菜单
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.
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 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.
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.
| name | cta-research-loop |
| description | 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. |
| allowed-tools | ["cta__artifact_find","cta__artifact_load","cta__archive_candidate","cta__archive_lineage","cta__proposal_generate","cta__approval_list","cta__approval_resolve","cta__apply_approved_transition"] |
Use this skill for persisted CTA research state, proposal generation, and archive governance inside Aura.
references/tool_contract.md, then use artifact and archive tools.StrategySpec, ExperimentSpec, and optional EvalReport, then call cta__proposal_generate.cta__archive_candidate.references/current_limits.md first. If no deterministic harness exists, stop and propose or implement the missing assembler instead of fabricating execution.references/research_playbook.md..archive/, .aura/, or large data directories with generic file listing when restoring CTA state; use CTA tools and targeted refs first.state_summary, evidence, recommended_action, blocked_by.evidence, cite concrete artifact refs, archive ids, approval ids, or report ids actually loaded in this turn.recommended_action, distinguish between proposal, approval_decision, archive_transition, and implementation_gap.StrategySpec -> executable strategy module path unless the repo has added one.references/tool_contract.md for task-to-tool mapping and payload expectations.references/current_limits.md when the task touches fresh execution, generic strategy compilation, or runtime boundaries.references/research_playbook.md for concrete end-to-end task patterns.references/response_contract.md when you need exact output shapes for state review, proposal, governance, or blocked execution tasks.