backtest-expert

Expert guidance for systematic backtesting of trading strategies. Use when developing, testing, stress-testing, or validating quantitative trading strategies. Covers "beating ideas to death" methodology, parameter robustness testing, slippage modeling, bias prevention, and interpreting backtest results. Applicable when user asks about backtesting, strategy validation, robustness testing, avoiding overfitting, or systematic trading development.

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is well-structured and highly actionable with a clear sequenced workflow and properly bundled one-level-deep references. The main weakness is redundancy across sections that inflates token count without adding new information.

Suggestions

Consolidate the repeated execution-friction guidance: 'Punish the Strategy' (Key Testing Principles) overlaps Step 4's 'Execution friction' — keep one canonical list and cross-reference it instead of restating.

Merge 'Common Failure Patterns' with the earlier 'Warning signs' in Step 5 to avoid restating the same six failure modes twice.

Move the per-dimension scoring detail of evaluate_backtest.py into references/methodology.md and keep only the invocation example + verdict summary inline to tighten the core SKILL.md.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and assumes competence (no explanations of basic backtesting concepts), but repeats material: "Punish the Strategy" restates Step 4's execution friction, and "Common Failure Patterns" restates the earlier warning signs. Not score 3 because the redundancy could be tightened; not score 1 because it does not pad with concepts Claude already knows.	2 / 3
Actionability	Provides an executable, copy-paste-ready command (python3 skills/backtest-expert/scripts/evaluate_backtest.py with concrete flags), specific parameter sweep values, and a concrete ✅/🔄/❌ decision criteria. Not score 2 because the guidance is fully executable rather than pseudocode.	3 / 3
Workflow Clarity	A clearly sequenced 6-step workflow with feedback checkpoints ("If fundamentally broken, iterate on hypothesis", walk-forward warning signs) and an explicit decision-criteria checklist. Not score 2 because validation/iteration checkpoints are explicit rather than implicit.	3 / 3
Progressive Disclosure	SKILL.md is an overview that points to real one-level-deep references (references/methodology.md, references/failed_tests.md, both present) with "When to read" guidance, and bundles the evaluation script. Not score 2 because references are clearly signaled and one level deep, not nested.	3 / 3
	Total	11 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific, trigger-rich, and complete, with explicit both "what" and "when" clauses in third-person voice. It carves a clear niche unlikely to conflict with other skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "developing, testing, stress-testing, or validating quantitative trading strategies" plus "parameter robustness testing, slippage modeling, bias prevention, and interpreting backtest results" — matching the anchor for listing several specific concrete actions.	3 / 3
Completeness	Explicitly answers both what ("Expert guidance for systematic backtesting…Covers…") and when ("Use when developing, testing, stress-testing…Applicable when user asks about backtesting…"), with explicit trigger clauses. Not score 2 because the when is explicit, not merely implied.	3 / 3
Trigger Term Quality	Covers natural terms a user would say — "backtesting, strategy validation, robustness testing, avoiding overfitting, or systematic trading development" — giving good coverage rather than just jargon. Not score 2 because common user phrasings like "backtesting" and "strategy validation" are all present.	3 / 3
Distinctiveness Conflict Risk	Has a clear niche — systematic/quantitative backtesting of trading strategies — with distinct triggers unlikely to fire for unrelated skills. Not score 2 because the domain and triggers are specific enough to avoid overlap.	3 / 3
	Total	12 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: tradermonty/claude-trading-skills
Path: skills/backtest-expert/SKILL.md
Commit: 62a1635

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.