ml-strategy

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

Quality

52%

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

67%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 content is highly actionable with an executable end-to-end pipeline and clear step sequencing, but it underperforms on progressive disclosure by inlining everything into one file and is somewhat verbose for an overview.

Suggestions

Move the Feature Engineering Reference, Model Selection Guide, and Parameters tables into separate reference files (e.g. references/features.md, references/models.md) and link to them from the body.

Extract the full SignalEngine example into a scripts/ file, keeping only a minimal quick-start snippet inline in SKILL.md.

Add an explicit validation/retry checkpoint in the batch loop (e.g. what to do when a symbol fails beyond the current WARN+skip) to strengthen workflow clarity for batch operations.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and code-forward, but the full ~180-line SignalEngine example plus duplicated feature tables and a model-selection guide pad the SKILL.md beyond a lean overview that assumes Claude's competence.	3 / 5
Actionability	It provides a complete, copy-paste-ready pipeline with executable functions (validate_data, build_features, walk_forward_predict, SignalEngine) plus a parameter table and install command, fully covering the common case.	5 / 5
Workflow Clarity	The Signal Logic section sequences validation -> features -> labels -> walk-forward training -> signal generation with built-in data-quality checks, though explicit validate/retry checkpoints for batch symbol processing are implicit rather than stated.	4 / 5
Progressive Disclosure	It is a monolithic SKILL.md with no bundle files (references/scripts/assets absent) and all reference material (feature table, model guide, parameters, pitfalls) inlined rather than split into one-level-deep referenced files.	2 / 5
	Total	14 / 20 Passed

Description

37%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 is reasonably specific and distinct, but it omits any explicit 'when to use' trigger guidance and relies on technical jargon rather than natural user phrasing, capping completeness and trigger quality.

Suggestions

Add a 'Use when...' clause naming natural trigger phrases (e.g. 'Use when you need to predict asset price direction from OHLCV data or generate ML-based trading signals').

Rephrase to include user-friendly synonyms like 'price prediction', 'trading signals', and 'backtesting signals' rather than only sklearn/walk-forward jargon.

Third-person voice is correct; keep it but make the concrete actions more granular (e.g. 'builds features, trains classifiers, and outputs [-1,1] signals').

Dimension	Reasoning	Score
Specificity	Names the ML domain and a few concrete actions (walk-forward training, feature engineering, signal generation) but stays at a summary level rather than listing multiple specific operations.	3 / 5
Completeness	It states a clear 'what' (ML predictive strategy with training and signal generation) but has no 'Use when...' clause or equivalent trigger guidance for when to invoke the skill.	2 / 5
Trigger Term Quality	The terms used (sklearn, walk-forward training, OHLCV) are technical jargon; it lacks the natural phrases a user would actually say such as 'predict price direction' or 'trading signals'.	2 / 5
Distinctiveness Conflict Risk	The sklearn + walk-forward + OHLCV framing carves a fairly specific niche with low overlap risk against other skills, even though it shares the broad strategy category.	4 / 5
	Total	11 / 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: HKUDS/Vibe-Trading
Path: agent/src/skills/ml-strategy/SKILL.md
Commit: e90b6c6

Reviewed: ~12 hours 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.