Parsing Ccda Documents

What it does

When your agent uses it

• Keywords: C-CDA
• Clinical document
• Narrative block
• Discharge summary XML

Example prompts

• “Use the parsing-ccda-documents skill to parse C-CDA / CCD XML clinical documents to extract human-readable section narrative plus coded entries…”
• “/parsing-ccda-documents”

Requirements

• Python 3

Workflow steps

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

1. 1Confirm it's CDA. is_cda_document(...) checks for a ClinicalDocument
2. 2Read the header for context: patient, author, effectiveTime,
3. 3Walk sections by templateId or section code (LOINC). Map to your
4. 4Flatten narrative with itertext()`; preserve the section→text
5. 5De-identify → analyze each narrative with OpenMed. Prefer coded

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

  No scripts in the folder and no shell commands in SKILL.md (its code samples are python and xml).

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

• Network

  Links to these hosts (documentation or services it may open):

  • hl7.org
  • loinc.org

  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

Parsing Ccda Documents loads about 1.9k tokens when it runs. Until then it costs about 170 tokens; SKILL.md has 606 words of instructions outside code blocks.

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

~170

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

~1.9k

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). 606 words, ~1,947 tokens.

name

parsing-ccda-documents

description

Parses C-CDA / CCD XML clinical documents to extract human-readable section narrative plus coded entries, keyed by section LOINC codes and templateIds. Use before OpenMed processing when ingesting C-CDA R2.1 documents (CCD, Discharge Summary, H&P, Consultation Note) exported from an EHR and you need the narrative section text de-identified and analyzed. Hand section narrative to openmed.deidentify and openmed.analyze_text; XML-aware de-identification that preserves CDA markup is available via openmed.interop.cda. Trigger keywords: C-CDA, CCD, CDA, clinical document, templateId, LOINC section, narrative block, discharge summary XML, ClinicalDocument.

license

Apache-2.0

metadata.project

OpenMed

metadata.category

data-ingestion

metadata.pairs

before

metadata.version

1.0

<ClinicalDocument xmlns="urn:hl7-org:v3">
  <recordTarget><patientRole>
    <id extension="12345" root="..."/>
    <patient><name><given>Jane</given><family>Doe</family></name>
      <birthTime value="19700115"/></patient>
  </patientRole></recordTarget>
  <component><structuredBody>
    <component><section>
      <templateId root="2.16.840.1.113883.10.20.22.2.5.1"/>   <!-- Problems -->
      <code code="11450-4" codeSystem="2.16.840.1.113883.6.1"/> <!-- LOINC -->
      <title>Problems</title>
      <text>Active problems: Type 2 diabetes, hypertension.</text>  <!-- narrative -->
      <entry>...coded SNOMED/ICD entries...</entry>
    </section></component>
  </structuredBody></component>
</ClinicalDocument>

import openmed
from xml.etree import ElementTree as ET

NS = {"hl7": "urn:hl7-org:v3"}
SECTION_LOINC = {
    "11450-4": "problems", "10160-0": "medications", "48765-2": "allergies",
    "30954-2": "results",  "18776-5": "plan",        "10164-2": "hpi",
    "8648-8": "hospital_course", "11488-4": "consult_note",
}

root = ET.parse("ccd.xml").getroot()
for section in root.findall(".//hl7:section", NS):
    code_el = section.find("hl7:code", NS)
    loinc = code_el.get("code") if code_el is not None else None
    text_el = section.find("hl7:text", NS)
    if text_el is None:
        continue
    narrative = "".join(text_el.itertext()).strip()       # flatten narrative block
    if not narrative:
        continue

    deid = openmed.deidentify(narrative, method="replace", policy="hipaa_safe_harbor")
    result = openmed.analyze_text(deid.text, output_format="dict")
    section_name = SECTION_LOINC.get(loinc, loinc)
    # attach (section_name, result) for downstream consumers

from openmed.interop.cda import redact_cda, is_cda_document

if is_cda_document("ccd.xml"):
    safe_xml = redact_cda("ccd.xml")     # returns redacted XML string

© 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/parsing-ccda-documents of maziyarpanahi/openmed.

Open the folder on GitHubat commit 34d7b8c