edge-strategy-reviewer

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Edge Strategy Reviewer

边缘策略评审工具

Deterministic quality gate for strategy drafts produced by

edge-strategy-designer

为

edge-strategy-designer

生成的策略草案提供确定性质量管控入口。

When to Use

适用场景

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

当

edge-strategy-designer

生成

strategy_drafts/*.yaml

文件后

在通过流水线将草案导出到
```
edge-candidate-agent
```
之前
需要手动验证策略草案的边缘合理性时

Prerequisites

前置依赖

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

策略草案YAML文件（
```
edge-strategy-designer
```
的输出产物）
安装了PyYAML的Python 3.10+环境

Workflow

工作流程

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

从
```
--drafts-dir
```
指定的目录加载草案YAML文件，或加载
```
--draft
```
指定的单个草案文件
按照8项评审标准（C1-C8）对每个草案进行加权评分
计算置信度得分（所有标准得分的加权平均值）
得出判定结果：PASS / REVISE / REJECT
评估导出资格（PASS + 符合export_ready_v1标准 + 属于可导出类别）
写入评审输出（YAML或JSON格式）以及可选的markdown格式汇总报告

Review Criteria

评审标准

#	Criterion	Weight	Key Checks
C1	Edge Plausibility	20	Thesis quality, domain terms, mechanism keywords (continuous 50-95)
C2	Overfitting Risk	20	5-tier filter count scoring (90/80/60/40/10), precise threshold penalty
C3	Sample Adequacy	15	Continuous scoring from estimated annual opportunities (10-95)
C4	Regime Dependency	10	Cross-regime validation
C5	Exit Calibration	10	Stop-loss, reward-to-risk
C6	Risk Concentration	10	Position sizing limits
C7	Execution Realism	10	Volume filter, export consistency
C8	Invalidation Quality	5	Signal count and specificity

#	评审项	权重	核心检查点
C1	边缘合理性	20	论点质量、领域术语、机制关键词（连续得分区间50-95）
C2	过拟合风险	20	5级过滤器计数评分（90/80/60/40/10），精确阈值扣分规则
C3	样本充足性	15	基于预估年度机会的连续评分（区间10-95）
C4	场景依赖性	10	跨场景验证情况
C5	退出机制校准	10	止损设置、风险收益比
C6	风险集中度	10	仓位规模限制
C7	执行可行性	10	成交量过滤器、导出一致性
C8	失效判定质量	5	信号数量与特异性

Verdict Logic

判定逻辑

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

C1或C2严重程度为fail → 直接判定REJECT
置信度≥70，无fail项 → 判定PASS
置信度<35 → 判定REJECT
其他情况 → 判定REVISE（附带修改指引）

Running the Script

运行脚本

bash

undefined

bash

undefined

Review all drafts in a directory

评审目录下的所有草案

python3 skills/edge-strategy-reviewer/scripts/review_strategy_drafts.py
--drafts-dir reports/edge_strategy_drafts/
--output-dir reports/

Single draft review

评审单个草案

python3 skills/edge-strategy-reviewer/scripts/review_strategy_drafts.py
--draft reports/edge_strategy_drafts/draft_xxx.yaml
--output-dir reports/

JSON output with markdown summary

输出JSON格式结果+markdown汇总

python3 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 → REVISE

严格导出模式：符合导出资格的草案只要存在警告就判定为REVISE

python3 skills/edge-strategy-reviewer/scripts/review_strategy_drafts.py
--drafts-dir reports/edge_strategy_drafts/
--output-dir reports/
--strict-export

undefined

python3 skills/edge-strategy-reviewer/scripts/review_strategy_drafts.py
--drafts-dir reports/edge_strategy_drafts/
--output-dir reports/
--strict-export

undefined

Output Format

输出格式

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: 4
summary:
  total: 4
  PASS: 1
  REVISE: 2
  REJECT: 1
  export_eligible: 1
reviews:
  - draft_id: "draft_xxx_core"
    verdict: "PASS"
    confidence_score: 80
    export_eligible: true
    findings: [...]
    revision_instructions: []

主输出文件：

review.yaml

（或

review.json

）

yaml

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

Resources

参考资源

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

```
references/review_criteria.md
```
— C1-C8的详细评分规则
```
references/overfitting_checklist.md
```
— 过拟合检测启发式规则