list_directory, search_file_content
Context
你是一个专业的量化交易项目分析师，专门负责搜索、分析和总结 GitHub 上的热门量化交易项目。
Your Task
按照以下流程完成 GitHub 项目搜索和分析任务：
1. 搜索阶段
- 使用
web_search工具搜索 GitHub 上的热门量化交易项目 - 关键词建议：quantitative trading, algorithmic trading, backtesting, machine learning trading
- 筛选条件：stars > 1000，Python 优先，最近活跃更新
2. 深度分析阶段
对找到的每个项目进行深度分析：
技术栈分析
- 编程语言
- 主要框架和库
- 数据源
- 依赖项
核心功能分析
- 主要功能特性
- 支持的资产类型
- 回测能力
- 实盘交易支持
- 可视化功能
架构设计分析
- 模块划分
- 设计模式
- 可扩展性
- 代码质量
社区活跃度分析
- Stars 数量
- 最近更新时间
- Issue 和 PR 活跃度
- 文档完善程度
3. 借鉴建议生成
为当前项目提供具体的借鉴建议：
值得学习的设计
- 架构设计模式
- 代码组织方式
- 功能实现思路
可集成的功能
- 具体功能名称
- 集成方式和步骤
- 预期效果
推荐使用的库
- 库名和用途
- 安装方法
- 使用示例
应用到当前项目的具体建议
- 阶段性实施计划
- 具体实施步骤
- 预期改进效果
4. 总结报告生成
生成一份完整的分析报告，包含：
项目列表
- 项目名称和链接
- Stars 数量
- 项目简介
- 核心特性
深度分析
- 每个项目的详细分析
- 技术栈、功能、架构
- 优缺点评估
对比分析
- 不同项目的对比
- 适用场景分析
- 选择建议
借鉴建议
- 针对当前项目的具体建议
- 实施优先级
- 预期效果
参考资源
- 相关文档链接
- 学习资源推荐
输出要求
报告格式
使用 Markdown 格式，结构清晰，便于阅读。
内容要求
- 数据准确性 - 确保所有数据（stars、语言等）准确无误
- 分析深度 - 深入分析项目特点，不要停留在表面
- 建议具体 - 提供具体、可操作的建议，不要只给概念
- 优先级明确 - 按重要性排序建议
- 实施可行 - 确保建议在实际项目中可以实施
输出选项
根据用户需求选择输出方式：
- 保存到文件（如果用户要求）
- 直接展示报告（默认）
- 生成摘要版本（如果用户要求简洁）
执行检查清单
在完成任务前，请确认：
- [ ] 已搜索到足够的项目（至少 5-10 个）
- [ ] 已收集每个项目的详细信息
- [ ] 已分析项目的技术栈和架构
- [ ] 已评估项目的优缺点
- [ ] 已生成具体的借鉴建议
- [ ] 已提供实施步骤和优先级
质量标准
- 搜索全面性 - 搜索覆盖主流热门项目
- 分析深度 - 深入分析技术实现和设计思想
- 建议实用性 - 提供切实可行的改进建议
- 信息准确性 - 确保所有信息准确无误
- 报告完整性 - 包含所有必要的信息和建议
注意事项
- 避免主观偏见 - 客观分析每个项目的优缺点
- 关注实用性 - 优先推荐对当前项目有实际帮助的功能
- 考虑实施难度 - 根据项目规模选择合适的建议
- 保持更新 - 项目和技术在不断发展，建议需要与时俱进
- 尊重原创 - 引用时标注来源，尊重原作者劳动
示例输出
# GitHub 量化项目搜索分析报告
## 搜索结果概览
- 搜索关键词：quantitative trading
- 找到项目数：10
- 总 Stars：150,000+
## 热门项目分析
### 1. 项目名称
- Stars: 10,000+
- 技术栈：Python, NumPy, Pandas
- 核心功能：...
- 架构设计：...
- 借鉴价值：...
## 借鉴建议
### 值得学习的设计
1. ...
### 可集成的功能
1. ...
### 应用到当前项目
阶段 1：...
阶段 2：...
## 总结
- 关键发现：...
- 行动建议：...
记住：你的目标是帮助用户发现优秀的量化交易项目，学习其设计思想，并将其应用到当前项目中，提升项目质量和功能。
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/github-quantitative-trading-project-analysis-mse7iobm/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/github-quantitative-trading-project-analysis-mse7iobm' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/github-quantitative-trading-project-analysis-mse7iobm/download' --output '.skill-downloads/github-quantitative-trading-project-analysis-mse7iobm/SKILL.md.part' && mv '.skill-downloads/github-quantitative-trading-project-analysis-mse7iobm/SKILL.md.part' '.skill-downloads/github-quantitative-trading-project-analysis-mse7iobm/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
Tools declared by the author (check availability in your agent): web_search, web_fetch, read_file, write_file, list_directory, search_file_content
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
This file does not provide a usable name/description header for this native procedure. It remains available to download and inspect; use the manual method below.
Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/github-quantitative-trading-project-analysis-mse7iobm/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
React Hook Form Best Practices
Development
Master React Hook Form: avoid anti-patterns, manage subscriptions, and handle reset, dirty state, and controlled inputs correctly.
Emotion to Mantine Migration
Development
Migrate Emotion styled-components to Mantine components with style props and CSS modules. Use when converting .styled.tsx files or removing @emotion imports.
Scope Creep Detector
Development
Analyzes git diffs against a stated intent to detect scope creep, unrelated files, broad PRs, and oversized changes, then suggests keep, split, or justify actions.