backtesting-frameworks

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

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

72%

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

The body is concise and well-structured with good progressive disclosure, but the instructions remain abstract and lack concrete execution detail and explicit validation checkpoints. Adding specific, executable guidance and validation feedback loops would raise actionability and workflow clarity.

Suggestions

Make instructions more concrete: specify how to structure train/validation/test splits, give a minimal event-driven simulation skeleton, and name realistic cost-model components (spread, slippage, fees).

Add an explicit validation/feedback checkpoint, e.g. 'After each walk-forward window, re-check for look-ahead bias and overfitting before proceeding.'

Verify the referenced bundle file exists and aligns the path with the actual bundle directory ('references/' rather than 'resources/') so the signaled reference is real.

Dimension	Reasoning	Score
Conciseness	The body is lean (~40 lines), uses terse bullets, and avoids explaining concepts Claude already knows; every section earns its place.	3 / 3
Actionability	Instructions list real steps but stay abstract ('Build point-in-time data pipelines', 'Implement event-driven simulation') without concrete specifics, parameters, or copy-paste examples.	2 / 3
Workflow Clarity	A sequence is present (define → build data → simulate → validate), but there are no explicit validation checkpoints or feedback loops for the validation-heavy, batch-oriented work this skill describes.	2 / 3
Progressive Disclosure	A short, well-organized overview with clearly signaled one-level-deep reference ('resources/implementation-playbook.md'), matching the simple-skill guidance that allows a 3 with well-organized sections.	3 / 3
	Total	10 / 12 Passed

Description

50%

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 conveys a focused niche (backtesting) and what the skill does, but relies on abstract capability language and omits any explicit 'Use when...' trigger clause. Adding concrete actions and natural trigger terms would lift specificity, completeness, and trigger quality.

Suggestions

Append a 'Use when...' clause with natural triggers, e.g. 'Use when building trading strategy backtests, validating strategy performance, or doing walk-forward analysis.'

Replace abstract verbs ('build robust systems', 'avoid common pitfalls') with a few concrete actions (e.g., 'Design event-driven backtests, model transaction costs, run walk-forward validation').

Add common trigger variations users would actually say (e.g., 'backtest', 'strategy validation', 'overfitting', 'point-in-time data').

Dimension	Reasoning	Score
Specificity	It names the domain ('backtesting systems') and some actions ('build...avoid common pitfalls...produce reliable...estimates'), but these are abstract capabilities rather than a list of concrete enumerable actions.	2 / 3
Completeness	The 'what' is clearly stated but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 2 per the judging guidelines.	2 / 3
Trigger Term Quality	'backtesting' and 'trading strategy performance' are relevant keywords a user might say, but coverage is limited with no common variations and no natural 'Use when...' phrasing.	2 / 3
Distinctiveness Conflict Risk	'Backtesting systems' is a distinct niche unlikely to conflict, but the absence of explicit trigger language keeps it from a clean 3 and leans toward the 'somewhat specific' anchor.	2 / 3
	Total	8 / 12 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/antigravity-awesome-skills
Commit: 5e71bba

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.