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

86%

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

72%Weight 40%Scale 1-3

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

The body is actionable and well-structured with executable commands and clean progressive disclosure to real reference files. Its weaknesses are redundant feature/table duplication, stray nonsensical code comments, and a lack of validation checkpoints in the workflow.

Suggestions

Remove the duplicate 'Key Features' strategy and metric lists since they reappear verbatim in the 'Supported Strategies' and Output tables.

Delete the out-of-place comments in the code blocks ('# HTTP 200 OK' on the param-grid line, '# 10000: 10 seconds in ms' on capital/commission values) — they are unrelated to the content and confuse readers.

Add a validation/verification checkpoint to the workflow, e.g. confirm the data cache exists after fetch_data.py and verify the report files were generated in ${CLAUDE_SKILL_DIR}/reports/ before analyzing.

Dimension	Reasoning	Score
Conciseness	Mostly efficient tables and code, but the 'Key Features' bullet list re-lists the 8 strategies and metrics that appear again in dedicated tables, and odd injected comments ('# HTTP 200 OK', '# 10000: 10 seconds in ms') add noise without earning their tokens. Not a 1 because it avoids explaining concepts Claude already knows; not a 3 due to the redundancy and noise.	2 / 3
Actionability	Provides fully executable, copy-paste-ready commands with concrete flags and JSON params — 'python ${CLAUDE_SKILL_DIR}/scripts/backtest.py --strategy rsi_reversal ... --params '{"period": 14, ...}'' — plus a strategies table with key parameters and a config YAML example.	3 / 3
Workflow Clarity	Steps are clearly numbered (fetch data → run backtest → analyze results → optimize) but there are no validation or verification checkpoints for the batch/grid optimize step or data-fetch step, capping the score at 2 per the destructive/batch guideline.	2 / 3
Progressive Disclosure	SKILL.md is a clear overview with well-signaled one-level-deep references to real files ('See ${CLAUDE_SKILL_DIR}/references/errors.md', 'references/examples.md') and a Files table listing the scripts; content is appropriately split. Not below 3 because referenced paths resolve to actual bundle files.	3 / 3
	Total	10 / 12 Passed

Description

100%Weight 40%Scale 1-3

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 concise, third-person, and clearly states both capabilities and explicit trigger conditions with natural user phrases. It hits all anchors at the top level with no fluff or over-claims.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Backtest crypto and traditional trading strategies', 'Calculates performance metrics (Sharpe, Sortino, max drawdown)', 'generates equity curves', 'optimizes strategy parameters' — matching the score-3 anchor.	3 / 3
Completeness	Explicitly answers both what (backtest, calculate metrics, generate equity curves, optimize) and when via a 'Use when user wants to test a trading strategy, validate signals, or compare approaches' clause.	3 / 3
Trigger Term Quality	Provides natural phrases users would say — 'backtest strategy', 'test trading strategy', 'historical performance', 'simulate trades', 'optimize parameters', 'validate signals' — giving good coverage.	3 / 3
Distinctiveness Conflict Risk	Backtesting trading strategies is a clear niche with distinct, domain-specific triggers unlikely to collide with other 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
Path: plugins/crypto/trading-strategy-backtester/skills/backtesting-trading-strategies/SKILL.md
Commit: 4c47e33

Reviewed: 3 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.