OpenMed Model Card Writer

What it does

When your agent uses it

• Publishing or updating an OpenMed model that needs a card
• Turning eval artifacts into intended-use, metrics and limitations sections
• Preparing a transparency document for a clinical AI governance review

Example prompts

• “Write the model card for our de-identification model from the latest gate, fairness and error reports.”
• “Update the limitations section of the card using the new error_report output.”
• “Add the subgroup recall table from fairness_report to the model card and flag groups with no data.”

Requirements

• OpenMed evaluation outputs: a gate report, a fairness report and an error report
• The `openmed.eval` Python package

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

1. 1Gather artifacts. Gate report, fairness report, error report — all from a
2. 2Fill model details from the GateReport identity fields so the card,
3. 3Write intended use narrowly. Name the clinical task, language(s), and the
4. 4State out-of-scope and the disclaimer plainly (see template below).
5. 5Report metrics with their floors. For de-id, lead with leakage and the
6. 6Report subgroups honestly, including the documentation gap: if race/
7. 7List limitations from real errors, not boilerplate — cite the confusion

What it can do on your machine

Read from SKILL.md and the folder at commit 34d7b8c. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md (its code samples are python).

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Links to these hosts (documentation or services it may open):

  • arxiv.org
  • huggingface.co
  • doi.org
  • fda.gov

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

OpenMed Model Card Writer loads about 1.8k tokens when it runs, and up to ~2.5k if it reads all its reference files. Until then it costs about 162 tokens; SKILL.md has 634 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~162

When it runs · the whole SKILL.md, loaded when a task matches

~1.8k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~2.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from maziyarpanahi/openmed at commit 34d7b8c, republished under its Apache-2.0 licence (© maziyarpanahi). 634 words, ~1,821 tokens.

name

authoring-model-cards

description

Generate a model card for an OpenMed clinical NER or de-identification model documenting intended use, quantitative metrics, subgroup performance, limitations, and a medical-device disclaimer for clinical AI governance. Use when the user wants to write or update a model card, a README model section, or governance documentation, or to turn OpenMed eval outputs (release gate report, fairness_report, error_report) into the card's metrics and limitations sections. Trigger on "model card", "intended use", "model documentation", "governance", "limitations section", "datasheet", or "FDA/ONC transparency" for an OpenMed model.

license

Apache-2.0

metadata.project

OpenMed

metadata.category

evaluation-quality

metadata.pairs

after

metadata.version

1.0

from openmed.eval import (
    run_suite, ReleaseGate, fairness_report, error_report,
)

report = run_suite("eval/gold/test.json", suite="golden",
                   model_name="OpenMed/Privacy-PII-Detection", device="cpu",
                   metadata={"family": "PII", "tier": "base",
                             "policy": "hipaa_safe_harbor"})

gate = ReleaseGate(milestone="v1.6", policy="hipaa_safe_harbor").evaluate(report)
fair = fairness_report("OpenMed/Privacy-PII-Detection", "golden")
errs = error_report("OpenMed/Privacy-PII-Detection", "eval/gold/test.json")

card = {
    "model_details": {
        "repo_id": gate.repo_id, "family": gate.family, "tier": gate.tier,
        "format": gate.format, "license": "Apache-2.0",
    },
    "metrics": {
        "exact_span_f1": report.metrics["exact_span_f1"]["f1"],
        "residual_leakage_rate": gate.residual_leakage_rate,
        "critical_leakage_count": gate.critical_leakage_count,
        "per_label_recall": dict(gate.per_label_recall),
        "release_decision": gate.decision,            # RELEASABLE / QUARANTINED
    },
    "subgroup_analysis": fair.to_dict(),              # per-group leakage/recall
    "limitations": errs.to_dict()["confusion_matrix"],
}
# Render `card` into Markdown front matter + body (or the HF card template).

© maziyarpanahi, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (references) in skills/authoring-model-cards of maziyarpanahi/openmed.

• SKILL.md
• references/model-card-sections.md

Open the folder on GitHubat commit 34d7b8c