alpha-evaluate

alpha-evaluate is a skill for Claude Code, Codex from VernonOY/alpha-skills. It costs 74 tokens per session (6,985 once invoked), scanned A, original, Apache-2.0.

A multi-step workflow for testing an investment factor, meaning a measurable stock signal, against market data. It examines predictive relationship, grouped returns, risk-adjusted results, consistency, and robustness.

In plain words
What is it for?
Use it to evaluate a factor, run historical tests, compare stock groups, check long-short results, and produce evaluation outputs.
Why use it?
It replaces a single performance number with several checks that can reveal weak, unstable, or misleading results. It can use configured or local data sources and market settings.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to evaluate a factor, run historical tests, compare stock groups…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/vernonoy/alpha-skills/alpha-evaluate
Install

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.

Any agent
npx skills add VernonOY/alpha-skills --skill alpha-evaluate
Clone the repo
git clone --depth 1 https://github.com/VernonOY/alpha-skills

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for alpha-evaluate

README.md
[![agentmods](https://agentmods.dev/badge/skills/vernonoy/alpha-skills/alpha-evaluate.svg)](https://agentmods.dev/skills/vernonoy/alpha-skills/alpha-evaluate)
Your own site
<a href="https://agentmods.dev/skills/vernonoy/alpha-skills/alpha-evaluate"><img src="https://agentmods.dev/badge/skills/vernonoy/alpha-skills/alpha-evaluate.svg" alt="Measured on agentmods" height="20"></a>
Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,985 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00074 $0.06985
Opus 5 $0.00037 $0.03492
Sonnet 5 $0.00015 $0.01397
Haiku 4.5 $0.00007 $0.00698

Measured 7d ago against content hash caef25386d74, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

alpha-evaluate 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 7d 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.

skills/alpha-evaluate/SKILL.md · 558 lines

How it starts

The opening of the file, as written. The whole thing — 558 lines — stays where its author put it; the contents beside it link to each section on GitHub.

alpha-evaluate — Factor Evaluation / 因子评估

你是一个专业量化分析师。当用户要求评估一个因子时,按照以下流程执行。 You are a professional quant analyst. Follow the pipeline below when evaluating a factor.

Bilingual Terms / 双语术语

English 中文
Factor 因子
IC (Information Coefficient) 信息系数
ICIR (IC Information Ratio) IC信息比率
Quintile 五分位/分组
Long-Short 多空
Sharpe Ratio 夏普比率
Max Drawdown 最大回撤
Monotonicity 单调性
Robustness 鲁棒性
Holding Period 持有期
Factor Registry 因子注册表
Backtest 回测
Gate Check 门控检查

项目定位 / Project Context

项目目录在用户的当前工作目录,其中: Project directory is the user's current working directory, containing:

  • data_cache/ — 本地缓存的行情数据 Local cached market data(Parquet格式 format)
  • output/ — 报告输出目录 Report output directory
  • .claude/alpha-agent.config.md — 用户自定义评估参数 User-defined evaluation parameters

数据来源 / Data Source:技能支持任何数据源。优先检查用户配置中的 DATA_SOURCE 字段: The skill supports any data source. Check user config DATA_SOURCE field first:

  • tushare (默认 default) — 使用Tushare Pro API拉取A股数据 / Fetch A-share data via Tushare Pro API
  • csv — 从用户指定目录读取CSV/Parquet文件 / Read CSV/Parquet from user-specified directory
  • custom — 用户提供自定义数据加载函数 / User-provided custom data loader

如果用户已在项目中定义了自己的数据加载模块(如 my_data.py),优先使用用户的模块。 If the user has defined a custom data module (e.g., my_data.py), use it first. 检查方式:查看配置文件中是否有 DATA_MODULE 字段指定了自定义模块路径。 Check: look for DATA_MODULE field in config file for custom module path.

Multi-Market Support / 多市场支持:

Alpha Skills support A-share (default), HK, and US stocks via data adapters: Alpha Skills 通过数据适配器支持A股(默认)、港股和美股:

# .claude/alpha-agent.config.md
MARKET: A-share           # or "HK" or "US"
DATA_MODULE: (leave empty for A-share Tushare default)
                          # or "examples.us_data_yfinance"
                          # or "examples.hk_data_yfinance"

When a custom DATA_MODULE is set, the skill loads MARKET_CONFIG from that module to determine benchmark, cost rate, and trading rules. 设置自定义DATA_MODULE时,skill从该模块加载MARKET_CONFIG来确定基准、成本和交易规则。

Read the full file on GitHub · 558 lines

Changes

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.

  1. 7d ago First seen · 558 lines · 74 tokens per session scan A caef25386d74

Subscribe to this mod's changes

alpha-evaluate is a skill published in the GitHub repository VernonOY/alpha-skills (106 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 74 tokens to every session and 6,985 once invoked, about $0.0004 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.

Related

Other skills, from other repositories