Searching Clinicaltrials

What it does

When your agent uses it

• The user wants to find trials for a diagnosis
• Screen patients against open studies
• Build a trial-matching feature
• Pull a trial corpus for analysis

Example prompts

• “Use the searching-clinicaltrials skill to search ClinicalTrials.gov for studies by condition, intervention, and recruitment status using the modern…”
• “/searching-clinicaltrials”

Requirements

• Python 3

Workflow steps

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

1. 1Build the query from OpenMed facts. Map extracted Disease spans →
2. 2Page through with the cursor until nextPageToken is gone; cap total pulls.
3. 3Persist nctId, status, conditions, interventions, and the raw eligibility
4. 4Optionally re-NER the eligibility / outcomes text with

What it can do on your machine

Read from SKILL.md and the folder at commit 34d7b8c. 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:

  • curl

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Hosts in commands or code, which the agent is likely to contact:

  • clinicaltrials.gov

  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

Searching Clinicaltrials loads about 2k tokens when it runs. Until then it costs about 195 tokens; SKILL.md has 589 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~195

When it runs · the whole SKILL.md, loaded when a task matches

~2k

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

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 34d7b8c, republished under its Apache-2.0 licence (© maziyarpanahi). 589 words, ~2,028 tokens.

name

searching-clinicaltrials

description

Searches ClinicalTrials.gov for studies by condition, intervention, and recruitment status using the modern v2 REST API with cursor (pageToken) pagination. Use when the user wants to find trials for a diagnosis or drug, screen patients against open studies, build a trial-matching feature, or pull a trial corpus for analysis. Trigger keywords: clinical trial, ClinicalTrials.gov, NCT number, trial search, recruiting studies, eligibility, query.cond, query.intr, pageToken, v2 API. Pairs adjacent to OpenMed: take Disease/Pharmaceutical entities from openmed.analyze_text and turn them into query.cond / query.intr filters; the returned eligibility text feeds parsing-trial-eligibility. ClinicalTrials.gov API v2 is fully public — no API key, no license.

license

Apache-2.0

metadata.project

OpenMed

metadata.category

research-genomics

metadata.pairs

adjacent

metadata.version

1.0

import requests

BASE = "https://clinicaltrials.gov/api/v2"

def search_trials(condition: str, intervention: str | None = None,
                  status: str = "RECRUITING", page_size: int = 50) -> dict:
    """One page of studies for a condition (+ optional intervention)."""
    params = {
        "query.cond": condition,            # condition / disease search
        "filter.overallStatus": status,     # comma-separated enum values
        "pageSize": min(page_size, 1000),   # max 1000; default 10
        "countTotal": "true",               # include totalCount on first page
        "format": "json",
    }
    if intervention:
        params["query.intr"] = intervention  # drug / intervention search
    r = requests.get(f"{BASE}/studies", params=params, timeout=30)
    r.raise_for_status()
    return r.json()

data = search_trials("breast cancer", intervention="trastuzumab")
print(data["totalCount"])                    # total matches (first page only)
for study in data["studies"]:
    ps = study["protocolSection"]
    nct = ps["identificationModule"]["nctId"]
    title = ps["identificationModule"]["briefTitle"]
    print(nct, "-", title)

curl "https://clinicaltrials.gov/api/v2/studies?query.cond=breast+cancer\
&query.intr=trastuzumab&filter.overallStatus=RECRUITING&pageSize=50&format=json"

def iter_all(condition: str, status: str = "RECRUITING"):
    params = {"query.cond": condition, "filter.overallStatus": status,
              "pageSize": 1000, "format": "json"}
    while True:
        r = requests.get(f"{BASE}/studies", params=params, timeout=30)
        r.raise_for_status()
        page = r.json()
        yield from page.get("studies", [])
        token = page.get("nextPageToken")
        if not token:
            break
        params["pageToken"] = token        # cursor for the next page

params["fields"] = ("NCTId,BriefTitle,OverallStatus,"
                    "Condition,EligibilityCriteria")

© maziyarpanahi, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/searching-clinicaltrials of maziyarpanahi/openmed.

Open the folder on GitHubat commit 34d7b8c