菜单
Use whenever the task is to fetch, backfill, sync, repair, slice, inspect, or featureize AuraQuant CTA market data. Trigger on requests about OHLCV history, gap filling, data versions, data slices, feature slices, or local data storage layout.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Use whenever the task is to run CTA experiments, inspect eval reports, compare results, or turn structured backtest/evaluation output into the next research decision in AuraQuant.
Use whenever the task is to inspect archive lineage, write candidate records, request freeze transitions, resolve approvals, or advance CTA strategy lifecycle state in AuraQuant. Trigger on candidate, frozen, production, deprecated, archive, lineage, or approval requests.
Use whenever the user wants to advance CTA research in AuraQuant, asks what the next step is, wants the agent to take over the overall research loop, or needs a cross-stage decision spanning data, specs, runtime modules, experiments, evaluation, and archive governance.
Use whenever the task is to define or update CTA runtime modules or specs in AuraQuant, including baseline/filter/execution/risk code under cta_runtime, spec persistence, runtime validation, and first-run assembly with default modules.
Use for CTA research inside Aura when the task is to inspect archived runs, review evaluation artifacts, generate the next structured proposal, or advance approval-gated archive state. Do not use it for generic coding or to invent unsupported execution capability.
| name | cta-data-operator |
| description | Use whenever the task is to fetch, backfill, sync, repair, slice, inspect, or featureize AuraQuant CTA market data. Trigger on requests about OHLCV history, gap filling, data versions, data slices, feature slices, or local data storage layout. |
负责数据阶段的执行细节。主研究 agent 只消费你返回的结构化摘要。
你做：
你不做：
data/ 或 .archive/ 文件名DataVersion / DataSlice 对象直接用散落文件名作为状态统一 JSON CLI：python -m auraquant.cta --format json <command>
| 任务类型 | 命令 | 说明 |
|---|---|---|
| 长历史初始化 | data backfill-ohlcv --symbol BTC/USDT --tf 1h --since 2020-01-01 | 首次获取或补历史 |
| 增量同步 | data sync-ohlcv --symbol BTC/USDT --tf 1h | 从本地末端补到当前 |
| 修复缺口 | data repair-ohlcv --symbol BTC/USDT --tf 1h --version <ver> | 定向修复版本内缺口 |
| 构建切片 | data slice build --version <ver> --start 2022-01-01 --end 2023-01-01 | 产出 DataSlice |
| 构建特征 | feature build --slice <slice_id> --config <feature_config> | 产出 FeatureSlice |
数据存在性检查用 cta__data_version_list(venue=..., symbol=..., timeframe=...)。
cta__data_version_list 返回至少一个匹配项row_count 与时间范围符合实验 window_scheduleanomaly / missing_bars 超过阈值closed bar onlydata_operator_summary:
task_type: backfill | sync | repair | slice | feature
version_id: <DataVersion id>
slice_id: <DataSlice id，如适用>
feature_slice_id: <FeatureSlice id，如适用>
symbol: <交易对>
timeframe: <周期>
row_count: <行数>
time_range: [start, end]
gaps_remaining: <None 或缺口描述>
next_recommended: <建议主 agent 的下一步>