shap
Explains and audits machine-learning predictions with SHAP: choosing explainers and maskers, validating feature attributions and producing local or global plots.
- Kind
- Skill
- Works with
- Claude Code, Codex, Cursor, Gemini / Antigravity
- Source
- Scientific Agent Skills (K-Dense) @ 5f2bc0341354
- Path
- skills/shap/SKILL.md
- Jobs
- Review
- Topics
- Machine learning
Credit
- Made by
- K-Dense-AI
- Original
- github.com/K-Dense-AI/scientific-agent-skills/blob/5f2bc03413…
- License
- MIT
Listed by Skill Manifest; not made by us.
InstallInstall it by hand, following the source.
gh skill install K-Dense-AI/scientific-agent-skills shap
Install factsScanned 2 Nov 2026
- Adds
- .claude/skills/shap/ (the skill folder)
- 8 file(s) the skill refers to
- Runs scripts
- Yes
- allowed-tools includes Bash
- shell block in the text
- Uses the network
- Yes
- downloads Python packages
- Needs secrets
- None found
- Source revision
- 5f2bc0341354
- Licence
- MIT
- Last activity
- 26 Oct 2026
- Review
- Reviewed
Found by a static scan of the stored text; nothing is run. “None found” is not a guarantee, so read what you install before you run it.
- Only the main file is read; other files in the folder are not scanned
# SHAP Use SHAP to describe how a fitted predictive model maps inputs to outputs. Work from the modern `shap.Explanation` API, make the explained output and background distribution explicit, and validate every explanation before interpreting it. This skill is aligned with **SHAP 0.52.0** (released 2026-05-28). That release requires Python 3.12 or newer. The maintained examples were checked on Python 3.12.10 with SHAP 0.52.0, NumPy 2.5.3, pandas 3.0.6, scikit-learn 1.9.1, and matplotlib 3.11.2. Native tests cover small tree, exact, permutation, partition, linear, additive, kernel, text, and constant-image games; additional numeric XGBoost 3.4.1 smoke checks cover raw, probability, loss, and interaction outputs. Reference snippets that require a project model, framework, or data are adaptation templates; optional pretrained/deep, GPU, and distributed integrations remain illustrative and require their own runtime validation. ## Operating Rules 1. Explain a fixed, evaluated model; do not use SHAP as a substitute for predictive validation. …