name: kdense-shap description: "Model interpretability and explainability using SHAP (SHapley Additive exPlanations). Use this skill when explaining machine learning model predictions, computing feature importance, generating SHAP plots (waterfall, beeswarm, bar, scatter, force, heatmap), debugging models, analyzing model bias or fairness, comparing models, or implementing explainable AI. Works with tree-based models (XGBoost, LightGBM, Random Forest), deep learning (TensorFlow, PyTorch), linear models, and any black-box model." metadata: version: "1.0.1"

<!-- Generated by scripts/generate_wrappers.py; do not edit. -->

Kdense Shap

Use this Codex adapter for the pinned upstream scientific skill.

Catalog status

• Status: active
• Source: kdense
• Audit reasons: none
• Upstream license: MIT license
• Inventory: ../../inventory.json
• Upstream instructions: ../../../vendor/scientific-agent-skills/skills/shap/SKILL.md

Procedure

1. Resolve the plugin root as three directories above this skill directory.
2. Run "<plugin-root>/scripts/python_runtime.sh" "<plugin-root>/scripts/search_skills.py" --name kdense-shap and verify the record's status, reasons, and source path and the source's pinned commit (empty for first-party cx skills) from its output instead of reading inventory.json.
3. Read the upstream instructions only after confirming this record is still active in the current inventory.
4. Treat upstream frontmatter as source metadata, not as Codex configuration. Follow the instruction body only where it is compatible with available Codex tools and the current user-approved plan.
5. Treat tools named for another agent runtime as capability requests. Map them to an available Codex tool only when the behavior is equivalent; otherwise report the unavailable capability.
6. Ask before credentials, package installation, new network hosts, remote compute, writes, paid services, destructive actions, or imported executable code.
7. Use $science-provenance for produced scientific outputs and $science-review before presenting scientific claims.

Progressive loading

The upstream SKILL.md is 563 lines. Inspect its headings first, then read only the sections relevant to the current request. Load linked references only when the selected workflow requires them; do not load the entire upstream tree by default.

Boundaries

• This wrapper does not grant credentials, network access, package installation, or script execution.
• Do not change an inactive record to active from inside a research task.
• Preserve failures, uncertainty, source identifiers, and licensing constraints.