No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by gaaiyun · Agent Tool · ★ 82
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is joinquant-skill safe to install? View the security audit →
JoinQuant Skill 让 AI agent（Cursor / Claude Code / Codex / OpenCode 等）能正确生成符合聚宽（JoinQuant）平台的量化策略代码。 项目本身不教 AI 做策略，而是给 AI 一份结构化的 API 知识库、可粘贴运行的策略模板、静态检查工具、因子库与单因子分析工具，以及一条把券商研报变成聚宽策略代码的流水线。所有产物都被组织成一个可 install 的 skill，被 Cursor / Claude Code / MCP 客户端按需检索。 一、它解决什么具体问题 用 Claude / Cursor 写聚宽策略时反复遇到的几个坑： 模型乱编 API：让它写 DiD 它返回 ；让它写聚宽策略它返回 ——这些函数都不存在。 数据 API 与回测 API 混淆：聚宽的 在回测里和研究里行为不一样，模型常不分场景乱用。 未来函数防不胜防：回测里能跑、实盘崩盘的常见原因。 复权模式搞错：传统前复权 vs 真实价格（动态复权），细节一错全盘皆错。 API 文档塞不进 prompt：294KB 的官方文档不可能整段塞，但只塞一部分模型又用不全。 这些问题不是写更长的 prompt 能解决的，所以我们把它们封装成一个可 install 的 skill——按需检索、按场景路由、本地 lint。 二、能力地图（五大模块 + MCP 暴露层） python scripts/strategylint.py mystrat
| Stars | 82 |
| Forks | 18 |
| Language | Python |
| Category | Agent Tool |
| Quality Score | 60.5569357044147/100 |
| Open Issues | 1 |
| Last Updated | 2026-09-14 |
| Created | 2026-04-18 |
| Platforms | claude-code, python |
| Est. Tokens | ~16k |
Looking for a joinquant-skill alternative? If you're comparing joinquant-skill with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
迅投 QMT 量化 AI 技能集（Agent Skills）：研报因子回测脚本生成等，适用于 Claude Code / Cursor / Codex / Kimi 等 70+ AI 编程工具
宽宝 QuantBuddy： 一整套面向Agent Invesment投资研究与决策的底层设施与能力的调用skill， 覆盖A股/港股/美股/期货/宏观/ETF的量化分析与计算。支持行情、估值、财务查询、选股筛选、因子计
Quantitative factor research skills for AI coding assistants
A股数据分析、量化选股与模拟交易 Skill 集合，支持实时行情、历史K线、技术指标、自定义交易策略与模拟买入、卖出交易账户
World-class creative director in a skill. Methodology-driven ideation (SIT, TRIZ, Lateral Thinking, bisociatio
An Self-Evolving Stock Strategy Research Agent 策略回测和自我进化
Explore other popular agent tool tools:
joinquant-skill is AI agent skill for generating quantitative strategy code on JoinQuant platform - Cursor / Claude Code compatible. It is categorized as a Agent Tool with 82 GitHub stars.
joinquant-skill is primarily written in Python. It covers topics such as agent-skill, ai, backtesting.
You can find installation instructions and usage details in the joinquant-skill GitHub repository at github.com/gaaiyun/joinquant-skill. The project has 82 stars and 18 forks, indicating an active community.
The top alternatives to joinquant-skill on Agent Skills Hub include xtquantai, quant-buddy-skills, alpha-skills. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: