Agent skill

Cadec Query

by QSong-github in QSong-github/DrugClaw

Query the CADEC (CSIRO Adverse Drug Event Corpus). An agent skill from QSong-github/DrugClaw.

No licenceAuto-check passedDevelopment

Install Cadec Query

skills CLI
$ npx skills add QSong-github/DrugClaw --skill cadec-query -a claude-code

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

GitHub CLI
$ gh skill install QSong-github/DrugClaw cadec-query --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/QSong-github/DrugClaw.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/drug_nlp/cadec .claude/skills/cadec-query && 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
cadec-query
GitHub stars
116
Used in
1 other repo
Token cost
~471 tokens
SKILL.md length
170 words
Files
6
Skills in repo
31
Repo updated
First seen
Licence
None found

At a glance

Query the CADEC (CSIRO Adverse Drug Event Corpus). An agent skill from QSong-github/DrugClaw.

  • The user asks about adverse drug event mentions in consumer health text
  • SKILL.md covers API, Entity Types in Corpus, Usage and Data
  • Runs Python scripts from its folder
  • Entity annotations from patient forum posts

What it does

Cadec Query is an agent skill from QSong-github/DrugClaw. Query the CADEC (CSIRO Adverse Drug Event Corpus). Use whenever the user asks about adverse drug event mentions in consumer health text, entity annotations from patient forum posts, MedDRA/SNOMED-CT normalised ADR spans, or wants to look up drugs, symptoms, or coded entities in the CADEC corpus.

Its SKILL.md is about 470 tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files (for example `README.md`, `__init__.py` and `cadec_skill.py`).

It sits in Development, covering Architecture decision records and Natural language processing. The repository describes itself as: 🦀 Agentic RAG for drug intelligence · 57 skills · 15 task categories · DTI · ADR · DDI · PGx · Repurposing · Powered by LangGraph.

When your agent uses it

  • The user asks about adverse drug event mentions in consumer health text
  • Entity annotations from patient forum posts
  • MedDRA/SNOMED-CT normalised ADR spans
  • Wants to look up drugs

Example prompts

  • “/cadec-query”

Requirements

  • Python 3

What it can do on your machine

Read from SKILL.md and the folder at commit bc7b93e. 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.

    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

Cadec Query loads about 471 tokens when it runs. Until then it costs about 77 tokens; SKILL.md has 170 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~77
When it runs · the whole SKILL.md, loaded when a task matches
~471

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

Without a licence we can't republish the file, so here is its outline and opening line. It has 170 words (~471 tokens).

“Search CADEC annotated patient forum posts by any entity. Auto-detects type:”

— opening of SKILL.md by QSong-github
name
cadec-query

Read the full SKILL.md on GitHub

Files

SKILL.md and 5 other files in skills/drug_nlp/cadec of QSong-github/DrugClaw.

  • SKILL.md
  • README.md
  • __init__.py
  • cadec_skill.py
  • example.py
  • retrieve.py

Open the folder on GitHubat commit bc7b93e

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in QSong-github/DrugClaw, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Cadec Query 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.

Cadec Query compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Cadec Query this skillQSong-github/DrugClaw1161 repos~471Automated safety check: PassNone
Awesome Rebuttalxiongqi123123/awesome-rebuttal305—~3.3kAutomated safety check: PassMIT
RAG Code Reviewlyonzin/knowledge-rag290—~1.8kAutomated safety check: PassMIT
Track Ideacdiggins/plato106—~1.3kAutomated safety check: PassMIT
Pci Secure Softwaretransilienceai/communitytools559—~1.8kAutomated safety check: PassMIT
Start DesignLog2n-io/Typhon250—~3.9kAutomated safety check: PassCustom licence

Similar skills

  • Awesome Rebuttal

    xiongqi123123/awesome-rebuttal

    Global-installable, project-level academic rebuttal strategy skill for AI/ML/CV/NLP/Robotics papers.

    305 GitHub stars~3.3k tokensUpdated 3 mo ago
    DevelopmentAuto-check passed
  • RAG Code Review

    lyonzin/knowledge-rag

    When performing code review on a PR, diff, snippet, or "look at this change" request, first consult the corpus for related ADRs, coding standards, prior patterns, and similar files.

    290 GitHub stars~1.8k tokensUpdated 3 days ago
    DevelopmentAuto-check passed
  • Track Idea

    cdiggins/plato

    Log a new idea into tracker/ with elaboration — assumptions, design decisions, related work links, approach brainstorm, and simplest implementation.

    106 GitHub stars~1.3k tokensUpdated 10 days ago
    DevelopmentAuto-check passed
  • Pci Secure Software

    transilienceai/communitytools

    Automated PCI Secure Software Standard (SSS) v2.0 readiness gap-assessment of an application from its source code and documentation.

    559 GitHub stars~1.8k tokensUpdated 2 mo ago
    DevelopmentAuto-check passed
  • Start Design

    Log2n-io/Typhon

    Start design for a GitHub issue - creates design doc from research/ideas, updates status to Todo

    250 GitHub stars~3.9k tokensUpdated today
    DevelopmentAuto-check passed
  • Harness Similarity

    ruvnet/ruflo

    ADR-152 — weighted similarity between two harness fingerprints (genome + score JSON).

    74k GitHub stars~866 tokensUpdated today
    DevelopmentAuto-check: notes

More from QSong-github/DrugClaw

All 31 skills in this repo
  • Dailymed Query

    QSong-github/DrugClaw

    Query DailyMed for FDA drug label / package insert information.

    116 GitHub starsUsed in 1 repo~581 tokens
    Auto-check passed
  • Drkg Query

    QSong-github/DrugClaw

    Query the DRKG (Drug Repurposing Knowledge Graph). An agent skill from QSong-github/DrugClaw.

    116 GitHub starsUsed in 1 repo~915 tokens
    Auto-check passed
  • Drugbank Query

    QSong-github/DrugClaw

    Query a locally downloaded DrugBank database. An agent skill from QSong-github/DrugClaw.

    116 GitHub starsUsed in 1 repo~462 tokens
    Auto-check passed
  • Drugcentral Query

    QSong-github/DrugClaw

    Query the DrugCentral drug pharmacology database. An agent skill from QSong-github/DrugClaw.

    116 GitHub starsUsed in 1 repo~710 tokens
    Auto-check passed
  • Drugmechdb Query

    QSong-github/DrugClaw

    Query the DrugMechDB drug mechanism-of-action database. An agent skill from QSong-github/DrugClaw.

    116 GitHub starsUsed in 1 repo~734 tokens
    Auto-check passed
  • Fda Orange Book Query

    QSong-github/DrugClaw

    Query or inspect the FDA Orange Book - FDA-Approved Drug Products Listing resource for drug-centric tasks with emphasis on drug knowledgebase Use whenever Codex needs the calling pattern…

    116 GitHub starsUsed in 1 repo~521 tokens
    Auto-check passed

Questions about Cadec Query

What does Cadec Query do?

Query the CADEC (CSIRO Adverse Drug Event Corpus). An agent skill from QSong-github/DrugClaw. Cadec Query is an agent skill from QSong-github/DrugClaw. Query the CADEC (CSIRO Adverse Drug Event Corpus).

When should I use Cadec Query?

Cadec Query fits situations like: the user asks about adverse drug event mentions in consumer health text; entity annotations from patient forum posts; medDRA/SNOMED-CT normalised ADR spans; wants to look up drugs.

How do I install Cadec Query in Claude Code?

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

How do I install Cadec Query in Codex?

Run `npx skills add QSong-github/DrugClaw --skill cadec-query -a codex`. Or copy the skill folder (skills/drug_nlp/cadec in QSong-github/DrugClaw) into .agents/skills/cadec-query in your project. Codex loads it when a task matches its description.

Can I use Cadec Query 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 QSong-github/DrugClaw --skill cadec-query -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/cadec-query, .gemini/skills/cadec-query, .github/skills/cadec-query and .opencode/skills/cadec-query in your project.

What does Cadec Query need to run?

Going by SKILL.md and its folder, Cadec Query needs Python for the scripts in its folder. Our summary lists: Python 3.

Does Cadec Query 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 Cadec Query 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 Cadec Query use?

No licence was found for Cadec Query or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Cadec Query use?

About 471 tokens (SKILL.md is roughly 1.9k 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 Cadec Query?

Skills that share tags, products or a category with Cadec Query: Awesome Rebuttal (xiongqi123123/awesome-rebuttal, 305 stars), RAG Code Review (lyonzin/knowledge-rag, 290 stars), Track Idea (cdiggins/plato, 106 stars) and Pci Secure Software (transilienceai/communitytools, 559 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Cadec Query?

QSong-github (a GitHub user) maintains it in QSong-github/DrugClaw, which has 116 GitHub stars. The repository holds 31 skills in this directory. The repository was last updated on August 25, 2026.

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