aiskillstore/marketplace / skills/89jobrien/machine-learning
machine-learning
VerifiedMachine learning development patterns, model training, evaluation, and deployment. Use when building ML pipelines, training models, feature engineering, model evaluation, or deploying ML systems to production.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 6.1 KB |
| references/preprocessing.md | markdown | 3.4 KB |
| skill-report.json | config | 13.3 KB |
skill-report.json
View on GitHub{
"schema_version": "2.0",
"meta": {
"generated_at": "2026-07-05T12:49:54.649Z",
"slug": "89jobrien-machine-learning",
"source_url": "https://github.com/89jobrien/steve/tree/main/steve/skills/machine-learning",
"source_ref": "main",
"model": "codex",
"analysis_version": "3.0.0",
"source_type": "community",
"content_hash": "d5a44351f8832a855108ce8a81ed6d79064e9c672f00926d132bc69eef374307",
"tree_hash": "36ca3887a7ef7adeadf1f38ceda8b641678adb11d94e775c7a36769a6aa5264b",
"provenance": {
"model_effective": "codex",
"fallback_chain": [
{
"agent": "codex",
"outcome": "success"
}
],
"analysis_version": "3.0.0"
}
},
"skill": {
"name": "machine-learning",
"description": "Machine learning guidance for planning pipelines, preparing data, selecting models, evaluating performance, and operating ML systems in production.",
"summary": "Plan, build, evaluate, and operate machine learning systems with practical lifecycle guidance.",
"icon": "📦",
"version": "1.0.2",
"author": "Joseph OBrien",
"license": "MIT",
"tags": [
"machine-learning",
"mlops",
"feature-engineering",
"model-evaluation",
"data-science"
],
"supported_tools": [
"claude",
"codex",
"claude-code"
],
"risk_factors": [
"external_commands"
],
"category": "data"
},
"security_audit": {
"risk_level": "safe",
"is_blocked": false,
"safe_to_publish": true,
"analysis_status": "ok",
"summary": "All six static findings are false positives caused by Markdown formatting or machine learning terminology. No prompt injection, malicious intent, data exfiltration, or unsafe execution behavior was found in the reviewed files.",
"remediation": [],
"risk_factor_evidence": [
{
"factor": "external_commands",
"evidence": [
{
"file": "SKILL.md",
"line_start": 178,
"line_end": 187
},
{
"file": "SKILL.md",
"line_start": 187,
"line_end": 206
},
{
"file": "SKILL.md",
"line_start": 206,
"line_end": 207
},
{
"file": "SKILL.md",
"line_start": 207,
"line_end": 208
}
]
}
],
"static_findings": [
{
"id": "external_commands:SKILL.md:178:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 178,
"line_end": 187,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:187:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 187,
"line_end": 206,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:206:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 206,
"line_end": 207,
"snippet": "- **`references/preprocessing.md`** - Data preprocessing patterns and feature engineering techniques"
},
{
"id": "external_commands:SKILL.md:207:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 207,
"line_end": 208,
"snippet": "- **`references/model_patterns.md`** - Model architecture patterns and implementation examples"
},
{
"id": "blocker:SKILL.md:68:system-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "System reconnaissance",
"file": "SKILL.md",
"line_start": 68,
"line_end": 68,
"snippet": "- Geospatial: distance features, clustering, grid encoding"
},
{
"id": "blocker:SKILL.md:98:system-reconnaissance",
"category": "blocker",
"severity": "low",
"pattern": "System reconnaissance",
"file": "SKILL.md",
"line_start": 98,
"line_end": 98,
"snippet": "- Grid Search: exhaustive, good for small spaces"
}
],
"finding_verdicts": [
{
"id": "external_commands:SKILL.md:178:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.96,
"reason": "Line 178 is a Markdown code fence before an example model directory tree. It is documentation text, not Ruby backtick execution or a shell command."
},
{
"id": "external_commands:SKILL.md:187:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.96,
"reason": "Line 187 is the closing Markdown code fence for the directory tree. There is no executable command or user-controlled input path."
},
{
"id": "external_commands:SKILL.md:206:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.95,
"reason": "The backticks wrap a reference file path in Markdown inline code. The text instructs users to load documentation as needed, not to execute a command."
},
{
"id": "external_commands:SKILL.md:207:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.95,
"reason": "The backticks wrap a referenced Markdown file name. This is formatting for documentation and does not create a command execution vector."
},
{
"id": "blocker:SKILL.md:68:system-reconnaissance",
"verdict": "false_positive",
"confidence": 0.97,
"reason": "The line describes geospatial feature engineering with grid encoding. It does not request host discovery, network scanning, or system reconnaissance."
},
{
"id": "blocker:SKILL.md:98:system-reconnaissance",
"verdict": "false_positive",
"confidence": 0.97,
"reason": "The line describes grid search for hyperparameter tuning. It is an ML optimization method, not system reconnaissance activity."
}
],
"semantic_findings": [],
"critical_findings": [],
"high_findings": [],
"medium_findings": [],
"low_findings": [],
"dangerous_patterns": [],
"files_scanned": 2,
"total_lines": 374,
"audit_model": "codex",
"audited_at": "2026-07-05T12:49:54.649Z",
"agent_auto_install_policy": "allowed",
"manual_install_policy": "allowed"
},
"content": {
"user_title": "Build Machine Learning Pipelines",
"value_statement": "Machine learning projects fail when data, metrics, and deployment choices are unclear. This skill gives structured guidance for model planning, preprocessing, evaluation, and MLOps.",
"seo_keywords": [
"Claude machine learning",
"Codex machine learning",
"Claude Code machine learning",
"ML pipeline guidance",
"feature engineering",
"model evaluation",
"MLOps workflow",
"hyperparameter tuning",
"data preprocessing",
"model deployment"
],
"actual_capabilities": [
"Guides ML work from problem definition through production monitoring.",
"Maps problem types to suitable metrics and model families.",
"Explains preprocessing patterns for missing values, scaling, encoding, outliers, and leakage prevention.",
"Covers model training, hyperparameter tuning, cross-validation, and imbalanced data handling.",
"Describes serving patterns, versioning, CI/CD checks, monitoring, and retraining triggers."
],
"limitations": [
"It does not train models or inspect datasets without additional user-provided code and data.",
"Some referenced files are not included in the package, including model patterns and evaluation guides.",
"Examples focus on Python and scikit-learn style workflows.",
"It does not provide cloud-specific deployment manifests or infrastructure automation."
],
"use_cases": [
{
"title": "Plan a New ML Project",
"description": "Define the problem type, success metrics, data split strategy, and first model candidates before implementation begins.",
"target_user": "Data scientist"
},
{
"title": "Prepare Training Data",
"description": "Choose imputation, encoding, scaling, outlier handling, and leakage prevention steps for a reliable dataset.",
"target_user": "Machine learning engineer"
},
{
"title": "Review Production Readiness",
"description": "Check serving approach, model versioning, CI/CD tests, monitoring signals, and retraining triggers before launch.",
"target_user": "MLOps engineer"
}
],
"prompt_templates": [
{
"title": "Choose the ML Approach",
"scenario": "Beginner project planning",
"prompt": "Use the machine-learning skill to classify my problem type, recommend metrics, and suggest baseline models. My goal is: [describe goal]. My data is: [describe data]."
},
{
"title": "Design Data Preparation",
"scenario": "Feature engineering and preprocessing",
"prompt": "Use the machine-learning skill to design preprocessing for this dataset: [columns, types, missing values, target]. Include leakage risks and train-test split guidance."
},
{
"title": "Build an Evaluation Plan",
"scenario": "Model comparison and validation",
"prompt": "Use the machine-learning skill to create an evaluation plan for [classification, regression, ranking, clustering]. Include primary metrics, validation strategy, and error analysis steps."
},
{
"title": "Prepare for Production ML",
"scenario": "Advanced deployment and operations review",
"prompt": "Use the machine-learning skill to review production readiness for this model: [model, latency needs, traffic, monitoring plan]. Identify deployment risks and retraining triggers."
}
],
"output_examples": [
{
"input": "A product team wants churn prediction from account, usage, billing, and support data.",
"output": "The skill would frame this as binary classification, recommend stratified splits, suggest AUC-ROC and PR-AUC, and flag leakage from post-churn fields."
},
{
"input": "A dataset has missing numerical values, high-cardinality categories, and strong outliers.",
"output": "The skill would recommend train-only imputation, target or frequency encoding review, robust scaling, clipping options, and pipeline-based preprocessing."
},
{
"input": "An ML team wants to release a model behind an API.",
"output": "The skill would outline staging checks, shadow testing, gradual rollout, latency monitoring, drift tracking, model versioning, and rollback planning."
}
],
"best_practices": [
"Define the prediction target, metric, and data split before selecting models.",
"Fit preprocessing only on training data, then transform validation and test data.",
"Track code version, data version, hyperparameters, metrics, and model artifacts for every experiment."
],
"anti_patterns": [
"Do not tune on the test set or report validation results as final performance.",
"Do not use future information or target-derived fields as model inputs.",
"Do not deploy without monitoring latency, input drift, prediction drift, and error rates."
],
"faq": [
{
"question": "Can this skill train a model directly?",
"answer": "No. It provides workflow guidance and patterns. You still need data, code, compute, and framework-specific implementation."
},
{
"question": "Which AI tools can use this skill?",
"answer": "The report declares support for Claude, Codex, and Claude Code."
},
{
"question": "Does it cover feature engineering?",
"answer": "Yes. It covers numerical, categorical, temporal, text, geospatial, interaction, and preprocessing patterns."
},
{
"question": "Does it help with model evaluation?",
"answer": "Yes. It recommends metrics by problem type and emphasizes held-out tests, cross-validation, overfitting checks, and error analysis."
},
{
"question": "Is it specific to one machine learning framework?",
"answer": "No, but the included preprocessing examples are closest to Python and scikit-learn workflows."
},
{
"question": "Does it include production guidance?",
"answer": "Yes. It covers serving patterns, versioning, CI/CD checks, monitoring signals, fallback strategies, and retraining triggers."
}
]
},
"file_structure": [
{
"name": "references",
"type": "dir",
"path": "references",
"children": [
{
"name": "preprocessing.md",
"type": "file",
"path": "references/preprocessing.md",
"lines": 158
}
]
},
{
"name": "SKILL.md",
"type": "file",
"path": "SKILL.md",
"lines": 216
}
]
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deployment | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy. | Stars: 119k | Updated | Claude CodeCodex | Verified | Install |
| childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |