model-card SKILL.md skillA
model-card from qa-aman/claude-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add qa-aman/claude-skills/model-card@git:20260303.8412b01Pins git:20260303.8412b01 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- qa-aman/claude-skills
- Path
skills/by-role/data-scientist/model-card/SKILL.md- Versions recorded
- 1
- Latest version
- git:20260303.8412b01, committed Mar 3, 2026
- Size
- 7,630 bytes
- Repository stars
- 21
- License
- MIT
Document a machine learning model in a structured, transparent format for stakeholders, reviewers, and future maintainers. Use when the user says "document this model", "write a model card", "model documentation", "how should I document my ML model", "bias and fairness report", "model transparency", "what does this model do", "model handoff", "production model documentation", or needs to communicate what a model does, how it was built, where it works, and where it fails.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
## Overview Based on **"Interpretable Machine Learning"** by Christoph Molnar, with structure informed by the Google Model Cards framework (Mitchell et al., 2019). The core principle: a model without documentation is a liability. Interpretability is not a post-hoc courtesy - it is a prerequisite for responsible deployment. A model card makes the model's intended use, performance limits, and failure modes explicit before the model reaches production. ## Workflow ### Step 1: Write the model overview section ```markdown ## Model Overview **Model name:** [descriptive name, not a variable name] **Version:** [semantic version, e.g., v1.2.0] **Model type:** [e.g., XGBoost binary classifier, LSTM time-series forecaster] **Owner:** [team or individual responsible for this model] **Last updated:** [date] **What does this model do?** [One paragraph. Plain language. No jargon. What input does it take? What output does it produce? What decision does it support?] **Primary use case:** [Specific intended application. Be concrete: "Predicts 30-day churn probability for active subscribers with > 60 days of account history."] **Out-of-scope uses:** …
Read the whole file at its exact version.
How to install
mdr add qa-aman/claude-skills/model-card@sha256:5880639d699c442eThe line at the top of this page pins the label git:20260303.8412b01, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_yla7u7gbz6efyckd)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Mar 3, 2026.
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (7630 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
qa-aman/claude-skills · 21 stars · license MIT · pushed 2026-10-19 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_yla7u7gbz6efyckd GET https://markdownregistry.com/api/v1/resolve?ref=qa-aman/claude-skills/model-card GET https://markdownregistry.com/api/v1/blob/5880639d699c442eb44fc0256326ff63e4dc811acf20bcd6181a1e435d3775b9
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.
More from qa-aman/claude-skills
Every file in qa-aman/claude-skills