Medical Case Interpreter

Source: https://github.com/aipoch/medical-research-skills

When to Use

• Use this skill when the request matches its documented task boundary.
• Use it when the user can provide the required inputs and expects a structured deliverable.
• Prefer this skill for repeatable, checklist-driven execution rather than open-ended brainstorming.

Key Features

• Scope-focused workflow aligned to: Generates compliant medical case report articles for WeChat.
• Packaged executable path(s): scripts/validate_skill.py.
• Structured execution path designed to keep outputs consistent and reviewable.

Dependencies

• Python: 3.10+. Repository baseline for current packaged skills.
• Third-party packages: not explicitly version-pinned in this skill package. Add pinned versions if this skill needs stricter environment control.

Example Usage

cd "20260316/scientific-skills/Others/medical-case-interpreter"
python -m py_compile scripts/validate_skill.py
python scripts/validate_skill.py --help

Example run plan:

1. Confirm the user input, output path, and any required config values.
2. Edit the in-file CONFIG block or documented parameters if the script uses fixed settings.
3. Run python scripts/validate_skill.py with the validated inputs.
4. Review the generated output and return the final artifact with any assumptions called out.

Implementation Details

• Execution model: validate the request, choose the packaged workflow, and produce a bounded deliverable.
• Input controls: confirm the source files, scope limits, output format, and acceptance criteria before running any script.
• Primary implementation surface: scripts/validate_skill.py.
• Parameters to clarify first: input path, output path, scope filters, thresholds, and any domain-specific constraints.
• Output discipline: keep results reproducible, identify assumptions explicitly, and avoid undocumented side effects.

Validation Shortcut

Run this minimal command first to verify the supported execution path:

python scripts/validate_skill.py --help

Medical Case Interpreter

Description

This skill acts as a Senior Medical Expert to transform raw clinical data into a professional WeChat case report article. It enforces strict privacy, formatting, and style rules without requiring external scripts.

Inputs

• Case Data: Raw text or files containing patient history, exams, and treatment.
• Product Name: The target drug/product to highlight.
• Doctor Info: Name and affiliation of the expert.
• Drug Mapping: (Optional) Specific Chinese translations for English drug names.

Generation Rules

When executing this skill, the Agent must follow these steps and constraints:

Step 1: Privacy & Data Cleaning (Mental Check)

• Strictly Anonymize: Convert all patient names to "Patient (Gender, Age)".
• Remove Dates: Convert specific admission dates to relative time (e.g., "Day 1", "Month 3").
• Hospital Info: Do not mention specific hospital ID numbers.

Step 2: Content Generation

Generate the article in a single pass using the following structure:

1. Title

• Create an engaging, professional title suitable for a medical audience.

2. Foreword

• Constraint: Strictly under 200 words.
• Format: Single paragraph.
• Content: Summarize the case significance and hook the reader. Do not reveal the full outcome yet.

3. Case Report Body

• Header: Start with ## Case Report.
• Structure:
  • ### Patient Information: History, Symptoms (Anonymized).
  • ### Auxiliary Examination: Key lab results and imaging.
  • ### Diagnosis: Clear clinical diagnosis.
  • ### Treatment Process: Detail the regimen. Highlight the [Product Name] usage here.
  • ### Summary: Clinical takeaways.
• Drug Names: If [Drug Mapping] is provided, ALWAYS use the specified Chinese names.

Example Prompt for User

"Please generate a case report for [Product Name] based on the attached file. The doctor is [Doctor Name]."

When Not to Use

• Do not use this skill when the required source data, identifiers, files, or credentials are missing.
• Do not use this skill when the user asks for fabricated results, unsupported claims, or out-of-scope conclusions.
• Do not use this skill when a simpler direct answer is more appropriate than the documented workflow.

Required Inputs

• A clearly specified task goal aligned with the documented scope.
• All required files, identifiers, parameters, or environment variables before execution.
• Any domain constraints, formatting requirements, and expected output destination if applicable.

Recommended Workflow

1. Validate the request against the skill boundary and confirm all required inputs are present.
2. Select the documented execution path and prefer the simplest supported command or procedure.
3. Produce the expected output using the documented file format, schema, or narrative structure.
4. Run a final validation pass for completeness, consistency, and safety before returning the result.

Output Contract

• Return a structured deliverable that is directly usable without reformatting.
• If a file is produced, prefer a deterministic output name such as medical_case_interpreter_result.md unless the skill documentation defines a better convention.
• Include a short validation summary describing what was checked, what assumptions were made, and any remaining limitations.

Validation and Safety Rules

• Validate required inputs before execution and stop early when mandatory fields or files are missing.
• Do not fabricate measurements, references, findings, or conclusions that are not supported by the provided source material.
• Emit a clear warning when credentials, privacy constraints, safety boundaries, or unsupported requests affect the result.
• Keep the output safe, reproducible, and within the documented scope at all times.

Failure Handling

• If validation fails, explain the exact missing field, file, or parameter and show the minimum fix required.
• If an external dependency or script fails, surface the command path, likely cause, and the next recovery step.
• If partial output is returned, label it clearly and identify which checks could not be completed.

Quick Validation

Run this minimal verification path before full execution when possible:

No local script validation step is required for this skill.

Expected output format:

Result file: medical_case_interpreter_result.md
Validation summary: PASS/FAIL with brief notes
Assumptions: explicit list if any

Deterministic Output Rules

• Use the same section order for every supported request of this skill.
• Keep output field names stable and do not rename documented keys across examples.
• If a value is unavailable, emit an explicit placeholder instead of omitting the field.

Completion Checklist

• Confirm all required inputs were present and valid.
• Confirm the supported execution path completed without unresolved errors.
• Confirm the final deliverable matches the documented format exactly.
• Confirm assumptions, limitations, and warnings are surfaced explicitly.