Agent skill

Medical Data Tools

Medical data workflow guide for DICOM metadata inspection and basic de-identification, physiological signal analysis with NeuroKit2, and cohort-table profiling for clinical research datasets.

Apache-2.0Auto-check passedResearch & Science

Install Medical Data Tools

skills CLI

$ npx skills add DrugClaw/DrugClaw --skill medical-data-tools -a claude-code

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

GitHub CLI

$ gh skill install DrugClaw/DrugClaw medical-data-tools --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/DrugClaw/DrugClaw.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/medical/medical-data-tools .claude/skills/medical-data-tools && 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/

Paste into Claude Code

Install the "medical-data-tools" agent skill from https://github.com/DrugClaw/DrugClaw/tree/main/skills/medical/medical-data-tools into .claude/skills/medical-data-tools/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "medical-data-tools", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/DrugClaw/DrugClaw/tree/main/skills/medical/medical-data-tools

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add DrugClaw/DrugClaw --skill medical-data-tools -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install DrugClaw/DrugClaw medical-data-tools --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/DrugClaw/DrugClaw.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/medical/medical-data-tools .agents/skills/medical-data-tools && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "medical-data-tools" agent skill from https://github.com/DrugClaw/DrugClaw/tree/main/skills/medical/medical-data-tools into .agents/skills/medical-data-tools/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "medical-data-tools", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add DrugClaw/DrugClaw --skill medical-data-tools -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install DrugClaw/DrugClaw medical-data-tools --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/DrugClaw/DrugClaw.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/medical/medical-data-tools .cursor/skills/medical-data-tools && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "medical-data-tools" agent skill from https://github.com/DrugClaw/DrugClaw/tree/main/skills/medical/medical-data-tools into .cursor/skills/medical-data-tools/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "medical-data-tools", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/DrugClaw/DrugClaw.git --path skills/medical/medical-data-tools

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add DrugClaw/DrugClaw --skill medical-data-tools -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install DrugClaw/DrugClaw medical-data-tools --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/DrugClaw/DrugClaw.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/medical/medical-data-tools .gemini/skills/medical-data-tools && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "medical-data-tools" agent skill from https://github.com/DrugClaw/DrugClaw/tree/main/skills/medical/medical-data-tools into .gemini/skills/medical-data-tools/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "medical-data-tools", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install DrugClaw/DrugClaw medical-data-tools

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add DrugClaw/DrugClaw --skill medical-data-tools -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/DrugClaw/DrugClaw.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/medical/medical-data-tools .github/skills/medical-data-tools && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "medical-data-tools" agent skill from https://github.com/DrugClaw/DrugClaw/tree/main/skills/medical/medical-data-tools into .github/skills/medical-data-tools/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "medical-data-tools", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add DrugClaw/DrugClaw --skill medical-data-tools -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install DrugClaw/DrugClaw medical-data-tools --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/DrugClaw/DrugClaw.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/medical/medical-data-tools .opencode/skills/medical-data-tools && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "medical-data-tools" agent skill from https://github.com/DrugClaw/DrugClaw/tree/main/skills/medical/medical-data-tools into .opencode/skills/medical-data-tools/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "medical-data-tools", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: medical-data-tools
GitHub stars: 126
Token cost: ~1.3k tokens
SKILL.md length: 404 words
Files: 4
Skills in repo: 25
Repo updated: Mar 23, 2026
First seen: Oct 7, 2026
Licence: Apache-2.0

At a glance

Medical data workflow guide for DICOM metadata inspection and basic de-identification, physiological signal analysis with NeuroKit2, and cohort-table profiling for clinical research datasets.

Works in 5 steps: Identify the input surface first: DICOM… → Run the smallest deterministic template… → Save both the machine-readable output… → …
The user asks to inspect imaging metadata
SKILL.md covers Environment Check, Bundled Assets, Preferred Workflow and DICOM, plus 4 more sections
Runs Python scripts from its folder; calls python3

What it does

Medical Data Tools is an agent skill from DrugClaw/DrugClaw. Medical data workflow guide for DICOM metadata inspection and basic de-identification, physiological signal analysis with NeuroKit2, and cohort-table profiling for clinical research datasets. Use when the user asks to inspect imaging metadata, summarize ECG/PPG/EDA/RSP/EMG signals, or profile tabular medical datasets without making patient-specific diagnoses or treatment decisions.

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files (for example `templates/clinical_cohort_profile.py`, `templates/dicom_inspect.py` and `templates/neuro_signal_analyze.py`).

It sits in Research & Science, covering Clinical and healthcare research. The repository describes itself as: 💊 AI Research Assistant for Accelerated Drug Discovery. 🦞. The licence is Apache-2.0.

When your agent uses it

The user asks to inspect imaging metadata
Summarize ECG/PPG/EDA/RSP/EMG signals
Profile tabular medical datasets without making patient-specific diagnoses
Treatment decisions

Example prompts

“/medical-data-tools”

Requirements

Python 3

Workflow steps

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

Identify the input surface first: DICOM file tree, CSV or TSV signal table, or cohort table.
Run the smallest deterministic template before any broader interpretation.
Save both the machine-readable output and the summary JSON.
Report missing columns, unreadable files, or module gaps explicitly.
Treat all outputs as research or operations artifacts, not clinical decisions.

What it can do on your machine

Read from SKILL.md and the folder at commit 960a6e0. 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
Ships script files (Python), which the agent can run.
Shell commands in SKILL.md call:
- python3
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
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

Medical Data Tools loads about 1.3k tokens when it runs. Until then it costs about 101 tokens; SKILL.md has 404 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~101
When it runs · the whole SKILL.md, loaded when a task matches: ~1.3k

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 DrugClaw/DrugClaw at commit 960a6e0, republished under its Apache-2.0 licence (© DrugClaw). 404 words, ~1,267 tokens.

Download SKILL.mdSave it as .claude/skills/medical-data-tools/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.

name: medical-data-tools
description: Medical data workflow guide for DICOM metadata inspection and basic de-identification, physiological signal analysis with NeuroKit2, and cohort-table profiling for clinical research datasets. Use when the user asks to inspect imaging metadata, summarize ECG/PPG/EDA/RSP/EMG signals, or profile tabular medical datasets without making patient-specific diagnoses or treatment decisions.

Medical Data Tools

Use this skill when the user asks to inspect medical imaging files, biosignal recordings, or cohort tables for research, QA, or data-engineering work.

Typical triggers:

inspect DICOM files, modality mix, study or series structure, metadata completeness
write basic de-identified DICOM copies for downstream research workflows
analyze ECG, PPG, EDA, RSP, or EMG tables with NeuroKit2
summarize clinical cohort tables exported from EHR, OMOP, FHIR, registry, or claims workflows
profile labels, codes, visits, time ranges, or subgroup balance before modeling

Environment Check

bash

which python3 || true
python3 - <<'PY'
mods = ["pandas", "numpy", "pydicom", "neurokit2"]
for name in mods:
    try:
        __import__(name)
        print(f"{name}: ok")
    except Exception as exc:
        print(f"{name}: missing ({exc})")
PY

If pydicom or neurokit2 is missing, say so immediately instead of pretending the analysis ran.

Bundled Assets

templates/dicom_inspect.py
templates/neuro_signal_analyze.py
templates/clinical_cohort_profile.py

Preferred Workflow

Identify the input surface first: DICOM file tree, CSV or TSV signal table, or cohort table.
Run the smallest deterministic template before any broader interpretation.
Save both the machine-readable output and the summary JSON.
Report missing columns, unreadable files, or module gaps explicitly.
Treat all outputs as research or operations artifacts, not clinical decisions.

DICOM

Use templates/dicom_inspect.py for:

modality or study inventory
metadata QA
study/series counts
basic research-oriented de-identification copies

Quick start:

bash

python3 templates/dicom_inspect.py imaging/ct_series \
  --recursive \
  --output medical/dicom_inventory.csv \
  --summary medical/dicom_inventory.json

Basic de-identification example:

bash

python3 templates/dicom_inspect.py imaging/mri_case \
  --recursive \
  --deidentify-dir medical/dicom_deidentified \
  --output medical/dicom_case.csv \
  --summary medical/dicom_case.json

Deliverables:

per-file metadata CSV
summary JSON with modality counts and study/series counts
optional de-identified DICOM copies

State clearly that the built-in de-identification is basic tag scrubbing, not a validated anonymization pipeline.

Show full SKILL.md (187 more words)Show less

Biosignals

Use templates/neuro_signal_analyze.py for:

ECG feature extraction and quality-aware summaries
PPG, EDA, RSP, or EMG preprocessing and interval features
quick physiology feature generation for downstream research models

Example:

bash

python3 templates/neuro_signal_analyze.py \
  --input signals/ecg.csv \
  --signal-column ecg \
  --signal-type ecg \
  --sampling-rate 250 \
  --signals-output medical/ecg_processed.csv \
  --output medical/ecg_features.csv \
  --summary medical/ecg_features.json

Deliverables:

one-row feature CSV
optional processed signal CSV
summary JSON with duration and processing metadata

Do not overstate these outputs. They are research features, signal summaries, and QA signals, not diagnoses.

Cohort Tables

Use templates/clinical_cohort_profile.py for:

patient and visit counts
label balance checks
code distribution checks
subgroup balance before survival, prediction, or trial-emulation work

Example:

bash

python3 templates/clinical_cohort_profile.py \
  --input cohorts/nsclc_registry.csv \
  --patient-id-column patient_id \
  --visit-id-column visit_id \
  --time-column encounter_time \
  --label-column response \
  --code-column regimen \
  --group-column sex \
  --group-column stage \
  --output medical/nsclc_profile.csv \
  --summary medical/nsclc_profile.json

Deliverables:

normalized metric table CSV
summary JSON with patient, visit, label, code, and group distributions

Output Expectations

Good answers should mention:

the exact input paths and column names used
which template was run
what files were written
the key data-quality findings
any missing metadata, missing modules, or de-identification limits

For public drug, clinical-trial, regulatory, or literature APIs, activate pharma-db-tools. For study design, evidence synthesis, and reporting-guideline work, activate clinical-research-tools. For biology databases, activate bio-db-tools. For hypothesis tests, regression, or survival analysis on cohort tables, activate stat-modeling-tools or survival-analysis-tools. For review matrices, citation cleanup, or hypothesis and reproducibility planning, activate literature-review-tools or scientific-workflow-tools.

Files

SKILL.md and 3 other files in skills/medical/medical-data-tools of DrugClaw/DrugClaw.

SKILL.md
templates/clinical_cohort_profile.py
templates/dicom_inspect.py
templates/neuro_signal_analyze.py

Open the folder on GitHubat commit 960a6e0

Compare with similar skills

Medical Data Tools 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.

Medical Data Tools compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Medical Data Tools this skillDrugClaw/DrugClaw	126	—	~1.3k	Automated safety check: Pass	Apache-2.0	6 mo ago
Clinical Trials Databasegoogle-deepmind/science-skills	3.2k	2 repos	~3.2k	Automated safety check: Pass	Apache-2.0	yesterday
CHARLS Paper Reproduction Guidexjtulyc/MedgeClaw	617	1 repos	~1.8k	Automated safety check: Pass	None	7 mo ago
Biomedical Analysis Dispatchxjtulyc/MedgeClaw	617	1 repos	~2k	Automated safety check: Pass	None	7 mo ago
Research Paperluwill/research-skills	862	—	~1.9k	Automated safety check: Pass	None	yesterday
Research Proposalluwill/research-skills	862	—	~4.5k	Automated safety check: Notes	None	yesterday

Similar skills

Clinical Trials Database
google-deepmind/science-skills
Query ClinicalTrials.gov via APIv2. An agent skill from google-deepmind/science-skills.
3.2k GitHub starsUsed in 2 repos~3.2k tokens
Research & ScienceAuto-check passed
CHARLS Paper Reproduction Guide
xjtulyc/MedgeClaw
Guides an agent through reproducing papers built on the CHARLS health and retirement survey, from variable mapping to cognition, depression and isolation scores.
617 GitHub starsUsed in 1 repo~1.8k tokens
Research & ScienceAuto-check passed
Biomedical Analysis Dispatch
xjtulyc/MedgeClaw
Routes bioinformatics, drug discovery, clinical and multi-omics tasks from a chat interface to Claude Code sessions running K-Dense scientific skills, with a live dashboard per task.
617 GitHub starsUsed in 1 repo~2k tokens
Research & ScienceAuto-check passed
Research Paper
luwill/research-skills
A skill your agent uses when the user asks to write or draft an ORIGINAL RESEARCH ARTICLE — IMRaD paper, conference paper, short/workshop paper, 研究论文/期刊论文/会议论文 — reporting their own completed…
862 GitHub stars~1.9k tokensUpdated yesterday
Research & ScienceAuto-check passed
Research Proposal
luwill/research-skills
A skill your agent uses when the user asks to write or draft a PhD / doctoral research proposal, research plan, 研究计划书, or 开题报告 — a forward-looking plan of background, gap, research questions…
862 GitHub stars~4.5k tokensUpdated yesterday
Research & ScienceAuto-check: notes
Medical Imaging Review
LeonChaoX/qinyan-academic-skills
Write comprehensive literature reviews for medical imaging AI research.
944 GitHub starsUsed in 3 repos~1.1k tokens
Research & ScienceAuto-check: notes

Questions about Medical Data Tools

What does Medical Data Tools do?

Medical data workflow guide for DICOM metadata inspection and basic de-identification, physiological signal analysis with NeuroKit2, and cohort-table profiling for clinical research datasets. Medical Data Tools is an agent skill from DrugClaw/DrugClaw. Medical data workflow guide for DICOM metadata inspection and basic de-identification, physiological signal analysis with NeuroKit2, and cohort-table profiling for clinical research datasets.

When should I use Medical Data Tools?

Medical Data Tools fits situations like: the user asks to inspect imaging metadata; summarize ECG/PPG/EDA/RSP/EMG signals; profile tabular medical datasets without making patient-specific diagnoses; treatment decisions.

How do I install Medical Data Tools in Claude Code?

Run `npx skills add DrugClaw/DrugClaw --skill medical-data-tools -a claude-code`. Or copy the skill folder (skills/medical/medical-data-tools in DrugClaw/DrugClaw) into .claude/skills/medical-data-tools in your project. Claude Code loads it when a task matches its description.

How do I install Medical Data Tools in Codex?

Run `npx skills add DrugClaw/DrugClaw --skill medical-data-tools -a codex`. Or copy the skill folder (skills/medical/medical-data-tools in DrugClaw/DrugClaw) into .agents/skills/medical-data-tools in your project. Codex loads it when a task matches its description.

Can I use Medical Data Tools 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 DrugClaw/DrugClaw --skill medical-data-tools -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/medical-data-tools, .gemini/skills/medical-data-tools, .github/skills/medical-data-tools and .opencode/skills/medical-data-tools in your project.

What does Medical Data Tools need to run?

Going by SKILL.md and its folder, Medical Data Tools needs Python for the scripts in its folder and the command-line tools its instructions call (python3). Our summary lists: Python 3.

Does Medical Data Tools access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Medical Data Tools 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 Medical Data Tools use?

Medical Data Tools is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Medical Data Tools use?

About 1.3k tokens (SKILL.md is roughly 5.1k 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 Medical Data Tools?

Skills that share tags, products or a category with Medical Data Tools: Clinical Trials Database (google-deepmind/science-skills, 3.2k stars), CHARLS Paper Reproduction Guide (xjtulyc/MedgeClaw, 617 stars), Biomedical Analysis Dispatch (xjtulyc/MedgeClaw, 617 stars) and Research Paper (luwill/research-skills, 862 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Medical Data Tools?

DrugClaw (a GitHub organization) maintains it in DrugClaw/DrugClaw, which has 126 GitHub stars. The repository holds 25 skills in this directory. The repository was last updated on March 23, 2026.

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

Install Medical Data Tools

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Medical Data Tools

Environment Check

Bundled Assets

Preferred Workflow

DICOM

Biosignals

Cohort Tables

Output Expectations

Related Skills

Files

Compare with similar skills

Similar skills

More from DrugClaw/DrugClaw

Related

Questions about Medical Data Tools