model-cards skillA
model-cards is agent-read markdown (skill) from habitat-thinking/ai-literacy-superpowers: Use when authoring or interpreting Mitchell-extended model cards in this plugin. Covers when each of the 10 sections applies, the citation discipline, the honesty rules (claim-level and card-level), and the tiered source strategy. Reference for the model-card-researcher agent and the /model-card command..
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# Mitchell-Extended Model Cards This plugin produces 10-section model cards: Mitchell et al.'s 9 canonical sections plus an "Operational Details" 10th section for the consumer-evaluator audience. This skill is the reference for what each section is for and how to fill it honestly. ## The ten sections ### 1. Model Details What the model IS — name, provider, family, release date, parameter count where disclosed. Tier 1 (provider docs) is primary; tier 2 (HuggingFace) is secondary for open-source / fine-tuned models. ### 2. Intended Use What the model is for — primary uses, intended users, explicitly out-of-scope uses. The provider's documentation usually makes this explicit; quote it faithfully and cite. ### 3. Factors Subgroups, environmental factors, instrumentation. Often sparse for proprietary API-served models — write "Not publicly available" rather than fabricate. ### 4. Metrics Performance measures the provider reports. Distinguish provider-reported benchmarks from independent evaluations (tier 1 vs tier 4). ### 5. Evaluation Data Datasets used to evaluate. Frequently "Not publicly available" for …
Read the whole file at its exact version.
How to install
mdr add habitat-thinking/ai-literacy-superpowers/model-cards@git:20260429.0053b36mdr add habitat-thinking/ai-literacy-superpowers/model-cards@sha256:2dd9bb68df750056Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
[](https://markdownregistry.com/a/art_rb5e7ga4f3hhpqzg)
1 badge views in 30 days
Versions
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 (5063 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
habitat-thinking/ai-literacy-superpowers · 106 stars · license NOASSERTION · pushed 2026-09-20 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_rb5e7ga4f3hhpqzg GET https://markdownregistry.com/api/v1/resolve?ref=habitat-thinking/ai-literacy-superpowers/model-cards GET https://markdownregistry.com/api/v1/blob/2dd9bb68df750056e2355231331a7c8a8f4cbf3bd9a8ab7fe23f2240e56c0e72
Your agent 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.