a5c-ai/babysitter / library/specializations/data-science-ml/skills/lime-explainer
lime-explainer
UnverifiedLIME-based local explanation skill for individual predictions across tabular, text, and image data.
lime-explainer
Overview
LIME-based local explanation skill for individual predictions across tabular, text, and image data using Local Interpretable Model-agnostic Explanations.
Capabilities
- Tabular data explanations
- Text classification explanations
- Image classification explanations
- Submodular pick for representative samples
- Custom distance metrics
- Kernel width tuning
- Feature discretization
- Local surrogate model analysis
Target Processes
- Model Interpretability and Explainability Analysis
- Model Evaluation and Validation Framework
Tools and Libraries
- LIME
- scikit-learn
- numpy
- PIL/Pillow (for images)
Input Schema
{
"type": "object",
"required": ["modelPath", "dataType", "instancePath"],
"properties": {
"modelPath": {
"type": "string",
"description": "Path to the trained model or prediction function"
},
"dataType": {
"type": "string",
"enum": ["tabular", "text", "image"],
"description": "Type of data to explain"
},
"instancePath": {
"type": "string",
"description": "Path to instance(s) to explain"
},
"tabularConfig": {
"type": "object",
"properties": {
"trainingDataPath": { "type": "string" },
"featureNames": { "type": "array", "items": { "type": "string" } },
"categoricalFeatures": { "type": "array", "items": { "type": "integer" } },
"classNames": { "type": "array", "items": { "type": "string" } }
}
},
"textConfig": {
"type": "object",
"properties": {
"classNames": { "type": "array", "items": { "type": "string" } },
"splitExpression": { "type": "string" }
}
},
"imageConfig": {
"type": "object",
"properties": {
"segmenter": { "type": "string", "enum": ["quickshift", "slic", "felzenszwalb"] },
"hideColor": { "type": "string" },
"numSamples": { "type": "integer" }
}
},
"explainerConfig": {
"type": "object",
"properties": {
"numFeatures": { "type": "integer" },
"numSamples": { "type": "integer" },
"kernelWidth": { "type": "number" }
}
}
}
}
Output Schema
{
"type": "object",
"required": ["status", "explanations"],
"properties": {
"status": {
"type": "string",
"enum": ["success", "error"]
},
"explanations": {
"type": "array",
"items": {
"type": "object",
"properties": {
"instanceId": { "type": "string" },
"predictedClass": { "type": "string" },
"predictionProbability": { "type": "number" },
"features": {
"type": "array",
"items": {
"type": "object",
"properties": {
"feature": { "type": "string" },
"weight": { "type": "number" },
"contribution": { "type": "string" }
}
}
},
"localAccuracy": { "type": "number" }
}
}
},
"visualizations": {
"type": "array",
"items": {
"type": "object",
"properties": {
"instanceId": { "type": "string" },
"plotPath": { "type": "string" }
}
}
}
}
}
Usage Example
{
kind: 'skill',
title: 'Generate LIME explanations for predictions',
skill: {
name: 'lime-explainer',
context: {
modelPath: 'models/classifier.pkl',
dataType: 'tabular',
instancePath: 'data/instances_to_explain.csv',
tabularConfig: {
trainingDataPath: 'data/train.csv',
featureNames: ['age', 'income', 'credit_score'],
categoricalFeatures: [0, 2],
classNames: ['reject', 'approve']
},
explainerConfig: {
numFeatures: 10,
numSamples: 5000
}
}
}
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 463k | Updated | Claude CodeCodex | Verified | Install |
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 463k | Updated | Claude CodeCodex | Verified | Install |
| discernment-nudgeanthropics/skillsAfter you give a substantive answer or draft that the user may act on — advice or recommendations, drafted artifacts such as goals, plans, pitches, proposals, or emails, estimates or projections, analysis or interpretation of data, factual claims they may rely on, or a multi-step argument — invoke this skill BEFORE finalizing your reply and then, if it applies, append 2-3 short follow-up questions, each tied to something specific in what you just produced, that help the user check key facts, probe the reasoning or assumptions, and notice missing context. Do this at most once per conversation. Skip it when the user asked a trivial how-to or simple lookup, wants a purely educational explanation, asked you only to format, convert, or assemble a file from content they provided, is writing code they will run, is doing creative writing or casual chat, or already asked you to double-check, cite, or review — the skill file explains these boundaries and the exact output format. | Stars: 195k | Updated | Claude CodeCodex | Verified | Install |
| internal-commsanthropics/skillsA set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.). | Stars: 195k | Updated | Claude CodeCodex | Verified | Install |