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.
npx skills add cyijun/china-financial-services --skill a-share-factor-validationgit clone --depth 1 https://github.com/cyijun/china-financial-servicesWrote 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.
[](https://agentmods.dev/skills/cyijun/china-financial-services/a-share-factor-validation)<a href="https://agentmods.dev/skills/cyijun/china-financial-services/a-share-factor-validation"><img src="https://agentmods.dev/badge/skills/cyijun/china-financial-services/a-share-factor-validation/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/cyijun/china-financial-services/a-share-factor-validation"><img src="https://agentmods.dev/badge/skills/cyijun/china-financial-services/a-share-factor-validation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00068 | $0.00986 |
| Opus 5.5 | $0.00027 | $0.00394 |
| Sonnet 5.5 | $0.00014 | $0.00197 |
| Haiku 4.5 | $0.00007 | $0.00099 |
Grade A, and why
a-share-factor-validation 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 1mo 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.
What it actually says
A股因子与回测验证
工作流
- 预注册因子公式、经济机制、方向、持有期、股票池、基准、再平衡和主要指标，区分探索性与验证性研究。
- 使用
china-market-data建立严格PIT数据契约：原始价、复权因子、财务公告日、历史行业/指数成员、ST/退市/停牌状态。AKShare当前快照不得替代历史股票池。 - 画清信号、决策和成交时间线；收盘信号不得假设同收盘成交，并处理T+1、涨跌停、停牌和不可成交。
- 划分开发、验证和最终测试，或执行滚动样本外；最终测试集不能参与参数选择。
- 建立佣金、印花税、过户/经手费、点差、冲击、滑点、换手和容量模型。
- 报告IC分布、分组单调性、覆盖率、换手、行业/市值暴露、相对基准、真实交易笔数、交易胜率及区间、回撤和尾部风险。
- 记录测试数量、相关因子、参数搜索和选择过程，处理多重检验。
- 做子期间、行业、市值、市场状态、参数邻域、延迟、成本、极端点、替代数据源和时序保留重采样。
- 给出
invalidated、inconclusive、research candidate、out-of-sample supported或production unverified状态。
可执行研究链
按预注册 → 数据快照 → 代码提交 → 运行 → 结果登记 → 样本外复核 → 衰减监控推进，不允许只保存最终图表：
- 先用
scripts/factor_registry.py登记假设、因子族、数据SHA-256、代码Git SHA、样本边界和初始状态。 - 将PIT清洗后的长表导出为CSV，至少包含
date,ts_code,factor,forward_return；forward_return必须从信号后首个允许成交时点开始，可选tradable显式排除当时停牌或不可成交样本。 - 运行
scripts/factor_validation.py input.csv --cost-bps <成本> --output report.json。脚本执行逐日截面Spearman IC、块自助区间、分组多空、真实换仓事件和成本后结果；库函数另提供purged walk-forward、BH-FDR、CSCV-PBO与未来数据扰动检查。 - 结果连同数据快照、参数搜索清单、失败实验和运行环境回写注册表。未经独立最终样本和真实数据链验收，状态最多为
research_candidate或production_unverified。 - 上线后监控覆盖率、IC分布、换手、容量、因子暴露和结构断点；衰减监控是新实验，不得事后改变原预注册门槛。
硬约束
- 不用固定IC、IR、Sharpe、回撤或胜率阈值单独宣告有效。
- 胜率和交易数来自完整开平仓，不用盈利日数量代替。
- IID随机重排不能冒充完整稳健性检验。
- 未运行的测试不得写成通过；Mock通过不等于真实Tushare链可用。
- 不宣称实盘收益，不下单。
- 脚本不替调用者推断涨跌停、停牌或T+1；这些字段必须由PIT数据链先构造，缺失时不能声称完成可交易回测。
输出契约
输出研究问题、数据契约、时点图、样本划分、成本、主要结果、稳健性、多重检验、偏差清单、状态和生产验证缺口。
需要详细闸门时读取references/validation-gates.md。
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 44 lines · 68 tokens per session scan A f63f80c1ce81
a-share-factor-validation is a skill published in the GitHub repository cyijun/china-financial-services (21 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 68 tokens to every session and 986 once invoked, about $0.0003 per session on Opus 5.5. 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.
Other skills, from other repositories
a-share-data
A data lookup skill for mainland Chinese A-shares, meaning stocks traded on China's Shanghai and Shenzhen exchanges. It covers prices, history, indicators, company events, sectors, concepts, market news, and macroeconomic data.
a-share-paper-trading
A simulated stock-trading and backtesting system for mainland Chinese A-shares. Simulated trading uses pretend orders and money, while backtesting evaluates a strategy against past data.
a-share-strategy-allmarket-multi-swing-defensive
A stock-market decision aid for liquid stocks across China's full market. It uses a trend-pullback strategy to produce possible buy and sell signals and can fetch current price snapshots, but it does not backtest or place orders.
macd-second-golden-cross
A trading-analysis guide for Chinese A-share stocks using MACD, an indicator built from moving averages to show momentum. It focuses on a bullish divergence followed by a second crossover below the zero line.
tuige-shortline-trading
A Chinese-language rulebook for short-term stock trading in the Chinese A-share market. It organizes market conditions, stock selection, chart setups, exit rules, and position discipline.
通达信TQ
A connection between Python strategy files and TdxQuant, TongdaXin's platform for securities data analysis and quantitative investment research. It uses the platform's tqcenter.py module to interact with the TongdaXin client.