Summarizing Clinical Notes

What it does

When your agent uses it

• Wants a discharge summary draft
• Chart-abstraction summary
• Keywords: summarize note
• Discharge summary

Example prompts

• “Use the summarizing-clinical-notes skill to produce structured, citation-anchored summaries of clinical notes — one-liner, hospital course, and…”
• “/summarizing-clinical-notes”

Requirements

• Python 3

Workflow steps

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

1. 1De-identify with openmed.deidentify. Summaries are often shared or
2. 2Extract grounding spans with openmed.analyze_text (problems, meds,
3. 3Resolve context with openmed.clinical (negation, temporality, subject)
4. 4Compose by view
5. 5Enforce citation coverage. Reject or flag any output sentence with zero
6. 6Mark it a draft. Render the medical-device disclaimer and require human

What it can do on your machine

Read from SKILL.md and the folder at commit 9dca507. 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).

  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
  • jointcommission.org
  • ihi.org
  • fda.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

Summarizing Clinical Notes loads about 1.7k tokens when it runs. Until then it costs about 152 tokens; SKILL.md has 639 words of instructions outside code blocks.

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

~152

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

~1.7k

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 9dca507, republished under its Apache-2.0 licence (© maziyarpanahi). 639 words, ~1,738 tokens.

name

summarizing-clinical-notes

description

Produces structured, citation-anchored summaries of clinical notes — one-liner, hospital course, and problem-oriented views — where every claim cites a source span so nothing is hallucinated. Use after de-identifying notes when the user wants a discharge summary draft, handoff/SBAR, problem list, or chart-abstraction summary. De-identify FIRST with openmed.deidentify, then anchor summary claims to entity spans from openmed.analyze_text. Trigger keywords: summarize note, discharge summary, hospital course, problem-oriented, one-liner, SOAP, SBAR, handoff, chart abstraction.

license

Apache-2.0

metadata.project

OpenMed

metadata.category

clinical-nlp

metadata.pairs

after

metadata.version

1.0

import openmed

note = """\
HPI: 68M with HTN, T2DM presents with 3 days of productive cough and fever to
38.9C. CXR shows RLL infiltrate. Started on ceftriaxone and azithromycin.
Hospital course: improved on IV antibiotics, transitioned to PO. Discharged on
amoxicillin-clavulanate. Follow up with PCP in 1 week.
"""

# 1) ALWAYS de-identify before summarizing or sending text anywhere.
deid = openmed.deidentify(note, method="replace", policy="hipaa_safe_harbor")

# 2) Extract entities; their offsets become your citation anchors.
ner = openmed.analyze_text(deid.text, output_format="dict")
spans = {
    (e["start"], e["end"]): e["text"]
    for e in ner["entities"]
}

# 3) Compose the summary. Every bullet references a (start, end) span so a
#    reviewer can click back to the exact evidence.
def cite(start, end):
    return f"[{start}:{end}] {deid.text[start:end]!r}"

# Example problem-oriented line, grounded in detected spans:
# "Community-acquired pneumonia (RLL infiltrate) — treated with ceftriaxone +
#  azithromycin." with cite(...) anchors for each entity.

© 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/summarizing-clinical-notes of maziyarpanahi/openmed.

Open the folder on GitHubat commit 9dca507