---
title: "SHAP - Air Market"
description: "Your model gave an answer and someone wants to know why. This helps you compute feature attributions with SHAP, choose the setup that fits your model, sanity-check the numbers rather than take them a…"
canonical: "https://airmarket.ai/app/shap"
---

[Air Market](/) / [Data & Analytics](/category/data) / SHAP

Skill by [K-Dense](/@k-dense-ai)

# SHAP

See which features moved a prediction, and check the answer

## What this does

Your model gave an answer and someone wants to know why. This helps you compute feature attributions with SHAP, choose the setup that fits your model, sanity-check the numbers rather than take them at face value, and produce plots for a single case or the whole dataset.

### Top 3 things it does for you

- Explain why a model made one particular prediction
- Pick the right explainer and masker for your model
- Validate the feature attributions you got

## Information

**SHAP at a glance**

|  |  |
| --- | --- |
| Kind | Skill |
| Publisher | [K-Dense](/@k-dense-ai) |
| Category | [Data & Analytics](/category/data) |
| Works with | Agent Skills - an open standard supported by 40+ agents |
| Version | 2.0 |
| Size | 117 KB |
| Licence | MIT |
| Repository | [k-dense-ai/scientific-agent-skills](https://github.com/k-dense-ai/scientific-agent-skills/tree/70a0d595e54b8d92ca54f216d4315e0ab8c7d967/skills/shap) |
| GitHub stars | 34,239 (as of Nov 2026) |

## Security report

**Verified.** AIR scanned this exact version of SHAP and flagged nothing. AIR's verdict: **safe**.

**What SHAP's check was run against**

|  |  |
| --- | --- |
| Commit | 70a0d595e54b8d92ca54f216d4315e0ab8c7d967 |
| Content hash | 85a91360b85754adab93bbf8a945ace2e5a0c2bdf348a99a7a0de9eb8cdda1b9 |
| Files read | [Browse the files at this exact commit](https://github.com/k-dense-ai/scientific-agent-skills/blob/70a0d595e54b8d92ca54f216d4315e0ab8c7d967/skills/shap/SKILL.md) |

A scan is named by the exact content it read, not by a version number. A different version is a different artifact, and nothing here applies to a version AIR has not scanned.

[Read the full security report for SHAP](/security/shap)

## About SHAP

This is for explaining and auditing machine-learning predictions with SHAP. It covers selecting SHAP explainers and maskers, computing and validating feature attributions, and handling multi-output explanations.

It also covers producing SHAP visualizations, whether for a single prediction or across the model as a whole.

## What's inside

- SKILL.md - instructions
- references/data-maskers.md - reference
- references/explainers.md - reference
- references/migration.md - reference
- references/modalities.md - reference
- references/plots.md - reference
- references/theory.md - reference
- references/troubleshooting.md - reference
- references/workflows.md - reference
- scripts/tabular_report.py - script

## Questions

### Is SHAP safe to install?

AIR scanned this exact version of SHAP and flagged nothing. AIR's verdict: safe. The verdict is named by the content that was read, at commit 70a0d595e54b, so it cannot drift onto a version nobody scanned. The full report is at https://airmarket.ai/security/shap.

### How do I install SHAP?

Open https://airmarket.ai/app/shap on Air Market and use the install action: Air Market hands Claude a prompt naming this exact skill, and Claude sets it up. Source, pinned to the exact commit this listing describes: https://github.com/k-dense-ai/scientific-agent-skills/tree/70a0d595e54b8d92ca54f216d4315e0ab8c7d967/skills/shap. Install from that link, not the branch.

## Related on Air Market

- [More Data & Analytics listings](/category/data)
- [Everything by K-Dense](/@k-dense-ai)

---

Canonical URL: <https://airmarket.ai/app/shap>