Works with the AI Agents you already use
model explainability and diagnostics
Use when asked to explain model behaviour, rank drivers, show dependence, find where errors concentrate or review an explanation for caveats.
$1.99
About this skill
Explains a linear or logistic model on an approved sample: exact contributions, importance with bootstrap rank stability, partial dependence, error slices, leakage and causal-claim checks. Small cells suppressed; actions are drafts. Decision support only.
What it does
Explains a supplied linear or logistic scoring model on an approved sample for technical reviewers and decision makers. A script computes exact feature contributions (SHAP for additive models), global importance with bootstrap rank stability, partial dependence, error slices with small-cell suppression, leakage screens and causal-claim checks. Use when asked to explain model behaviour, rank drivers, show dependence, find where errors concentrate or review an explanation for caveats. Not for optimisation models.
Use cases
- Compute exact feature contributions and global importance with bootstrap rank stability for a scoring model.
- Show partial dependence and locate the slices where prediction errors concentrate.
- Review an explanation for caveats such as leakage and overstated causal claims.
What is included
SKILL.md: the workflow, trigger rules and output format.references/: method notes and the markers used in outputs, loaded only when needed.scripts/run.py: one self-contained Python script (standard library only) that does every calculation deterministically.assets/: input and output schemas with a sample request and result.
Limits
Decision support only. Outputs label analytical estimates, information gaps and actions that need human approval. The skill does not send, publish, pay or change anything by itself, and it does not claim legal, regulatory or standards compliance.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse All Claude Skills.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 2 days ago