New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Choosing Openmed Models

by maziyarpanahi in maziyarpanahi/openmed

Discover and pick the right OpenMed model for a clinical or biomedical task, domain, or language.

Apache-2.0Auto-check passed

Install Choosing Openmed Models

skills CLI
$ npx skills add maziyarpanahi/openmed --skill choosing-openmed-models -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install maziyarpanahi/openmed choosing-openmed-models --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/maziyarpanahi/openmed.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/choosing-openmed-models .claude/skills/choosing-openmed-models && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
choosing-openmed-models
GitHub stars
5.5k
Token cost
~1.9k tokens
SKILL.md length
480 words
Files
1
Skills in repo
74
Repo updated
First seen
Licence
Apache-2.0

At a glance

Discover and pick the right OpenMed model for a clinical or biomedical task, domain, or language.

  • The user asks which OpenMed model to use
  • SKILL.md covers When to use, Install, Quick start: browse… and What ModelInfo tells you, plus 8 more sections
  • Calls pip
  • Wants to list model categories

What it does

Choosing Openmed Models is an agent skill from maziyarpanahi/openmed. Discover and pick the right OpenMed model for a clinical or biomedical task, domain, or language. Use when the user asks which OpenMed model to use, wants to list model categories, find a Disease vs Oncology vs Privacy/PII model, get a PII model for a specific language, search models by size or task, or inspect a model's labels and metadata before loading. Covers listmodelcategories, getmodelsbycategory, getpiimodelsbylanguage, getdefaultpiimodel, searchmodels(ModelQuery(...)), getmodelinfo, and the openmed…

Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: Local-first healthcare AI: clinical NER and HIPAA PII de-identification on hardware you control. 2,200+ medical models, 35 model-backed PII languages, and Python, MLX, Android… The licence is Apache-2.0.

When your agent uses it

  • The user asks which OpenMed model to use
  • Wants to list model categories
  • Find a Disease vs Oncology vs Privacy/PII model
  • Get a PII model for a specific language

Example prompts

  • “/choosing-openmed-models”

Requirements

  • Python 3

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

    Shell commands in SKILL.md call:

    • pip

    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):

    • huggingface.co

    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

Choosing Openmed Models loads about 1.9k tokens when it runs. Until then it costs about 150 tokens; SKILL.md has 480 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~150
When it runs · the whole SKILL.md, loaded when a task matches
~1.9k

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

Auto-check passed

The automated check found no risky patterns in SKILL.md.

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). 480 words, ~1,928 tokens.

Download SKILL.mdSave it as .claude/skills/choosing-openmed-models/SKILL.md (or your agent's skills folder).
name
choosing-openmed-models
description
Discover and pick the right OpenMed model for a clinical or biomedical task, domain, or language. Use when the user asks which OpenMed model to use, wants to list model categories, find a Disease vs Oncology vs Privacy/PII model, get a PII model for a specific language, search models by size or task, or inspect a model's labels and metadata before loading. Covers list_model_categories, get_models_by_category, get_pii_models_by_language, get_default_pii_model, search_models(ModelQuery(...)), get_model_info, and the openmed models CLI. Pairs with loading-openmed-models.
license
Apache-2.0
metadata.project
OpenMed
metadata.category
openmed-core
metadata.pairs
adjacent
metadata.version
1.0

Choosing OpenMed Models

OpenMed ships a registry of clinical and biomedical NER models grouped into 12 categories. Never hardcode a model list — query the registry at runtime so your code stays correct as models are added. This skill helps you go from "I need to find diseases in Spanish discharge notes" to a concrete model key.

When to use

  • The user knows the task (find diseases / tumors / PHI) but not the model.
  • You need the right PII model for a language (es, fr, de, …).
  • You want to filter models by size, task, or tier before loading.
  • You want to inspect a model's labels, params, and license first.

Once you have a key, hand off to loading-openmed-models to load it.

Install

bash
pip install openmed         # registry queries work without the [hf] extra

Quick start: browse categories, then pick

python
import openmed

# 1) The 12 categories
openmed.list_model_categories()
# ['Medical', 'Privacy', 'Anatomy', 'Hematology', 'Chemical', 'Disease',
#  'Genomics', 'Oncology', 'Species', 'Pathology', 'Pharmaceutical', 'Protein']

# 2) Models in a category -> list[ModelInfo]
for m in openmed.get_models_by_category("Disease"):
    print(m.model_id, "|", m.size_category, "|", m.entity_types)

# 3) Inspect one model before loading
info = openmed.get_model_info("OpenMed/OpenMed-NER-DiseaseDetect-BigMed-278M")
print(info.display_name, info.task, info.param_count, info.license)

get_models_by_category and get_all_models return ModelInfo objects. get_all_models() returns a dict[str, ModelInfo] keyed by registry key.

What ModelInfo tells you

Every model exposes (real attributes):

text
model_id          # HF repo id, e.g. "OpenMed/OpenMed-NER-DiseaseDetect-BigMed-278M"
display_name      # human-friendly name
category          # one of the 12 categories
specialization    # e.g. "disease entity detection"
entity_types      # list[str] of labels the model emits, e.g. ["DISEASE", ...]
size_category     # "Tiny" | "Small" | "Medium" | "Large" | "XLarge"
recommended_confidence   # suggested confidence_threshold for this model
family            # "NER" | "PII" | ...
task              # "token-classification"
languages         # e.g. ["en"], ["es"]
param_count       # e.g. 278000000
license           # e.g. "apache-2.0"

Use entity_types to confirm the model emits the labels you need, and recommended_confidence as a sensible default confidence_threshold.

Disease vs Oncology vs Privacy: worked choices

python
import openmed

# Disease conditions in a general clinical note:
disease = openmed.get_models_by_category("Disease")
# e.g. "OpenMed/OpenMed-NER-DiseaseDetect-BigMed-278M"
#      "OpenMed/OpenMed-NER-DiseaseDetect-BioClinical-108M" (smaller/faster)

# Tumors, staging, oncologic findings -> Oncology, not Disease:
onco = openmed.get_models_by_category("Oncology")
# e.g. "OpenMed/OpenMed-NER-OncologyDetect-BigMed-278M"

# PHI / PII detection -> Privacy category:
privacy = openmed.get_models_by_category("Privacy")

Rule of thumb: bigger (278M/560M) = more accurate, slower; smaller (108M, "Small"/"Tiny") = faster, edge-friendly. Start with a mid-size model and size up only if recall is short.

Pick a PII model by language

python
import openmed

# All PII models for Spanish -> dict[str, ModelInfo]
es_models = openmed.get_pii_models_by_language("es")

# The recommended default PII model id for a language:
default_es = openmed.get_default_pii_model("es")
print(default_es)   # HF repo id, or None if unsupported

deidentify(..., lang="es") and extract_pii(..., lang="es") already select an appropriate default — use these helpers when you need to override or to confirm coverage. Supported de-id languages live in openmed.SUPPORTED_LANGUAGES (en es pt fr de it nl hi te ar tr ja).

Structured search with ModelQuery

For filtering by task, language, size, or tier, use the typed search:

python
from openmed import search_models, ModelQuery

results = search_models(ModelQuery(
    task="token-classification",
    language="en",
    max_params=200_000_000,   # keep it small for on-device
    license="apache-2.0",
))
for r in results:
    print(r.repo_id, r.param_count, r.languages, r.formats)

Each result is a ModelSearchResult with fields like repo_id, family, task, languages, tier, param_count, architecture, base_model, formats, canonical_labels, license, and released. ModelQuery filters include task, language, tier, max_params, min_params, format, license, and a free-text query.

Show full SKILL.md (182 more words)Show less

Let OpenMed suggest a model from text

python
import openmed

for key, info, reason in openmed.get_model_suggestions(
    "Stage III adenocarcinoma with metastasis to regional lymph nodes."
):
    print(key, "->", reason)

get_model_suggestions(text) returns (registry_key, ModelInfo, reason) tuples — handy when the domain is unclear from the request.

CLI

bash
openmed models list                 # registry keys (add --include-remote to query the Hub)
openmed models info <registry-key>  # max sequence length for a key
openmed analyze --text "Stage III adenocarcinoma." --model oncology_detection_bigmed_278m

Hand-off to / from OpenMed

  • To loading-openmed-models: pass the chosen model_id/registry key as model_name= to ModelLoader.load_model(...) or openmed.analyze_text(...).
  • To extracting-clinical-entities: use the model's recommended_confidence as your confidence_threshold and verify entity_types matches your schema.
  • To de-identification: feed get_default_pii_model(lang) into openmed.deidentify(model_name=..., lang=...).
python
import openmed
key = "oncology_detection_bigmed_278m"
info = openmed.get_model_info(key)
result = openmed.analyze_text(
    "Stage III adenocarcinoma with nodal metastasis.",
    model_name=key,
    confidence_threshold=info.recommended_confidence,
)

Edge cases & gotchas

  • Category, not keyword. "cancer" is the Oncology category; "diabetes" is Disease. Check entity_types if unsure which fits.
  • get_default_pii_model(lang) can return None for an unsupported language — fall back to a supported one and warn, do not silently use English on non-English text.
  • search_models reads a committed manifest, so it only returns models that have been catalogued — combine with get_all_models() for the full registry.
  • Match labels before committing. A model in the right category may still not emit the exact label you need; confirm via entity_types / canonical_labels.
  • Licensing. All OpenMed registry models are permissively licensed; do not swap in models that bundle restricted terminologies (UMLS/SNOMED/CPT).

Standards & references

© 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

Just SKILL.md in skills/choosing-openmed-models of maziyarpanahi/openmed.

Open the folder on GitHubat commit 34d7b8c

Compare with similar skills

Choosing Openmed Models next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Choosing Openmed Models compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Choosing Openmed Models this skillmaziyarpanahi/openmed5.5k—~1.9kAutomated safety check: PassApache-2.0
Clinical Reportsdavila7/claude-code-templates33k11 repos~9.9kAutomated safety check: NotesMIT
Clinical Researchalirezarezvani/claude-skills28k—~2.7kAutomated safety check: PassMIT
Clinical Decision SupportK-Dense-AI/scientific-agent-skills48k1 repos~3.5kAutomated safety check: PassMIT
Discover Pluginsruvnet/ruflo74k—~2kAutomated safety check: NotesMIT
Flutter Cherry Pickflutter/flutter180k—~1.8kAutomated safety check: PassBSD-3-Clause

Similar skills

  • Clinical Reports

    davila7/claude-code-templates

    Write comprehensive clinical reports including case reports (CARE guidelines), diagnostic reports (radiology/pathology/lab), clinical trial reports (ICH-E3, SAE, CSR), and patient documentation…

    33k GitHub starsUsed in 11 repos~9.9k tokens
    Legal & ComplianceAuto-check: notes

  • Clinical Research

    alirezarezvani/claude-skills

    A skill your agent uses when designing a prospective clinical study before submission — selecting and classifying endpoints (primary / key-secondary / exploratory, with surrogate-endpoint flagging)…

    28k GitHub stars~2.7k tokensUpdated 1 mo ago
    Research & ScienceAuto-check passed

  • Clinical Decision Support

    K-Dense-AI/scientific-agent-skills

    Prepares and validates research-only clinical decision-support evaluation, evidence-profile, cohort, survival, biomarker/model, privacy, and governance artifacts.

    48k GitHub starsUsed in 1 repo~3.5k tokens
    Research & ScienceAuto-check passed

  • Discover Plugins

    ruvnet/ruflo

    Discover and recommend ruflo plugins based on your workflow, installed MCP tools, and current task

    74k GitHub stars~2k tokensUpdated yesterday
    Agent WorkflowsAuto-check: notes

  • Flutter Cherry Pick

    flutter/flutter

    How to land a formal cherry-pick of a merged PR for the flutter/flutter repo stable or beta channel.

    180k GitHub stars~1.8k tokensUpdated today
    MobileAuto-check passed

  • Aas Discover

    sickn33/agentic-awesome-skills

    Discover AAS skills for an explicit task and compare their complete instructions without installing them.

    47k GitHub starsUsed in 1 repo~523 tokens
    Auto-check passed

More from maziyarpanahi/openmed

All 74 skills in this repo

  • HIPAA Safe Harbor Coverage Audit

    maziyarpanahi/openmed

    Checks OpenMed de-identified clinical text against the 18 HIPAA Safe Harbor identifier categories and reports gaps and residual re-identification risk.

    5.5k GitHub stars~1.7k tokensUpdated today
    Auto-check passed

  • OpenMed Model Card Writer

    maziyarpanahi/openmed

    Fills in a model card for an OpenMed clinical NER or de-identification model from its evaluation reports: intended use, metrics, subgroups and limitations.

    5.5k GitHub stars~1.8k tokensUpdated today
    Auto-check passed

  • HIPAA Pre-Deployment Compliance Check

    maziyarpanahi/openmed

    Walks a data pipeline against the HIPAA Privacy and Security Rule checklist and produces a gap report before it processes patient data.

    5.5k GitHub stars~2k tokensUpdated today
    Auto-check passed

  • ICD-10 Coding Assistant

    maziyarpanahi/openmed

    Suggests candidate ICD-10-CM diagnosis and ICD-10-PCS procedure codes for clinical text extracted by OpenMed, with rationale for a certified coder to review.

    5.5k GitHub stars~2k tokensUpdated today
    Auto-check passed

  • OpenMed ETL to OMOP CDM

    maziyarpanahi/openmed

    Maps OpenMed-extracted, terminology-coded conditions, drugs and measurements into OMOP CDM v5.4 tables for OHDSI and ATLAS analytics.

    5.5k GitHub stars~1.9k tokensUpdated today
    Auto-check passed

  • Extracting SDOH and Z-Codes

    maziyarpanahi/openmed

    Finds social risks such as housing instability or food insecurity in clinical notes and proposes matching ICD-10-CM Z-codes for a coder to confirm.

    5.5k GitHub stars~1.9k tokensUpdated today
    Auto-check passed

Questions about Choosing Openmed Models

What does Choosing Openmed Models do?

Discover and pick the right OpenMed model for a clinical or biomedical task, domain, or language. Choosing Openmed Models is an agent skill from maziyarpanahi/openmed. Discover and pick the right OpenMed model for a clinical or biomedical task, domain, or language.

When should I use Choosing Openmed Models?

Choosing Openmed Models fits situations like: the user asks which OpenMed model to use; wants to list model categories; find a Disease vs Oncology vs Privacy/PII model; get a PII model for a specific language.

How do I install Choosing Openmed Models in Claude Code?

Run `npx skills add maziyarpanahi/openmed --skill choosing-openmed-models -a claude-code`. Or copy the skill folder (skills/choosing-openmed-models in maziyarpanahi/openmed) into .claude/skills/choosing-openmed-models in your project. Claude Code loads it when a task matches its description.

How do I install Choosing Openmed Models in Codex?

Run `npx skills add maziyarpanahi/openmed --skill choosing-openmed-models -a codex`. Or copy the skill folder (skills/choosing-openmed-models in maziyarpanahi/openmed) into .agents/skills/choosing-openmed-models in your project. Codex loads it when a task matches its description.

Can I use Choosing Openmed Models in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add maziyarpanahi/openmed --skill choosing-openmed-models -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/choosing-openmed-models, .gemini/skills/choosing-openmed-models, .github/skills/choosing-openmed-models and .opencode/skills/choosing-openmed-models in your project.

What does Choosing Openmed Models need to run?

Going by SKILL.md and its folder, Choosing Openmed Models needs the command-line tools its instructions call (pip). Our summary lists: Python 3.

Does Choosing Openmed Models access the network?

SKILL.md names 1 domain. As links in the text: huggingface.co. This is read from the text; nothing was executed.

Is Choosing Openmed Models safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Choosing Openmed Models use?

Choosing Openmed Models is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Choosing Openmed Models use?

About 1.9k tokens (SKILL.md is roughly 7.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Choosing Openmed Models?

Skills that share tags, products or a category with Choosing Openmed Models: Clinical Reports (davila7/claude-code-templates, 33k stars), Clinical Research (alirezarezvani/claude-skills, 28k stars), Clinical Decision Support (K-Dense-AI/scientific-agent-skills, 48k stars) and Discover Plugins (ruvnet/ruflo, 74k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Choosing Openmed Models?

maziyarpanahi (a GitHub user) maintains it in maziyarpanahi/openmed, which has 5,506 GitHub stars. The repository holds 74 skills in this directory. The repository was last updated on October 11, 2026.

Source: maziyarpanahi/openmed on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.