AA

    A股盘面回测 · A-Share Backtester

    1

    把盘面信号整理成可回测的策略假设,输出回测口径、样本与风险提示。 Turn market signals into backtestable strategy hypotheses with backtesting scope, samples, and risk warnings.

    $7

    Secure checkout via Stripe

    30-day refund guarantee

    Converts to your local currency at checkout

    0 installsSecurity scanned

    Works with the AI tools you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIGitHub CopilotGitHub CopilotGemini CLIGemini CLI+20 more
    AA

    A股盘面回测 · A-Share Backtester

    Example session with this skill installed

    请把「放量突破 20 日高点后买入」这个想法整理成可回测的策略假设。

    • Read your context and instructions
    • Compiled the a a-share backtester

    A股盘面回测方案已生成。

    假设

    沪深 300 成分股中,放量突破 20 日高点后买入,未来 20 日超额收益 > 2%。

    规则

    • 买入:收盘价突破 20 日高点且成交量 > 1.5 倍均量
    • 卖出:跌破 10 日均线或持有 20 日
    • 仓位:单票 5%,最多 10 只
    • 止损:-8%

    回测口径

    • 样本:2019-2024 沪深 300 成分股
    • 基准:沪深 300 指数
    • 指标:年化超额、最大回撤、胜率

    风险提示

    • 剔除 ST 与停牌股
    • 注意前视偏差(信号用当日收盘价确认)
    • 覆盖牛熊两段行情

    Next steps

    1. 先跑 2019-2021 单段验证。
    2. 与纯 20 日动量规则对比。
    3. 参数做敏感性测试(1.2x/1.8x 量能)。

    Connects securely to your tools. The creator never sees your data.

    What you get

    Convert market observations into falsifiable strategy hypotheses.Define technical entry, exit, and stop-loss rules for A-share trading.Generate structured documentation for team strategy reviews.Identify survivorship and look-ahead biases in proposed models.

    About this skill

    它解决什么问题

    观察A股市场的想法从未得到检验：没有假设，没有入场规则，也无法区分信号和运气。

    这个技能做什么

    • 将市场观察转化为可证伪的策略假设。
    • 定义进入、退出、持仓和停止规则。
    • 设置回测窗口、基准测试和评估指标。
    • 列出需要控制的生存风险和前瞻性风险。

    为什么比裸提示词强

    它强制执行一个测试框架：假设、规则、样本、基准和风险控制，因此结果是可检查的而不是轶事。

    典型用例

    • 在模拟交易前验证突破信号。
    • 沪深300股票两种动量规则的比较。
    • 记录团队审查的策略。

    局限

    它设计测试，而不是执行引擎；实际的回测还是需要数​​据和代码。

    English · 英文介绍

    The problem

    Ideas from watching the A-share market never get tested: no hypothesis, no entry rules, and no way to tell signal from luck.

    What it does

    • Turns a market observation into a falsifiable strategy hypothesis.
    • Defines entry, exit, position, and stop rules.
    • Sets backtest windows, benchmarks, and evaluation metrics.
    • Lists survivorship and look-ahead risks to control.

    Why this beats prompting it yourself

    It enforces a test frame: hypothesis, rules, sample, benchmark, and risk controls, so results are checkable instead of anecdotal.

    Use cases

    • Validating a breakout signal before paper trading.
    • Comparing two momentum rules on CSI 300 stocks.
    • Documenting a strategy for team review.

    Known limitations

    It designs the test, not the execution engine; actual backtesting still needs data and code.

    How to install

    Works the same in every agent - Claude, Cursor, Codex, Copilot and 20+ more.

    ~30 seconds
    1. 1

      Download the ZIP

      Free skills download straight away. Paid skills unlock right after purchase.

    2. 2

      Unzip into your skills folder

      Every agent reads skills from one folder on your machine. Drop the unzipped folder in there.

    3. 3

      Ask your agent to use it

      Restart the agent if it was already running. It picks the skill up automatically - no config needed.

    Skills folder by agent

    Click the path to copy it. Create the folder if it does not exist yet.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill passes our trust checks below.

    Security scanned

    Passed our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    30-day refund

    Not a fit? Get your money back

    Trust & safety

    Security scanned

    Verified clean today

    • Passed all security checks, Safe to install

    Listedtoday

    Frequently Asked Questions