Skill

Pass

Audit score 90

edge-strategy-reviewer

Q: What triggers a REJECT verdict?

Immediate REJECT if C1 (edge plausibility) or C2 (overfitting risk) has severity=fail, or if confidence score is below 35%.

Q: What is the difference between PASS and REVISE?

PASS: confidence ≥70% with no fail findings; REVISE: confidence 35–70% or fail findings in non-critical criteria; REJECT: confidence <35% or critical failures.

Q: Can I review a single draft file?

Yes, use --draft /path/to/single_draft.yaml instead of --drafts-dir to review one file.

Q: What does export_eligible mean?

A draft is export-eligible if it has PASS verdict, export_ready_v1 flag set, and belongs to an exportable family; strict-export mode downgrades PASS to REVISE if any warnings exist.

Q: How does the bias checklist work?

When --bias-checklist is enabled, the script applies a mandatory strategy-research bias gate; any unaddressed required items downgrade PASS to REVISE and remove export eligibility.

tradermonty/claude-trading-skills

Quality gate for trading strategy drafts—evaluates edge plausibility, overfitting risk, and execution realism before pipeline export.

Source View on skills.sh

What is edge-strategy-reviewer?

Deterministically reviews strategy YAML files from edge-strategy-designer against 8 weighted criteria (edge plausibility, overfitting risk, sample adequacy, regime dependency, exit calibration, risk concentration, execution realism, invalidation quality). Use after strategy generation and before exporting to the pipeline; outputs PASS/REVISE/REJECT verdicts with confidence scores.

Load and evaluate strategy draft YAML files against 8 criteria with weighted scoring
Compute confidence score and determine verdict (PASS ≥70% / REVISE 35–70% / REJECT <35%)
Assess export eligibility based on verdict, export_ready_v1 flag, and exportable family
Detect overfitting via 5-tier filter count scoring and precise threshold penalties
Validate edge plausibility through thesis quality, domain terminology, and mechanism keywords
Generate YAML or JSON review output with findings and revision instructions

How to install edge-strategy-reviewer

npx skills add https://github.com/tradermonty/claude-trading-skills --skill edge-strategy-reviewer

Prerequisites

Strategy draft YAML files (output of edge-strategy-designer)
Python 3.10 or later
PyYAML library

Claude Code

Cursor

Windsurf

Cline

How to use edge-strategy-reviewer

1.Install the skill via npx skills add
2.Place strategy draft YAML files in a designated directory (e.g., reports/edge_strategy_drafts/)
3.Run the review script with --drafts-dir or --draft flag pointing to your drafts
4.Optionally add --format json, --markdown-summary, --strict-export, or --bias-checklist flags
5.Review the generated review.yaml (or review.json) output with verdicts and confidence scores
6.Address any REVISE or REJECT findings and re-run the reviewer on updated drafts
7.Export PASS-verdict drafts to the edge-candidate-agent pipeline

Use cases

Good for

Review all strategy drafts in a directory before batch pipeline export
Single-draft validation during manual strategy development and iteration
Strict export mode to ensure only high-confidence, bias-checked strategies proceed
Generate markdown summaries for stakeholder review of strategy quality metrics
Detect overfitting and sample-size inadequacy before live trading deployment

Who it's for

Quantitative traders and strategy developers using edge-strategy-designer
Risk managers validating strategy quality before pipeline export
Algo trading teams implementing deterministic quality gates
Researchers evaluating strategy robustness and regime dependency

edge-strategy-reviewer FAQ

What triggers a REJECT verdict?

Immediate REJECT if C1 (edge plausibility) or C2 (overfitting risk) has severity=fail, or if confidence score is below 35%.

What is the difference between PASS and REVISE?

PASS: confidence ≥70% with no fail findings; REVISE: confidence 35–70% or fail findings in non-critical criteria; REJECT: confidence <35% or critical failures.

Can I review a single draft file?

Yes, use --draft /path/to/single_draft.yaml instead of --drafts-dir to review one file.

What does export_eligible mean?

A draft is export-eligible if it has PASS verdict, export_ready_v1 flag set, and belongs to an exportable family; strict-export mode downgrades PASS to REVISE if any warnings exist.

How does the bias checklist work?

When --bias-checklist is enabled, the script applies a mandatory strategy-research bias gate; any unaddressed required items downgrade PASS to REVISE and remove export eligibility.

Full instructions (SKILL.md)

Source of truth, from tradermonty/claude-trading-skills.

name: edge-strategy-reviewer description: > 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.

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

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

Review Criteria

#	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

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

# 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)

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

Related skills

More from tradermonty/claude-trading-skills and the wider catalog.

exposure-coach

tradermonty/claude-trading-skills

Synthesize market signals into a unified exposure ceiling and portfolio posture recommendation.

2.7k installsAudited

finviz-screener

tradermonty/claude-trading-skills

Build and open FinViz screener URLs from natural language stock filtering requests in English or Japanese.

3.0k installsAudited

ftd-detector

tradermonty/claude-trading-skills

Detect market bottoms and rally confirmation using William O'Neil's Follow-Through Day methodology.

2.9k installs

futures-position-sizer

tradermonty/claude-trading-skills

Calculate futures contract position sizes from direction, entry, and stop-loss using verified per-symbol specs.

2.1k installs

fxmacrodata-calendar

tradermonty/claude-trading-skills

Fetch official macro release-calendar events for trade planning and event-risk filtering.

2.0k installsAudited

ibd-distribution-day-monitor

tradermonty/claude-trading-skills

Detect IBD Distribution Days on QQQ/SPY and recommend TQQQ/QQQ exposure adjustments based on market deterioration risk.

2.5k installsAudited