Agent skill

Deidentify A Dataset

by maziyarpanahi in maziyarpanahi/openmed

De-identify selected free-text columns in a local CSV, JSONL, or Parquet dataset with OpenMed and produce a separate redacted dataset plus a PHI-free aggregate summary.

Apache-2.0Auto-check passedData & Analytics

Install Deidentify A Dataset

skills CLI

$ npx skills add maziyarpanahi/openmed --skill deidentify-a-dataset -a claude-code

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

GitHub CLI

$ gh skill install maziyarpanahi/openmed deidentify-a-dataset --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/deidentify-a-dataset .claude/skills/deidentify-a-dataset && 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 "deidentify-a-dataset" agent skill from https://github.com/maziyarpanahi/openmed/tree/master/skills/deidentify-a-dataset into .claude/skills/deidentify-a-dataset/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "deidentify-a-dataset", 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/maziyarpanahi/openmed/tree/master/skills/deidentify-a-dataset

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 maziyarpanahi/openmed --skill deidentify-a-dataset -a codex

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

GitHub CLI

$ gh skill install maziyarpanahi/openmed deidentify-a-dataset --agent codex

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

Manual copy

$ git clone --depth 1 https://github.com/maziyarpanahi/openmed.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/deidentify-a-dataset .agents/skills/deidentify-a-dataset && 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 "deidentify-a-dataset" agent skill from https://github.com/maziyarpanahi/openmed/tree/master/skills/deidentify-a-dataset into .agents/skills/deidentify-a-dataset/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "deidentify-a-dataset", 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 maziyarpanahi/openmed --skill deidentify-a-dataset -a cursor

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

GitHub CLI

$ gh skill install maziyarpanahi/openmed deidentify-a-dataset --agent cursor

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

Manual copy

$ git clone --depth 1 https://github.com/maziyarpanahi/openmed.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/deidentify-a-dataset .cursor/skills/deidentify-a-dataset && 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 "deidentify-a-dataset" agent skill from https://github.com/maziyarpanahi/openmed/tree/master/skills/deidentify-a-dataset into .cursor/skills/deidentify-a-dataset/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "deidentify-a-dataset", 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/maziyarpanahi/openmed.git --path skills/deidentify-a-dataset

--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 maziyarpanahi/openmed --skill deidentify-a-dataset -a gemini-cli

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

GitHub CLI

$ gh skill install maziyarpanahi/openmed deidentify-a-dataset --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/maziyarpanahi/openmed.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/deidentify-a-dataset .gemini/skills/deidentify-a-dataset && 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 "deidentify-a-dataset" agent skill from https://github.com/maziyarpanahi/openmed/tree/master/skills/deidentify-a-dataset into .gemini/skills/deidentify-a-dataset/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "deidentify-a-dataset", 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 maziyarpanahi/openmed deidentify-a-dataset

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 maziyarpanahi/openmed --skill deidentify-a-dataset -a github-copilot

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

Manual copy

$ git clone --depth 1 https://github.com/maziyarpanahi/openmed.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/deidentify-a-dataset .github/skills/deidentify-a-dataset && 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 "deidentify-a-dataset" agent skill from https://github.com/maziyarpanahi/openmed/tree/master/skills/deidentify-a-dataset into .github/skills/deidentify-a-dataset/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "deidentify-a-dataset", 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 maziyarpanahi/openmed --skill deidentify-a-dataset -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 maziyarpanahi/openmed deidentify-a-dataset --agent opencode

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

Manual copy

$ git clone --depth 1 https://github.com/maziyarpanahi/openmed.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/deidentify-a-dataset .opencode/skills/deidentify-a-dataset && 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 "deidentify-a-dataset" agent skill from https://github.com/maziyarpanahi/openmed/tree/master/skills/deidentify-a-dataset into .opencode/skills/deidentify-a-dataset/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "deidentify-a-dataset", 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: deidentify-a-dataset
GitHub stars: 5.5k
Token cost: ~760 tokens
SKILL.md length: 206 words
Files: 1
Skills in repo: 74
Repo updated: Oct 9, 2026
First seen: Oct 7, 2026
Licence: Apache-2.0

At a glance

De-identify selected free-text columns in a local CSV, JSONL, or Parquet dataset with OpenMed and produce a separate redacted dataset plus a PHI-free aggregate summary.

Works in 6 steps: Confirm that the input is CSV,… → Confirm which columns contain free text.… → Choose a policy and language. Prefer… → …
An agent must prepare a clinical dataset for analysis
SKILL.md covers Procedure, Runnable synthetic example, Safety checks and Repository example
Calls python

What it does

Deidentify A Dataset is an agent skill from maziyarpanahi/openmed. De-identify selected free-text columns in a local CSV, JSONL, or Parquet dataset with OpenMed and produce a separate redacted dataset plus a PHI-free aggregate summary. Use when an agent must prepare a clinical dataset for analysis or sharing without overwriting the source or exposing cell values in logs.

Its SKILL.md is about 760 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Data & Analytics, covering DataFrames and CSV and tabular files. 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

An agent must prepare a clinical dataset for analysis
Sharing without overwriting the source
Exposing cell values in logs

Example prompts

“/deidentify-a-dataset”

Requirements

Python 3

Workflow steps

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

Confirm that the input is CSV, JSONL/NDJSON, or Parquet.
Confirm which columns contain free text. Do not scan or log values to guess.
Choose a policy and language. Prefer strict_no_leak when recall is the
Write to a new path; never overwrite the input.
Inspect only result.summary, which contains aggregate counts and rates.
Validate recall and residual leakage on representative synthetic or

What it can do on your machine

Read from SKILL.md and the folder at commit 9dca507. 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:
- python
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

Deidentify A Dataset loads about 760 tokens when it runs. Until then it costs about 82 tokens; SKILL.md has 206 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~82
When it runs · the whole SKILL.md, loaded when a task matches: ~760

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 9dca507, republished under its Apache-2.0 licence (© maziyarpanahi). 206 words, ~760 tokens.

Download SKILL.mdSave it as .claude/skills/deidentify-a-dataset/SKILL.md (or your agent's skills folder).

name: deidentify-a-dataset
description: De-identify selected free-text columns in a local CSV, JSONL, or Parquet dataset with OpenMed and produce a separate redacted dataset plus a PHI-free aggregate summary. Use when an agent must prepare a clinical dataset for analysis or sharing without overwriting the source or exposing cell values in logs.

De-identify a dataset

Keep the source local, name the free-text columns explicitly, and write to a different destination. Never infer columns or print source and redacted cell values.

Procedure

Confirm that the input is CSV, JSONL/NDJSON, or Parquet.
Confirm which columns contain free text. Do not scan or log values to guess.
Choose a policy and language. Prefer strict_no_leak when recall is the governing safety requirement.
Write to a new path; never overwrite the input.
Inspect only result.summary, which contains aggregate counts and rates.
Validate recall and residual leakage on representative synthetic or approved evaluation fixtures before releasing the output.

Runnable synthetic example

Install the model runtime first with python -m pip install "openmed[hf]".

python

import csv
from pathlib import Path

from openmed import redact_dataset

source = Path("synthetic-notes.csv")
destination = Path("synthetic-notes.redacted.csv")

with source.open("w", newline="", encoding="utf-8") as handle:
    writer = csv.DictWriter(handle, fieldnames=["record_id", "note"])
    writer.writeheader()
    writer.writerows(
        [
            {
                "record_id": "SYNTH-001",
                "note": (
                    "Taylor Example called 212-555-0198 about a "
                    "metformin refill."
                ),
            },
            {
                "record_id": "SYNTH-002",
                "note": (
                    "Send the synthetic follow-up to "
                    "demo.patient@example.test."
                ),
            },
        ]
    )

result = redact_dataset(
    source,
    text_columns=["note"],
    output_path=destination,
    policy="strict_no_leak",
    lang="en",
)

print(result.output_path)
print(result.summary.to_dict())  # Aggregate counts only; no cell contents.

Use the equivalent CLI for an existing dataset:

bash

openmed redact-dataset notes.csv \
  --text-columns note,comment \
  --policy strict_no_leak \
  --output notes.redacted.csv

Safety checks

Keep model inference and files on infrastructure the user controls.
Do not print input rows, detected entity surfaces, reversible mappings, or exception payloads that may contain source text.
Keep source and output paths separate and access-controlled.
Treat the aggregate summary as evidence, not as proof of compliance.
Never commit real clinical data or restricted evaluation corpora.

Repository example

Read and run the offline dataset walkthrough when you need a bundled synthetic fixture and first-run download controls.

Files

Just SKILL.md in skills/deidentify-a-dataset of maziyarpanahi/openmed.

Open the folder on GitHubat commit 9dca507

Compare with similar skills

Deidentify A Dataset 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.

Deidentify A Dataset compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Deidentify A Dataset this skillmaziyarpanahi/openmed	5.5k	—	~760	Automated safety check: Pass	Apache-2.0	today
CSV Data Summarizercoffeefuelbump/csv-data-summarizer-claude-skill	468	2 repos	~1.4k	Automated safety check: Pass	None	11 mo ago
CSV Processingbenchflow-ai/skillsbench	1.8k	—	~455	Automated safety check: Pass	Apache-2.0	2 mo ago
Metabolomics NormalizationTianGzlab/OmicsClaw	161	—	~836	Automated safety check: Pass	Apache-2.0	3 days ago
Minerals Datalamm-mit/scienceclaw	246	—	~730	Automated safety check: Pass	Apache-2.0	1 mo ago
Paper FiguresEvoScientist/EvoSkills	478	1 repos	~4.4k	Automated safety check: Pass	Apache-2.0	10 days ago

Similar skills

CSV Data Summarizer
coffeefuelbump/csv-data-summarizer-claude-skill
Analyzes CSV files, generates summary stats, and plots quick visualizations using Python and pandas.
468 GitHub starsUsed in 2 repos~1.4k tokens
Data & AnalyticsAuto-check passed
CSV Processing
benchflow-ai/skillsbench
A skill your agent uses when reading sensor data from CSV files, writing simulation results to CSV, processing time-series data with pandas, or handling missing values in datasets.
1.8k GitHub stars~455 tokensUpdated 2 mo ago
Data & AnalyticsAuto-check passed
Metabolomics Normalization
TianGzlab/OmicsClaw
Load when normalising a feature × sample metabolomics CSV via median, quantile, total (sum), PQN (probabilistic quotient), or log methods — emits a normalised wide-form table.
161 GitHub stars~836 tokensUpdated 3 days ago
Data & AnalyticsAuto-check passed
Minerals Data
lamm-mit/scienceclaw
Query and analyze structured CSV datasets on critical minerals production, trade, and supply chains
246 GitHub stars~730 tokensUpdated 1 mo ago
Data & AnalyticsAuto-check passed
Paper Figures
EvoScientist/EvoSkills
A skill your agent uses to produce standalone, publication-ready PNG graphics and reproducible matplotlib scripts from tabular data (CSVs or DataFrames).
478 GitHub starsUsed in 1 repo~4.4k tokens
Data & AnalyticsAuto-check passed
Verified Data Analysis with pandas
pipeshub-ai/pipeshub-ai
Loads, cleans, aggregates and joins tabular data with pandas under a verification rule: every number reported must be one that the code actually printed.
3.8k GitHub stars~1.2k tokensUpdated today
Data & AnalyticsAuto-check passed

Questions about Deidentify A Dataset

What does Deidentify A Dataset do?

De-identify selected free-text columns in a local CSV, JSONL, or Parquet dataset with OpenMed and produce a separate redacted dataset plus a PHI-free aggregate summary. Deidentify A Dataset is an agent skill from maziyarpanahi/openmed. De-identify selected free-text columns in a local CSV, JSONL, or Parquet dataset with OpenMed and produce a separate redacted dataset plus a PHI-free aggregate summary.

When should I use Deidentify A Dataset?

Deidentify A Dataset fits situations like: an agent must prepare a clinical dataset for analysis; sharing without overwriting the source; exposing cell values in logs.

How do I install Deidentify A Dataset in Claude Code?

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

How do I install Deidentify A Dataset in Codex?

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

Can I use Deidentify A Dataset 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 deidentify-a-dataset -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/deidentify-a-dataset, .gemini/skills/deidentify-a-dataset, .github/skills/deidentify-a-dataset and .opencode/skills/deidentify-a-dataset in your project.

What does Deidentify A Dataset need to run?

Going by SKILL.md and its folder, Deidentify A Dataset needs the command-line tools its instructions call (python). Our summary lists: Python 3.

Does Deidentify A Dataset 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 Deidentify A Dataset 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 Deidentify A Dataset use?

Deidentify A Dataset 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 Deidentify A Dataset use?

About 760 tokens (SKILL.md is roughly 3k 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 Deidentify A Dataset?

Skills that share tags, products or a category with Deidentify A Dataset: CSV Data Summarizer (coffeefuelbump/csv-data-summarizer-claude-skill, 468 stars), CSV Processing (benchflow-ai/skillsbench, 1.8k stars), Metabolomics Normalization (TianGzlab/OmicsClaw, 161 stars) and Minerals Data (lamm-mit/scienceclaw, 246 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Deidentify A Dataset?

maziyarpanahi (a GitHub user) maintains it in maziyarpanahi/openmed, which has 5,500 GitHub stars. The repository holds 74 skills in this directory. The repository was last updated on October 9, 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.

Deidentify A Dataset

Install Deidentify A Dataset

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

De-identify a dataset

Procedure

Runnable synthetic example

Safety checks

Repository example

Files

Compare with similar skills

Similar skills

CSV Data Summarizer

CSV Processing

Metabolomics Normalization

Minerals Data

Paper Figures

Verified Data Analysis with pandas

More from maziyarpanahi/openmed

HIPAA Safe Harbor Coverage Audit

OpenMed Model Card Writer

HIPAA Pre-Deployment Compliance Check

ICD-10 Coding Assistant

OpenMed ETL to OMOP CDM

Extracting SDOH and Z-Codes

Questions about Deidentify A Dataset

Install Deidentify A Dataset

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

De-identify a dataset

Procedure

Runnable synthetic example

Safety checks

Repository example

Files

Compare with similar skills

Similar skills

More from maziyarpanahi/openmed

Related

Questions about Deidentify A Dataset