ml-strategy

Machine-learning predictive strategy based on sklearn walk-forward training, feature engineering, and signal generation. Suitable for any OHLCV data.

Quality

72%

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 ./agent/src/skills/ml-strategy/SKILL.md

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 content is highly actionable with complete, executable code and a clear validated workflow, but it is monolithic with some redundancy between the inline code and the feature reference table.

Suggestions

Move the complete SignalEngine code into a bundled script (e.g. scripts/signal_engine.py) and keep only a concise usage snippet in SKILL.md, linking to the script.

Reduce redundancy between the Feature Engineering table and build_features() by keeping one as the source of truth and linking the other.

Split the Model Selection Guide and Parameters tables into a reference file (e.g. references/parameters.md) signaled from SKILL.md to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean executable code and reference tables that assume Claude's competence, but the Feature Engineering table duplicates formulas already in the code and could be tightened.	2 / 3
Actionability	Provides a fully executable, copy-paste-ready pipeline — validate_data, build_features, walk_forward_predict, and a SignalEngine class — plus specific parameter, feature, and model-selection tables.	3 / 3
Workflow Clarity	The Signal Logic section is a clearly sequenced 5-step workflow with explicit validation in step 1 (skip symbols that fail), and the code enforces checkpoints (NaN handling, retrain gating, skip-on-fail).	3 / 3
Progressive Disclosure	Sections are well-organized, but the skill is a monolithic ~260-line SKILL.md with all code and reference tables inline and no bundle files; the full pipeline and reference tables could be split into separate files for navigation.	2 / 3
	Total	10 / 12 Passed

Description

67%

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 specific and distinct, clearly conveying an ML-based predictive strategy with concrete techniques. Its main weakness is the lack of an explicit 'Use when...' trigger clause and jargon-heavy trigger terms.

Suggestions

Add an explicit trigger clause, e.g. 'Use when building machine-learning trading strategies on OHLCV data or when the user asks for ML-based signal generation.'

Soften jargon with natural user terms such as 'ML trading strategy', 'predictive signals', or 'stock price direction prediction' alongside 'sklearn' and 'OHLCV'.

Clarify the 'when' with a concrete data shape, e.g. 'Use on any OHLCV price series to generate [-1,1] directional signals.'

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'sklearn walk-forward training', 'feature engineering', and 'signal generation' — rather than vague language.	3 / 3
Completeness	The 'what' is clear, but 'when' is only implied by 'Suitable for any OHLCV data' with no explicit 'Use when...' trigger clause, which caps completeness at 2 per the rubric.	2 / 3
Trigger Term Quality	Relevant keywords exist ('Machine-learning', 'sklearn', 'OHLCV') but lean toward technical jargon; natural user phrasings like 'ML trading strategy' are only weakly covered.	2 / 3
Distinctiveness Conflict Risk	The ML predictive-strategy niche with sklearn/OHLCV triggers is clearly distinguishable and unlikely to fire for unrelated skills.	3 / 3
	Total	10 / 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: HKUDS/Vibe-Trading
Path: agent/src/skills/ml-strategy/SKILL.md
Commit: 8643fcd

Reviewed: 2 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.