ML model explanation — feature importance, SHAP-style attribution, LIME and partial dependence
Explain ML predictions with feature importance, a from-scratch SHAP-style calculator, a local LIME surrogate, partial dependence and sensitivity plots
- What
- Explain ML predictions with feature importance, a from-scratch SHAP-style calculator, a local LIME surrogate, partial dependence and sensitivity plots
- Cost
- Free
- Needs
- Python with scikit-learn, numpy, pandas, matplotlib, seaborn — a trained model or sample dataset to explain
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor — @aj-geddes's ML model explanation skill: a hands-on walkthrough of the explainability toolkit. Covers feature importance (impurity vs permutation), a from-scratch SHAP-style feature attribution calculator, a local LIME surrogate model, partial dependence plots, global behavior analysis, and feature sensitivity testing — with ready-to-run Python code and visualization recipes for each technique, plus a comparison table (speed, scope, cost) and regulatory context (GDPR right to explanation, fair lending, healthcare transparency). Honest caveats: the skill implements simplified from-scratch approximations of SHAP and LIME rather than the real libraries — excellent for learning the mechanics, not a drop-in for production explainability (use the `shap` package for real work). MIT licensed. Skill Harbor never reviews the code, review it yourself before use. Discovered via skills.sh.
Version:
Quick answer
ML model explanation — feature importance, SHAP-style attribution, LIME and partial dependence is a free Muse skill that explains ML predictions with feature importance, a from-scratch SHAP-style calculator, a local LIME surrogate, partial dependence and sensitivity plots, so a prediction comes with reasons you can inspect, not just a score.
Install
Copy the install package below, then paste it into Muse🧪 Install ran in our test sandbox · Nov 11, 2026📌 Pinned version: commit 3f5182cStep 0 — before installing anything: read this install prompt, summarize in a few lines what this build does and what installing it involves, then ask me to confirm before you proceed. Prerequisites: Python with scikit-learn, numpy, pandas, matplotlib, seaborn — a trained model or sample dataset to explain Install "ML model explanation — feature importance, SHAP-style attribution, LIME and partial dependence" for me. It gives my agent @aj-geddes's explainability walkthrough: feature importance (impurity vs permutation), a from-scratch SHAP-style attribution calculator, a local LIME surrogate, partial dependence plots, prediction-distribution and feature-sensitivity analysis, and visualization recipes, with a techniques comparison table and regulatory context. IMPORTANT: the skill uses simplified from-scratch SHAP/LIME approximations for learning — for production use, install the real shap library instead. MIT-licensed. Repository: https://raw.githubusercontent.com/aj-geddes/useful-ai-prompts/3f5182cfd739fc113f4af5244a1cf342ad7f7911/skills/ml-model-explanation/SKILL.md Pinned version: install the code at commit 3f5182cfd739fc113f4af5244a1cf342ad7f7911 exactly (Skill Harbor tested this version). Do not substitute a newer version. If this commit is unreachable, stop and tell me. 1. Fetch the SKILL.md file (and any helper files) from the repository path into a temporary folder 2. Safety check: review the SKILL.md and scripts for anything suspicious (unexpected network calls, shell commands, credential harvesting). This repo should contain zero secrets in code. Verify that holds here; STOP on any red flag and tell me. 3. Install it as a skill: copy SKILL.md and its helper files into the agent's skills directory, in a folder named "ml-model-explanation". 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself (e.g. pip install scikit-learn pandas matplotlib seaborn and point the agent at my trained model or dataset; nothing else — it's a walkthrough with runnable code). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.
Saved to your recent installs. Find it anytime on /connect.
🔒 Security, provenance and what this touches
The install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?
Verification certificate
Dated facts about what was checked for this listing, and how. This is not a safety certification.
- Pinned version
- 3f5182c · 2026-10-13
- Sandbox install test
- Install ran in our test sandbox · Nov 11, 2026 · Observed during the install test: registry.npmjs.org
- Creator identity
- Not verified
- Fingerprint watch
- Last checked · Nov 19, 2026 : no change detected in the files linked by this install prompt
- Install prompt analysis
- 2026-10-13 : No commands, network calls, packages, file writes or API keys detected.
Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify
Useful AI prompts
By the same creator, in the same series:
Questions
How do I install a skill?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the skill up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a skill before installing it.