How do I install the 52_NDF_RT skill?

Run npx skillmds@latest add gabrielmoreira/52-ndf-rt in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is 52_NDF_RT safe to use?

This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. Capability flags: executes scripts, makes network calls. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with 52_NDF_RT?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is 52_NDF_RT free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published 52_NDF_RT?

gabrielmoreira (@gabrielmoreira) published this skill. Their other Agent Skills are listed on their SkillMD profile.

52_NDF_RT by gabrielmoreira — Agent Skill

Name: 52_NDF_RT
Rating: 4.2 (5 reviews)
Author: gabrielmoreira

52_NDF_RT

Query NDF-RT (National Drug File Reference Terminology) via the NCI EVS REST API. Use when looking up drug mechanisms of action, physiological effects, pharmacologic classes, chemical structures, or drug–disease relationships (may_treat / may_prevent) in NDF-RT. Accepts drug names or NDF-RT codes.

gabrielmoreira Updated Sep 9, 2026 17 repo stars

File contents

NDF-RT Query Skill

Search NDF-RT concepts by drug name or NDF-RT code via the NCI EVS REST API. Auto-detects entity type by pattern:

Input Pattern	Detected As	Lookup Logic
`N0000145918`	NDF-RT code (`N` + 10 digits)	direct concept GET
anything else	free text	full-text search endpoint

API

Function	Input	Returns
`search(entity, limit)`	single entity string	`dict` with `entity`, `type`, `results`
`search_batch(entities, limit)`	list of entity strings	`dict[str, dict]`
`summarize(result, entity)`	search result dict + label	compact multi-line text
`to_json(result)`	search result dict	`list[dict]`

Result dict structure

Each item in results contains:

Key	Description
`code`	NDF-RT concept code
`name`	Preferred concept name
`kind`	Concept kind (e.g. `DRUG_KIND`, `DISEASE_KIND`)
`properties`	flat `{type: value}` property dict
`roles`	list of `{type, relatedCode, relatedName}` role relationships
`parents`	list of `{code, name}` ISA parent concepts
`synonyms`	deduplicated list of synonym strings

Key NDF-RT relationship types (roles)

Role	Meaning
`has_MoA`	mechanism of action
`has_PE`	physiological effect
`has_EPC`	established pharmacologic class
`may_treat`	indicated disease/condition
`may_prevent`	preventable disease/condition
`CI_with`	contraindicated with
`has_Chemical_Structure`	chemical structure classification

Usage

See if __name__ == "__main__" block in 52_NDF_RT.py for runnable examples covering: drug name search, code lookup, batch search, JSON output, and root concept listing.

Data

Source: NCI EVS REST API (https://api-evsrest.nci.nih.gov/api/v1)
Terminology: ndfrt
Auth: none required
Rate limits: not documented; use reasonable request spacing
Maintainer: U.S. Department of Veterans Affairs / NCI Enterprise Vocabulary Services

---name: 52-ndf-rtdescription: Query NDF-RT (National Drug File Reference Terminology) via the NCI EVS REST API. Use when looking up drug mechanisms of action, physiological effects, pharmacologic classes, chemical structures, or drug–disease relationships (may_treat / may_prevent) in NDF-RT. Accepts drug names or NDF-RT codes.--- # NDF-RT Query Skill Search NDF-RT concepts by drug name or NDF-RT code via the NCI EVS REST API. Auto-detects entity type by pattern: | Input Pattern | Detected As | Lookup Logic | |---|---|---| | `N0000145918` | NDF-RT code (`N` + 10 digits) | direct concept GET | | anything else | free text | full-text search endpoint | ## API | Function | Input | Returns | |---|---|---| | `search(entity, limit)` | single entity string | `dict` with `entity`, `type`, `results` | | `search_batch(entities, limit)` | list of entity strings | `dict[str, dict]` | | `summarize(result, entity)` | search result dict + label | compact multi-line text | | `to_json(result)` | search result dict | `list[dict]` | ### Result dict structure Each item in `results` contains: | Key | Description | |---|---| | `code` | NDF-RT concept code | | `name` | Preferred concept name | | `kind` | Concept kind (e.g. `DRUG_KIND`, `DISEASE_KIND`) | | `properties` | flat `{type: value}` property dict | | `roles` | list of `{type, relatedCode, relatedName}` role relationships | | `parents` | list of `{code, name}` ISA parent concepts | | `synonyms` | deduplicated list of synonym strings | ### Key NDF-RT relationship types (roles) | Role | Meaning | |---|---| | `has_MoA` | mechanism of action | | `has_PE` | physiological effect | | `has_EPC` | established pharmacologic class | | `may_treat` | indicated disease/condition | | `may_prevent` | preventable disease/condition | | `CI_with` | contraindicated with | | `has_Chemical_Structure` | chemical structure classification | ## Usage See `if __name__ == "__main__"` block in `52_NDF_RT.py` for runnable examples covering: drug name search, code lookup, batch search, JSON output, and root concept listing. ## Data - **Source**: NCI EVS REST API (`https://api-evsrest.nci.nih.gov/api/v1`) - **Terminology**: `ndfrt` - **Auth**: none required - **Rate limits**: not documented; use reasonable request spacing - **Maintainer**: U.S. Department of Veterans Affairs / NCI Enterprise Vocabulary Services

Frequently asked questions