backtesting-frameworks

Build robust, production-grade backtesting systems that avoid common pitfalls and produce reliable strategy performance estimates.

Quality

50%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/backtesting-frameworks/SKILL.md

Quality

Content

46%Weight 40%Scale 1-5

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-organized, appropriately brief, and honest about scope and safety limits, but it fails on substance: instructions remain at the headline level with no concrete executable guidance, and the one reference it relies on for detail points to a missing file. A reader following it would hit a dead end at the Resources section.

Suggestions

Ship the referenced resources/implementation-playbook.md (or remove/fix the reference) so the two pointers to it in Instructions and Resources resolve to real content.

Add concrete, actionable guidance in the body: name the specific biases to guard against (look-ahead, survivorship, overfitting) and give a concrete walk-forward procedure rather than 'use train/validation/test splits and walk-forward testing'.

Trim the generic 'Limitations' boilerplate that applies to any skill and keep only backtesting-specific caveats.

Dimension	Reasoning	Score
Conciseness	The body is lean with no explanations of concepts Claude already knows, but the generic 'Limitations' boilerplate and the 'Use this skill when' bullets that mirror the description are minor padding that could be trimmed.	4 / 5
Actionability	Instructions are high-level directives ('Build point-in-time data pipelines and realistic cost models') with no concrete commands, examples, or named biases, and all detail is deferred to 'resources/implementation-playbook.md' — a file that does not exist in the bundle.	2 / 5
Workflow Clarity	The instruction bullets form a rough logical sequence (define → data → simulate → validate) and mention train/validation/test splits, but there are no explicit validation checkpoints or error-recovery feedback loops.	3 / 5
Progressive Disclosure	The single external reference ('resources/implementation-playbook.md') is clearly signaled but broken — no resources/ directory exists — so the promised detailed patterns are inaccessible, leaving the skill with minimal effective structure for deeper content.	2 / 5
	Total	11 / 20 Passed

Description

53%Weight 40%Scale 1-5

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 clearly communicates the niche and purpose of the skill but stops short of the anchor-5 pattern: it lacks an explicit 'Use when...' trigger clause, omits natural synonyms users would say, and gestures at 'common pitfalls' without naming them. It is serviceable but noticeably below the best examples in the rubric.

Suggestions

Add an explicit trigger clause, e.g. 'Use when building trading strategy backtests, running walk-forward analysis, or validating strategy performance on historical data.'

Name the concrete actions and pitfalls (e.g., look-ahead bias, survivorship bias, overfitting, walk-forward testing) instead of the generic 'avoid common pitfalls'.

Include natural synonyms users would say such as 'backtest', 'trading strategy', and 'historical performance' to improve trigger term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('backtesting systems') with one concrete action ('build... systems') plus goal statements ('avoid common pitfalls', 'produce reliable strategy performance estimates'), but 'common pitfalls' and 'production-grade' are unspecified and no sub-actions like walk-forward analysis are listed.	3 / 5
Completeness	The 'what' is clear (build production-grade backtesting systems), but the description contains no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines.	3 / 5
Trigger Term Quality	'backtesting systems' and 'strategy performance estimates' are relevant keywords, but common user phrasings such as 'backtest', 'trading strategy', or 'walk-forward' are missing, matching the 'some relevant keywords but missing common variations' anchor.	3 / 5
Distinctiveness Conflict Risk	'Backtesting systems' is a clear niche with distinct triggers, though it could minorly overlap with general quantitative-finance or data-analysis skills; fits 'mostly distinct; minor overlap risk'.	4 / 5
	Total	13 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: sickn33/agentic-awesome-skills
Path: skills/backtesting-frameworks/SKILL.md
Commit: 7b534bc

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.