AI Skill MartBrowse skillsPromptsProgramsLearnWhat is a Skill?
 
← Back to list

SHAP Model Explanation Assistant

A skill that guides Claude through choosing SHAP explainers and maskers, computing, validating, and visualizing feature attributions on SHAP 0.52.

Data & AnalyticsAdvanced★ 33,030⑂ 3,248AI score 9/10Last updated: Aug 9, 2026

What it does

  • Provides a decision table for picking the right explainer and masker: tree ensembles, linear models, deep nets, text, and images.
  • Enforces the modern shap.Explanation API and a mandatory additivity check that base_values + values.sum() matches the exact model output being explained.
  • Covers multi-output (multiclass) slicing, probability/log-loss output modes for trees, and question-driven plot selection (bar, beeswarm, waterfall, scatter, heatmap, text, image).
  • Supplies a reporting checklist: output units, reference population, masker, approximation diagnostics, and an explicit non-causal disclaimer.
  • Ships a deterministic example script (scripts/tabular_report.py) plus eight reference docs (explainers, maskers, plots, workflows, modalities, migration, theory, troubleshooting).

Who it's for

  • Data scientists and ML engineers producing explanation reports for audits or compliance.
  • Anyone whose SHAP code broke after upgrading (e.g., legacy values[class_index] patterns).
  • Practitioners debugging additivity failures, shape mismatches, pipelines, or categorical handling.

Example uses

  1. "Compute SHAP for the positive-class probability of my RandomForest with a 100-row background and verify additivity" → generates TreeExplainer setup with np.testing.assert_allclose.
  2. "Compare per-class attributions for my multiclass model" → shows explanation[..., "class_name"] slicing and the rule against averaging signed values across classes.
  3. "Why can't I get probability-space tree explanations?" → points to feature_perturbation="interventional" plus background data, and walks the troubleshooting order.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/K-Dense-AI/scientific-agent-skills/HEAD/skills/shap/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on AI Skill Mart.
Copy the skills/shap folder from the GitHub repo K-Dense-AI/scientific-agent-skills into my ~/.claude/skills/shap/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/K-Dense-AI/scientific-agent-skills.git && mkdir -p ~/.claude/skills && cp -r scientific-agent-skills/skills/shap ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal.
  2. Clone the repo: git clone https://github.com/K-Dense-AI/scientific-agent-skills.git
  3. Create the skills folder: mkdir -p ~/.claude/skills
  4. Copy the skill: cp -r scientific-agent-skills/skills/shap ~/.claude/skills/
  5. Set up Python (uv required): uv venv --python 3.12 && source .venv/bin/activate && uv pip install "shap[plots]==0.52.0"
  6. Restart Claude Code and ask something like "Explain this model's predictions with SHAP" to trigger the skill.
  7. Smoke test: uv run --no-project --python 3.12 --with "shap[plots]==0.52.0" ~/.claude/skills/shap/scripts/tabular_report.py --output-dir /tmp/shap-report
View source on GitHub ↗License: MIT