Edge Strategy Reviewer

作者 tradermontyeab8d5cb97b9无许可证2.9K 个星标收录于 2026年10月8日更新于 2026年10月8日仓库3天前更新

Critically review strategy drafts from edge-strategy-designer for edge plausibility, overfitting risk, sample size adequacy, and execution realism. Use when strategy_drafts/*.yaml exists and needs quality gate before pipeline export. Outputs PASS/REVISE/REJECT verdicts with confidence scores.

包含脚本Business & FinanceData & Analytics
AI 生成的概览

审查交易策略草稿 YAML 文件，给出 PASS、REVISE 或 REJECT 结论及置信度评分。

功能
加载策略草稿 YAML 文件，并依据八项加权标准对每份草稿评分，涵盖边缘合理性、过拟合风险、样本充足性、市场状态依赖性、退出校准、风险集中度、执行现实性和失效质量。它会计算置信度评分，给出 PASS、REVISE 或 REJECT 结论，并判定是否可导出。它输出 review.yaml 或 review.json 文件，可选生成 markdown 摘要，还可应用内置偏差清单，将存在未处理项的草稿降级。
适用场景
适用于策略草稿生成之后、导出到下游流水线之前，或需要对草稿策略进行边缘合理性人工验证时。它是对草稿文件的质量把关，而非策略生成工具。
运行要求
需要 Python 3.10 或更高版本及 PyYAML，并以策略草稿 YAML 文件作为输入。该技能附带可执行脚本（含测试套件），并将结果写入指定目录。

Edge Strategy Reviewer

Deterministic quality gate for strategy drafts produced by edge-strategy-designer.

When to Use

  • After edge-strategy-designer generates strategy_drafts/*.yaml
  • Before exporting drafts to edge-candidate-agent via the pipeline
  • When manually validating a draft strategy for edge plausibility

Prerequisites

  • Strategy draft YAML files (output of edge-strategy-designer)
  • Python 3.10+ with PyYAML

Workflow

  1. Load draft YAML files from --drafts-dir or a single --draft file
  2. Evaluate each draft against 8 criteria (C1-C8) with weighted scoring
  3. Compute confidence score (weighted average of all criteria)
  4. Determine verdict: PASS / REVISE / REJECT
  5. Assess export eligibility (PASS + export_ready_v1 + exportable family)
  6. Write review output (YAML or JSON) and optional markdown summary

Review Criteria

#CriterionWeightKey Checks
C1Edge Plausibility20Thesis quality, domain terms, mechanism keywords (continuous 50-95)
C2Overfitting Risk205-tier filter count scoring (90/80/60/40/10), precise threshold penalty
C3Sample Adequacy15Continuous scoring from estimated annual opportunities (10-95)
C4Regime Dependency10Cross-regime validation
C5Exit Calibration10Stop-loss, reward-to-risk
C6Risk Concentration10Position sizing limits
C7Execution Realism10Volume filter, export consistency
C8Invalidation Quality5Signal count and specificity

Verdict Logic

  • C1 or C2 severity=fail → immediate REJECT
  • confidence >= 70, no fail findings → PASS
  • confidence < 35 → REJECT
  • Otherwise → REVISE (with revision instructions)

Running the Script

bash
# Review all drafts in a directorypython3 skills/edge-strategy-reviewer/scripts/review_strategy_drafts.py \  --drafts-dir reports/edge_strategy_drafts/ \  --output-dir reports/
# Single draft reviewpython3 skills/edge-strategy-reviewer/scripts/review_strategy_drafts.py \  --draft reports/edge_strategy_drafts/draft_xxx.yaml \  --output-dir reports/
# JSON output with markdown summarypython3 skills/edge-strategy-reviewer/scripts/review_strategy_drafts.py \  --drafts-dir reports/edge_strategy_drafts/ \  --output-dir reports/ \  --format json \  --markdown-summary
# Strict export mode: export-eligible drafts with any warn → REVISEpython3 skills/edge-strategy-reviewer/scripts/review_strategy_drafts.py \  --drafts-dir reports/edge_strategy_drafts/ \  --output-dir reports/ \  --strict-export
# Bias checklist (issue #297): mandatory strategy-research bias gate.# Uses the bundled checklist unless a custom YAML path is supplied.# A draft leaving any required item unaddressed is downgraded PASS → REVISE# and loses export eligibility.python3 skills/edge-strategy-reviewer/scripts/review_strategy_drafts.py \  --drafts-dir reports/edge_strategy_drafts/ \  --output-dir reports/ \  --bias-checklist

Output Format

Primary output: review.yaml (or review.json)

yaml
generated_at_utc: "2026-02-28T12:00:00+00:00"source:  drafts_dir: "/path/to/strategy_drafts"  draft_count: 4summary:  total: 4  PASS: 1  REVISE: 2  REJECT: 1  export_eligible: 1reviews:  - draft_id: "draft_xxx_core"    verdict: "PASS"    confidence_score: 80    export_eligible: true    findings: [...]    revision_instructions: []

Resources

  • references/review_criteria.md — Detailed scoring rubric for C1-C8
  • references/overfitting_checklist.md — Overfitting detection heuristics

来源与署名

来源：tradermonty/claude-trading-skills位于skills/edge-strategy-reviewer提交eab8d5c

许可证： 无许可证

内容归原作者所有。SourceWeft 从公开仓库中收录这些内容。

举报或申请下架

更多来自 tradermonty/claude-trading-skills 的技能

Weekly Performance Digest

tradermonty

将已平仓的交易论点汇总为每周绩效报告，包含指标、模式分解和经验教训。

包含脚本
Data & Analytics2.9K3天前更新

Trade Performance Coach

tradermonty

审查已记录的交易，评估流程遵守、风险纪律、执行质量与行为模式，并生成教练报告。

包含脚本
Business & Finance2.9K3天前更新

Strategy Pivot Designer

tradermonty

检测回测迭代停滞，并为交易策略生成结构不同的策略转向方案。

包含脚本
Business & Finance2.9K3天前更新

Skill Designer

tradermonty

Design new Claude skills from structured idea specifications. Use when the skill auto-generation pipeline needs to produce a Claude CLI prompt that creates a complete skill directory (SKILL.md, references, scripts, tests) following repository conventions.

包含脚本
待分类2.9K3天前更新

Residual Edge Analyzer

tradermonty

Separate a strategy return series into declared baseline exposure and residual edge with returns-based OLS attribution, HAC inference, rolling stability, alternate-baseline sensitivity, and regime breakdowns. Use when evaluating whether backtest, out-of-sample, or live returns contain independent alpha beyond market, equal-weight, momentum, sector, or user-supplied factor returns; when explaining whether a drawdown came from baseline exposure or strategy-specific behavior; or when a strategy needs an attribution quality gate after backtesting. Do not use for holdings-based Brinson attribution, feature-level Shapley explanations, or analysis from summary metrics without a dated return series.

包含脚本
待分类2.9K3天前更新

Pre Trade Discipline Gate

tradermonty

离线交易前检查清单闸门，批准、复核或阻止计划中的手动订单并记录决策。

包含脚本
Business & Finance2.9K3天前更新

更多Business & Finance技能

Value Creation Plan

anthropics

精选

构建并购后价值创造计划，将收入、成本与运营杠杆映射到 EBITDA 桥。

Business & Finance39K2周前更新

Swap Curve Strategy

anthropics

精选

利用 MCP 定价工具分析利率互换曲线、互换利差、实际利率与曲线交易机会。

Business & Finance39K2周前更新

Deal Sourcing

anthropics

精选

指导私募股权项目挖掘流程：寻找目标公司、核查 CRM 往来记录，并起草创始人外联邮件。

Business & Finance39K2周前更新

Unit Economics

anthropics

精选

为私募股权标的分析单位经济：ARR 队列、LTV/CAC、净留存、回收期与利润瀑布。

Business & Finance39K2周前更新

Option Vol Analysis

anthropics

精选

通过结合波动率曲面、含希腊字母的期权定价与历史价格，比较隐含波动率与已实现波动率。

Business & Finance39K2周前更新

Dd Meeting Prep

anthropics

精选

为尽职调查会议（如管理层演示、专家访谈）准备问题清单、基准数据和需重点探查的风险信号。

Business & Finance39K2周前更新