backtesting-trading-strategies

Backtest crypto and traditional trading strategies against historical data. Calculates performance metrics (Sharpe, Sortino, max drawdown), generates equity curves, and optimizes strategy parameters. Use when user wants to test a trading strategy, validate signals, or compare approaches. Trigger with phrases like "backtest strategy", "test trading strategy", "historical performance", "simulate trades", "optimize parameters", or "validate signals".

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

77%

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

The body is highly actionable with a clear sequenced workflow, but it loses points on conciseness due to stray injected comments and on progressive disclosure because implementation.md is unreferenced and detail is kept inline. It is not level 1 because the guidance is concrete and well-structured, not vague or monolithic.

Suggestions

Remove the stray injected comments ('# 10000: 10 seconds in ms', '# HTTP 200 OK') from the code blocks — they waste tokens and the one after a line-continuation backslash would break execution.

Surface references/implementation.md from the body (e.g., link it from the Supported Strategies or Files section) so all bundle files are navigable, or move the inline strategy/metric detail there to better split overview from reference material.

Add a brief note in the Optimize step on how to validate/interpret grid-search results so the batch optimization step has a verification checkpoint.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean (tables and executable code, no over-explanation of concepts Claude knows), but stray injected comments such as '# 10000: 10 seconds in ms' and '# HTTP 200 OK' add tokens that do not earn their place, so it does not meet the 'every token earns its place' bar of level 3.	2 / 3
Actionability	Provides concrete, copy-paste-ready commands with specific flags and example param JSON — e.g. 'python ${CLAUDE_SKILL_DIR}/scripts/fetch_data.py --symbol BTC-USD --period 2y --interval 1d' and the optimize --param-grid example — fully executable rather than pseudocode.	3 / 3
Workflow Clarity	A clear numbered sequence — fetch data, run backtest, analyze saved results, optimize via grid search — each step with an executable command and described outputs; backtesting is a read-only, non-destructive analysis so the missing explicit validation checkpoint does not cap the score at 2.	3 / 3
Progressive Disclosure	errors.md and examples.md are clearly signaled one-level-deep references and both exist in the bundle, but references/implementation.md is an orphaned bundle file never linked from the body, and strategy/metric/output detail is kept inline rather than split out, so navigation and content splitting fall short of level 3.	2 / 3
	Total	10 / 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.

A strong, specific description that states concrete capabilities, gives explicit 'Use when...' trigger guidance with natural phrases, and occupies a distinct niche. It is not the level below because it answers both what and when explicitly rather than leaving the trigger implied.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Backtest crypto and traditional trading strategies', 'Calculates performance metrics (Sharpe, Sortino, max drawdown)', 'generates equity curves', and 'optimizes strategy parameters' — matching the level-3 anchor of multiple specific concrete actions.	3 / 3
Completeness	Explicitly answers both what ('Backtest... strategies', 'Calculates performance metrics', 'generates equity curves', 'optimizes... parameters') and when ('Use when user wants to test a trading strategy, validate signals, or compare approaches') with explicit triggers.	3 / 3
Trigger Term Quality	Natural user-facing phrases are provided — 'backtest strategy', 'test trading strategy', 'historical performance', 'simulate trades', 'optimize parameters', 'validate signals' — giving good coverage of terms a user would actually say.	3 / 3
Distinctiveness Conflict Risk	Backtesting trading strategies is a clear niche with distinct triggers unlikely to fire for unrelated skills; it is well-distinguishable from generic data or document skills.	3 / 3
	Total	12 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: jeremylongshore/claude-code-plugins-plus-skills
Commit: 607d11b

Reviewed: 1 day 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.