agentleFS
YunghoYungho/family-doctor/document-tools/SKILL.md

document-tools

Skill2 starsChanged 8 months agoMITView on GitHub

Read, summarize, extract key data, and simplify medical documents for patients. Use when user asks to read a document, summarize a file, extract data from a report, parse health records, or simplify medical jargon. Supports patient-friendly mode that converts complex medical terms into plain language. Triggers on: read my, summarize, extract from, parse this, explain this report, simplify, what does this mean, medical terms, translate to plain language, patient-friendly.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read, summarize, extract key data, and simplify medical documents for patients.

    line 10
  2. Very specific:

    Use glob to find the file:

    line 35
  3. Distinctive:

    All processing is local

    line 253
  4. Distinctive:

    No external transmission of document content

    line 254

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Document Tools

Read, summarize, extract key data, and simplify medical documents for patients.

When to Use

  • User asks to "read my health report"
  • User asks to "summarize this document"
  • User asks to "extract data from X"
  • User asks to "explain this in simple terms"
  • User asks "what does this medical report mean?"
  • User provides a file path and asks for analysis
  • User wants patient-friendly explanation of medical jargon

Supported Formats

FormatHow to ReadNotes
.mdUse read toolFrontmatter + body
.jsonUse read toolStructured data
.txtUse read toolPlain text
.pdfUse bash + pdftotextRequires pdftotext

Execution Steps

Step 1: Locate the File

Use glob to find the file:

glob "**/thyroid*.md"
glob "**/2026*.md"

Step 2: Read the Content

read --path "/path/to/file.md"

Step 3: Determine Output Mode

User RequestModeDescription
"Summarize" / "Extract"TechnicalKey fields, structured data
"Explain" / "Simplify"Patient-FriendlyPlain language, visual aids
"What does this mean?"Patient-FriendlyFocus on interpretation

Step 4A: Technical Mode (Default)

Extract key fields for health documents:

  • Date of examination/report
  • Key measurements (numbers + units)
  • Classifications (TI-RADS, BI-RADS, etc.)
  • Doctor's conclusion/impression
  • Recommendations

Output format:

{
  "source": "path/to/file.md",
  "date": "YYYY-MM-DD",
  "extracted_fields": {
    "measurement": "value",
    "classification": "category",
    "conclusion": "doctor's note"
  },
  "summary": "2-3 sentence summary"
}

Step 4B: Patient-Friendly Mode (Enhanced)

Convert complex medical documents into easy-to-understand format:

Medical Term Simplification

Medical TermPlain Language
HypertensionHigh blood pressure
HyperglycemiaHigh blood sugar
BenignNot cancer, harmless
MalignantCancerous
NoduleSmall lump or bump
LesionArea of damaged tissue
EdemaSwelling from fluid
ErythemaRedness of skin
BilateralOn both sides
UnilateralOn one side
DiffuseSpread out, not in one spot
FocalIn one specific area
AcuteSudden, recent onset
ChronicLong-lasting, ongoing
AsymptomaticNo symptoms
PrognosisExpected outcome
Differential diagnosisPossible causes being considered
CBC (Complete Blood Count)Blood cell count test
BMP/CMP (Basic/Comprehensive Metabolic Panel)Blood chemistry test
HbA1cAverage blood sugar over 3 months
TSHThyroid function test
WBCWhite blood cell count
RBCRed blood cell count
PLTPlatelet count (blood clotting)

Visual Summary Format

📋 Medical Report Summary (Patient-Friendly)

🏥 What Was Tested:
[Plain language description of the test]

📊 Results at a Glance:
┌────────────────────────────────────────────────┐
│ Normal:        ✅ ✅ ✅ ⚠️ ✅                    │
│ Needs Attention: ⚠️ [1 item]                   │
└────────────────────────────────────────────────┘

🔍 Key Findings:
1. ✅ [Normal finding] - This means [explanation]
2. ⚠️ [Abnormal finding] - This means [explanation]
3. ✅ [Normal finding] - This means [explanation]

💡 What This Means for You:
[2-3 sentences explaining the overall significance]

⚠️ Important Notes:
[Any warnings or things to watch for]

❓ Questions to Ask Your Doctor:
1. [Relevant question based on findings]
2. [Follow-up question if needed]

📅 Next Steps:
- [Recommended action]
- [Follow-up timing]

Severity Indicators

StatusIconMeaning
Normal✅Within healthy range
Borderline⚠️Slightly outside normal, monitor
Abnormal🔶Outside normal range, follow up
Critical🔴Urgent attention needed

Common Health Document Patterns

Blood Test Results

Technical extraction:

  • Date, values outside normal range, doctor's note

Patient-friendly output:

🩸 Blood Test Results (March 2, 2026)

✅ Good News:
- White blood cells: Normal (fighting infection well)
- Red blood cells: Normal (carrying oxygen well)
- Platelets: Normal (blood clotting fine)

⚠️ Items to Discuss:
- Blood sugar: Slightly high (105 mg/dL)
  → Normal is under 100 mg/dL
  → Suggestion: Reduce sugary foods, retest in 3 months

📊 Overall: Generally healthy, one minor item to watch

Ultrasound Report

Technical extraction:

  • Date, organ, measurements, classification, conclusion

Patient-friendly output:

🔬 Ultrasound Report Summary

📍 What Was Checked: [Organ]

📏 Size Found: [X] × [Y] × [Z] mm
   → About the size of a [common object comparison]

📊 Risk Category: [TI-RADS/BI-RADS] [Number]
   → This means: [plain language explanation]
   → Likelihood of being cancerous: [X]%

👨‍⚕️ Doctor's Opinion: [Simplified conclusion]

💡 What You Should Know:
- [Key point 1]
- [Key point 2]

📅 Follow-Up: [Simplified recommendation]

Radiology Report

Patient-friendly output:

📷 Imaging Report Summary

🔍 What Was Scanned: [Body part]

📋 What They Found:
1. [Finding 1 in plain language]
2. [Finding 2 in plain language]

⚠️ Attention Needed:
- [Any concerning findings explained simply]

✅ Normal Findings:
- [List of normal results]

💡 Bottom Line:
[2-3 sentence overall assessment]

Output Format

Technical Mode

{
  "source": "path/to/file.md",
  "date": "YYYY-MM-DD",
  "type": "report_type",
  "extracted_fields": {},
  "summary": "Technical summary"
}

Patient-Friendly Mode

# [Report Type] — Simplified Summary

[Visual summary in plain language]

---
⚠️ This is a simplified interpretation for educational purposes only. 
Always discuss results with your healthcare provider.

Privacy Note

  • All processing is local
  • No external transmission of document content
  • Results stored in health/References/ locally

Error Handling

  • File not found → Ask user for correct path
  • Unsupported format → Suggest converting to .md
  • Empty file → Report empty, suggest checking source
  • Complex jargon → Use medical dictionary to explain

Version: 2.0.0 Updated: 2026-03-21 New in v2.0: Patient-friendly simplification mode, medical term translation Inspired by: OpenClaw Medical Skills patiently-ai (MIT License)

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.