Psytar Query

Community

QSong-github

psytar-query

Query the PsyTAR psychiatric adverse-reaction corpus. Use when the user asks about patient-reported ADRs, withdrawal symptoms, drug indications, or effectiveness for Zoloft, Lexapro, Cymbalta, or Effexor XR. Accepts drug names (brand or generic), symptom terms, or UMLS CUIs.

Overview

Publisher	QSong-github
Repository	`DrugClaw`
Skill name	`psytar-query`
Stars	118
Forks	3
Bundled files	4
Links	Skill source Repository Homepage

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
4 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by QSong-github on GitHub. Read the source before you install it.

Installation

Install the Psytar Query AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/QSong-github/DrugClaw/tree/main/skills/drug_nlp/psytar
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/QSong-github/DrugClaw.git /tmp/DrugClaw
mkdir -p .claude/skills
cp -r /tmp/DrugClaw/skills/drug_nlp/psytar .claude/skills/psytar-query

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Psytar Query in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Psytar Query on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Psytar Query is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

PsyTAR Query Skill

891 patient reviews → 6 009 annotated sentences → extracted ADR / WD / SSI / DI entities → mapped to 918 UMLS + 755 SNOMED CT concepts.

Entity Detection & Routing

Input Pattern	Detected As	Targets
`C0917801`	UMLS CUI	`*_Mapped` sheets only (UMLS1/UMLS2 cols)
`Zoloft` / `sertraline`	Drug name	`drug_id` or `drug` columns (alias-aware)
`nausea`, `insomnia` …	Free text	substring across all cell values

Generic ↔ brand aliases: sertraline↔Zoloft, escitalopram↔Lexapro, duloxetine↔Cymbalta, venlafaxine↔Effexor.

API

Function	Input	Returns
`search(entity, sheet?, label?)`	single string	`{sheet: [row_dict]}`
`search_batch(entities, sheet?, label?)`	list of strings	`{entity: {sheet: [row_dict]}}`
`summarize(results, entity)`	result dict + label	compact text
`to_json(results)`	result dict	`list[dict]` (flat, adds `_sheet`)
`describe()`	—	dataset overview text

Parameters

sheet — restrict to one sheet (fuzzy-matched: "ADR" → ADR_Identified).
label — when on Sentence_Labeling, keep only rows where the named label column (ADR / WD / EF / INF / SSI / DI) equals 1.

Sheet Schema

Sheet	Description	Key Columns
`Sample`	Original posts	drug_id, rating, indication, side-effect, comment, gender, age, duration
`Sentence_Labeling`	6 009 sentences, binary labels	drug_id, sentence_index, sentences, ADR, WD, EF, INF, SSI, DI, Findings, others, rating, category
`ADR_Identified`	Extracted ADR mentions	drug_id, sentence_index, sentences, ADR1 … ADRn
`WD_Identified`	Extracted WD mentions	drug_id, sentence_index, sentences, WD1 … WDn
`SSI_Identified`	Extracted SSI mentions	drug_id, sentence_index, sentences, SSI1 … SSIn
`DI_Identified`	Extracted DI mentions	drug_id, sentence_index, sentences, DI1 … DIn
`ADR_Mapped`	ADR → UMLS/SNOMED	drug_id, sentence_index, ADR/ADRs, UMLS1, UMLS2, SNOMED-CT, mild, moderate, severe, persistent, not-persistent, body-site, rating, drug, class, type, entity_type
`WD_Mapped`	WD → UMLS/SNOMED	(same structure as ADR_Mapped)
`SSI_Mapped`	SSI → UMLS/SNOMED	(same structure)
`DI_Mapped`	DI → UMLS/SNOMED	(same structure)

Mapped-sheet qualifier columns

mild, moderate, severe — severity descriptors; persistent, not-persistent — duration; body-site — anatomical site; entity_type — Cognitive / Physiological / Psychological / Functional.

Usage

python
from importlib.machinery import SourceFileLoader
m = SourceFileLoader("psytar", "36_PSYTAR.py").load_module()

# overview
print(m.describe())

# drug → ADR mappings
res = m.search("Zoloft", sheet="ADR_Mapped")
print(m.summarize(res, "Zoloft"))

# generic name works too
res = m.search("sertraline", sheet="ADR_Mapped")

# symptom in one Identified sheet
res = m.search("nausea", sheet="ADR_Identified")

# symptom across all sheets
res = m.search("insomnia")

# UMLS CUI (auto-scoped to Mapped sheets)
res = m.search("C0917801")

# withdrawal sentences for Effexor
res = m.search("Effexor", sheet="Sentence_Labeling", label="WD")

# batch
batch = m.search_batch(["Lexapro", "insomnia", "C0917801"])

# JSON for pipeline
flat = m.to_json(m.search("Cymbalta"))

Data Source

Corpus: PsyTAR v1.0 — CC BY 4.0
File: PsyTAR_dataset.xlsx — set via DATA_PATH or env PSYTAR_XLSX
Paper: Zolnoori et al., Data in Brief 24, 103838 (2019). https://doi.org/10.1016/j.dib.2019.103838
Stats: 891 reviews, 6 009 sentences, 4 813 ADR + 590 WD + 1 219 SSI
- 792 DI mentions, 918 UMLS / 755 SNOMED concepts

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Psytar Query AI skill do?

Why use Psytar Query on TypingMind?

Because you install it once and use it with any model. Psytar Query is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Psytar Query in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/QSong-github/DrugClaw/tree/main/skills/drug_nlp/psytar. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Psytar Query?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Psytar Query?

As many as you like. As long as a model supports skills, you can use Psytar Query with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Psytar Query AI skill free?

It is published on GitHub by QSong-github. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Pokemon Player

NousResearch

OrganizationPopular

Play Pokemon via headless emulator + RAM reads.

Docx

Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files) or Word templates (.dotx files). Triggers include: any mention of 'Word doc', 'word document',…

Openclaw Docker E2e Authoring

openclaw

OrganizationPopular

Author OpenClaw Docker E2E and live provider Docker lanes.

Openclaw Parallels Smoke

openclaw

OrganizationPopular

Prepare, snapshot, run, rerun, debug, or interpret OpenClaw Parallels guest install, onboarding, gateway smoke, and upgrade checks across macOS, Windows, and Linux.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

PsyTAR Query Skill

Entity Detection & Routing

API

Parameters

Sheet Schema

Mapped-sheet qualifier columns

Usage

Data Source

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now