mcpField
E
edge-strategy-reviewer

edge-strategy-reviewer

github.com/mphinanceOther3288 installsUpdated 3d ago
Repository

About edge-strategy-reviewer

A deterministic quality gate for strategy drafts produced by `edge-strategy-designer`. It scores drafts against eight weighted criteria, assigns PASS, REVISE, or REJECT, and checks export eligibility.

Key features

  1. 01Weighted scoring across eight criteria
  2. 02Calculates an overall confidence score
  3. 03Assigns PASS, REVISE, or REJECT verdicts
  4. 04Checks draft export eligibility
  5. 05Writes YAML, JSON, and optional Markdown

Use cases

  1. 01Reviewing drafts before export
  2. 02Auditing a directory of strategy drafts
  3. 03Manually checking a strategy's market plausibility

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/mphinance/alpha-skills --skill edge-strategy-reviewer

After installing, type/edge-strategy-reviewerin Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

README.md
references/
overfitting_checklist.md
review_criteria.md
scripts/
review_strategy_drafts.py
scripts/tests/
conftest.py
test_review_strategy_drafts.py

Details

From the project README

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

# Review all drafts in a directory
python3 skills/edge-strategy-reviewer/scripts/review_strategy_drafts.py \
  --drafts-dir reports/edge_strategy_drafts/ \
  --output-dir reports/

# Single draft review
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
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
python3 skills/edge-strategy-reviewer/scripts/review_strategy_drafts.py \
  --drafts-dir reports/edge_strategy_drafts/ \
  --output-dir reports/ \
  --strict-export

Output Format

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

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

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

Comments

Markdown supported