xgboost-analysis

Use when building XGBoost models on tabular data and returning feature importance ranking outputs. Supports binary classification and regression with automatic task detection, train-test split, performance tables, feature importance ranking tables, and PNG importance plots.

Quality

87%

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

Quality

Content

82%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.

A well-structured, highly actionable skill body with executable commands, a clear argument reference, and good progressive disclosure via a need→file table. Weaker on conciseness (repeated example commands) and workflow feedback loops, plus a few referenced test-data paths that do not exist in the bundle.

Suggestions

Collapse the three repetitive Quick Examples into one representative invocation plus a compact table of the variations (--task_type, --positive_class, --top_n) to save tokens.

Add an inline validate→fix→retry step to the Minimal Workflow (e.g. 'If expected outputs are missing, check the error code in Common Errors or references/troubleshooting.md and re-run') rather than only delegating recovery to a separate section.

Either include the referenced tests/data/ sample files in the bundle or point the examples at a sample path that exists, so the documented commands run as written.

Dimension	Reasoning	Score
Conciseness	Mostly lean tables and executable commands assuming Claude's competence, but the three near-identical Quick Examples and the separate Validation section repeat the same Rscript invocation, adding tokens that could be trimmed.	4 / 5
Actionability	Fully executable, copy-paste-ready Rscript commands throughout — a primary command, an argument table with defaults, input examples, and three concrete end-to-end examples covering the common classification cases.	5 / 5
Workflow Clarity	The Minimal Workflow is a clear 3-step sequence with an explicit validation step ('Check the output directory') and a dedicated Validation section verifying output files, but the validate→fix→retry feedback loop is delegated to Common Errors / troubleshooting rather than woven inline.	4 / 5
Progressive Disclosure	A clear overview with a well-signaled 'Read These Files When Needed' need→file table and one-level-deep references (algorithm.md, cli-guide.md, troubleshooting.md, main.R all exist), but the body references tests/data/ and dt_sample1.csv etc. that are not present in the bundle — a minor navigation gap.	4 / 5
	Total	17 / 20 Passed

Description

92%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.

A strong, third-person description that clearly states both capabilities and a specific use-trigger, with concrete output types. The only gap is keyword coverage missing common synonyms and file extensions.

Suggestions

Add natural synonyms and file extensions to broaden trigger matching, e.g. '...on tabular data (.csv, .tsv, .txt) and returning feature importance rankings or plots.'

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions and outputs — 'binary classification and regression with automatic task detection, train-test split, performance tables, feature importance ranking tables, and PNG importance plots' — giving comprehensive coverage of capabilities.	5 / 5
Completeness	Explicitly answers both what ('Supports binary classification and regression with automatic task detection...') and when ('Use when building XGBoost models on tabular data and returning feature importance ranking outputs') with concrete trigger phrasing.	5 / 5
Trigger Term Quality	Natural terms like 'building XGBoost models', 'tabular data', and 'feature importance ranking' are present, but it lacks synonyms and file-extension variants (e.g. .csv, 'importance plot') that users might say.	4 / 5
Distinctiveness Conflict Risk	The XGBoost-on-tabular-data plus feature-importance-ranking niche is distinct with specific triggers, leaving minimal overlap risk with other skills.	5 / 5
	Total	19 / 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: aipoch/medical-research-skills
Path: awesome-med-research-skills/Data Analysis/XGBoost-analysis/SKILL.md
Commit: f5ef65b

Reviewed: ~9 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.