← All skills

a-share-model-risk

100 / 100 · Low risk

Fine to try.

By aifinlab/FinClaw (GitHub) · data · 273 stars · scanned at commit 9e62862

A股模型风险/回测过拟合分析。当用户说"模型风险"、"model risk"、"过拟合"、"overfitting"、"回测失真"、"样本外失效"、"模型验证"时触发。基于 cn-stock-data 获取数据，评估量化模型的过拟合与模型风险。支持 formal/brief 两种输出风格。

Works with any agent that supports SKILL.md skills.

What this skill can do

We found nothing in the files we read that matches our rules. That does not prove the skill is safe: see the limits of static scanning.

Install

Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.

if [ -e ~/.agents/skills/'a-share-model-risk' ] || [ -L ~/.agents/skills/'a-share-model-risk' ]; then echo 'A skill folder named a-share-model-risk already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/aifinlab/FinClaw' "$d" && git -C "$d" checkout --quiet '9e62862d1412157fa03ffd1f0b74969dcf0ed66c' -- 'skills/a-share-model-risk' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/a-share-model-risk' ~/.agents/skills/'a-share-model-risk' && rm -rf "$d"; fi

Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'a-share-model-risk' ~/.claude/skills/'a-share-model-risk' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.

Badge for your README

The badge for aifinlab/FinClaw shows the score of its lowest-scoring skill.

[![SkillTrust](https://zalavijaysinh.github.io/skilltrust/badges/aifinlab/FinClaw.svg)](https://zalavijaysinh.github.io/skilltrust/repos/aifinlab/FinClaw/)

Score history

Also found in

Identical copies of this skill exist at:

• aifinlab/FinClaw/skills/archive/a-share-model-risk