CtrlK
BlogDocsLog inGet started
Tessl Logo

backtesting-frameworks

Build robust backtesting systems for trading strategies with proper handling of look-ahead bias, survivorship bias, and transaction costs. Use when developing trading algorithms, validating strategies, or building backtesting infrastructure.

68

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

65%

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

A well-organized, token-efficient instruction skill with clear trigger and anti-trigger lists, but its guidance stays high-level with all specifics deferred to a playbook file that is not present in the bundle, and the multi-step workflow lacks validation checkpoints.

Suggestions

Add a concrete inline example or minimal code/pseudocode for one step (e.g., a point-in-time data pipeline snippet or a walk-forward split schematic) so the skill is actionable without the external file.

Include an explicit validation/verification checkpoint in the Instructions (e.g., 'verify no look-ahead leakage by checking each feature uses only data available at decision time') to lift workflow clarity.

Provide the referenced `resources/implementation-playbook.md` (or correct the path) so the progressive-disclosure pointer resolves to a real file.

DimensionReasoningScore

Conciseness

The body is lean — bullet lists of triggers, instructions, and safety with no explaining of concepts Claude already knows and no padding — so every token earns its place, matching the lean-and-efficient anchor.

3 / 3

Actionability

Instructions name concrete components ("point-in-time data pipelines", "event-driven simulation", "train/validation/test splits") but give no specific examples, commands, or patterns — all detail is deferred to the playbook — so it lands at "some concrete guidance but incomplete" rather than fully executable/copy-paste-ready.

2 / 3

Workflow Clarity

A sequence is present (define → build pipelines → implement simulation → use splits/walk-forward) but there are no validation or verification checkpoints for the multi-step build, which per the rubric caps workflow clarity at 2.

2 / 3

Progressive Disclosure

Structure is clean and the playbook reference is signaled one level deep in both Instructions and Resources, but the referenced `resources/implementation-playbook.md` does not exist in the bundle, making it a dangling reference rather than a well-organized one-level-deep pointer.

2 / 3

Total

9

/

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 concise, third-person description that states concrete capabilities and provides an explicit "Use when" trigger covering natural user phrasing. It clearly distinguishes the skill's niche with low conflict risk.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "Build robust backtesting systems for trading strategies with proper handling of look-ahead bias, survivorship bias, and transaction costs" — naming both the build action and three specific bias/cost concerns, matching the multi-action anchor.

3 / 3

Completeness

It explicitly answers both what (build robust backtesting systems handling named biases/costs) and when (an explicit "Use when..." clause), matching the anchor that clearly answers both with explicit triggers.

3 / 3

Trigger Term Quality

The "Use when developing trading algorithms, validating strategies, or building backtesting infrastructure" clause covers natural terms a user would say ("trading algorithms", "backtesting", "validating strategies"), giving good coverage rather than just jargon.

3 / 3

Distinctiveness Conflict Risk

The backtesting-systems niche with triggers like "trading algorithms" and "backtesting infrastructure" is a clear, distinct niche unlikely to trigger for unrelated skills.

3 / 3

Total

12

/

12

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
rmyndharis/antigravity-skills
Reviewed

Table of Contents

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.