treatment-plans

Generate concise (typically 1–4 pages) patient-centered medical treatment plans in LaTeX/PDF when a clinician needs an actionable plan with SMART goals, evidence-based interventions, monitoring, and HIPAA-aware documentation.

53 stars

Best use case

treatment-plans is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Generate concise (typically 1–4 pages) patient-centered medical treatment plans in LaTeX/PDF when a clinician needs an actionable plan with SMART goals, evidence-based interventions, monitoring, and HIPAA-aware documentation.

Teams using treatment-plans should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/treatment-plans/SKILL.md --create-dirs "https://raw.githubusercontent.com/aipoch/medical-research-skills/main/scientific-skills/Other/treatment-plans/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/treatment-plans/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How treatment-plans Compares

Feature / Agenttreatment-plansStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Generate concise (typically 1–4 pages) patient-centered medical treatment plans in LaTeX/PDF when a clinician needs an actionable plan with SMART goals, evidence-based interventions, monitoring, and HIPAA-aware documentation.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

> **Source**: [https://github.com/aipoch/medical-research-skills](https://github.com/aipoch/medical-research-skills)

## When to Use

Use this skill when you need to produce a **clinically actionable, professionally typeset** treatment plan (LaTeX → PDF), especially when:

1. You must create an **individualized plan** for a patient across any specialty (medicine, surgery, rehab, behavioral health).
2. You need a **concise “quick reference” plan** (often 1 page) for busy clinical workflows.
3. You are coordinating **multidisciplinary care** (e.g., PCP + specialists + PT/OT + behavioral health) with clear roles and follow-up.
4. You must document **chronic disease management** with measurable targets, monitoring cadence, and escalation thresholds.
5. You need a structured plan for **perioperative care** or **pain management** with safety checks and risk mitigation.

## Key Features

- **Concise formats by default**
  - Preferred: **1-page quick reference card**
  - Standard: **3–4 pages** (front-page executive summary + supporting detail)
  - Extended: **5–6 pages** only when complexity requires it
- **Front-page executive summary (Foundation-style)**
  - Page 1 contains only: title + patient/report info + 2–4 colored “key boxes” (goals, interventions, decision points, timeline)
- **SMART goals**
  - Short- and long-term goals with measurable targets and time bounds
- **Evidence-based interventions with minimal citations**
  - Typically **0–3 brief in-text citations** (e.g., “ADA 2024”)
- **HIPAA-aware documentation**
  - De-identification expectations and documentation hygiene
- **Validation workflow**
  - Completeness and quality checks via scripts (sections present, SMART goals, monitoring adequacy, safety/risk mitigation)
- **Professional LaTeX styling**
  - Custom style package with colored boxes and tables for scan-friendly clinical documents
- **Visual support**
  - Supports adding at least one diagram (e.g., pathway, timeline, decision algorithm) to improve usability

## Dependencies

> Versions may vary by environment; pin them in your project if you need reproducibility.

- **Python**: 3.10+
- **TeX distribution**: TeX Live 2022+ (or MiKTeX equivalent)
- **LaTeX engines**:
  - `xelatex` (recommended)
  - `pdflatex` (supported)
- **Key LaTeX packages** (commonly required by the style/templates):
  - `tcolorbox` (with `most` library), `tikz/pgf`, `geometry`, `xcolor`, `fontspec` (XeLaTeX/LuaLaTeX), `fancyhdr`, `titlesec`, `enumitem`, `booktabs`, `longtable`, `array`, `colortbl`, `hyperref`, `natbib`
- **Project scripts (as referenced by this skill)**:
  - `scripts/generate_template.py`
  - `check_completeness.py`
  - `validate_treatment_plan.py`
  - `timeline_generator.py`
  - (optional) `scripts/generate_schematic.py` for diagram generation

## Example Usage

Below is a complete, runnable example that (1) generates a template, (2) compiles to PDF, and (3) runs validation checks. Adjust paths to match your repository layout.

### 1) Generate a LaTeX template

```bash
cd .claude/skills/treatment-plans/scripts

# Generate a mental health plan template
python generate_template.py --type mental_health --output depression_treatment_plan.tex
```

### 2) (Optional) Generate a diagram for the plan

```bash
# Example: a simple treatment pathway flowchart
python scripts/generate_schematic.py "Depression treatment pathway: assessment -> CBT/SSRI -> monitoring -> escalation criteria" -o figures/depression_pathway.png
```

Include the figure in your `.tex` file (example snippet):

```latex
\begin{figure}[h]
  \centering
  \includegraphics[width=0.95\linewidth]{figures/depression_pathway.png}
  \caption{Treatment pathway overview.}
\end{figure}
```

### 3) Compile to PDF

```bash
# Recommended (better font support)
xelatex depression_treatment_plan.tex

# If you use bibliography features
bibtex depression_treatment_plan || true
xelatex depression_treatment_plan.tex
xelatex depression_treatment_plan.tex
```

### 4) Run completeness and quality validation

```bash
python check_completeness.py depression_treatment_plan.tex
python validate_treatment_plan.py depression_treatment_plan.tex
```

### 5) (Optional) Generate a timeline artifact

```bash
python timeline_generator.py --plan depression_treatment_plan.tex --output timeline.pdf
```

## Implementation Details

### Document length strategy

- Start with the **1-page format** whenever possible.
- Expand to **3–4 pages** only when you need supporting detail (education, coordination, safety monitoring).
- Use **5–6 pages** rarely (multiple comorbidities, complex monitoring, research protocols).

### Front-page executive summary (required pattern)

- Page 1 must be a scan-friendly summary:
  - Title/subtitle
  - Patient/report info box (de-identified)
  - 2–4 colored boxes:
    - **Goals** (SMART bullets)
    - **Core interventions**
    - **Critical decision points / safety thresholds**
    - **Timeline overview**
- Table of contents (if used) begins on page 2; detailed sections follow.

Minimal LaTeX skeleton:

```latex
\maketitle
\thispagestyle{empty}

\begin{patientinfo}
  % De-identified demographics, diagnosis, date, framework
\end{patientinfo}

\begin{goalbox}[Primary Treatment Goals]
  \begin{itemize}
    \item Goal 1 (metric + timeframe)
    \item Goal 2 (metric + timeframe)
  \end{itemize}
\end{goalbox}

\begin{keybox}[Core Interventions]
  \begin{itemize}
    \item Intervention 1 (dose/frequency if applicable)
    \item Intervention 2 (visit cadence / therapy frequency)
  \end{itemize}
\end{keybox}

\begin{warningbox}[Critical Decision Points]
  \begin{itemize}
    \item Escalate if threshold X is met
  \end{itemize}
\end{warningbox}

\newpage
\tableofcontents
\newpage
```

### Core clinical sections (for standard 3–4 page plans)

Include only what changes decisions; prefer tables/bullets:

- Patient info (de-identified), diagnoses (ICD-10 where applicable)
- Assessment summary and risk stratification
- SMART goals (short- and long-term)
- Interventions:
  - pharmacologic (dose/route/frequency/titration + monitoring)
  - non-pharmacologic (lifestyle, therapy, education)
  - procedural/referrals/testing
- Timeline and follow-up schedule
- Monitoring parameters + escalation thresholds
- Expected outcomes (brief)
- Patient education (3–5 key takeaways + red flags)
- Risk mitigation (high-yield safety items only)
- Signature/date block

### Citation policy (minimalist)

- Use **brief in-text citations** only when needed (guidelines, nonstandard regimens, controversial interventions).
- Typical target: **0–3 citations** for a 3–4 page plan.
- Avoid long bibliographies unless explicitly required.

### Validation logic (what scripts should check)

- **Completeness**: required sections exist (goals, interventions, monitoring, follow-up, education, risk mitigation).
- **SMART quality**: goals include metric + timeframe; avoid vague phrasing.
- **Feasibility**: timeline cadence matches interventions; monitoring is realistic.
- **Safety**: contraindications, interaction checks, escalation thresholds, opioid safeguards (if applicable).
- **Compliance hygiene**: de-identification expectations and documentation defensibility.

### Template selection guidance

- `one_page_treatment_plan.tex`: default for most cases (quick reference)
- `general_medical_treatment_plan.tex`: internal medicine / general practice
- `rehabilitation_treatment_plan.tex`: PT/OT/SLP protocols and milestones
- `mental_health_treatment_plan.tex`: psychotherapy + pharmacotherapy + safety plan
- `chronic_disease_management_plan.tex`: long-term targets + coordination
- `perioperative_care_plan.tex`: pre/intra/post-op structure (ERAS, VTE, antibiotics)
- `pain_management_plan.tex`: multimodal analgesia + opioid risk mitigation

Related Skills

treatment-response-predictor-planner

53
from aipoch/medical-research-skills

Designs studies for predicting treatment response or resistance in biomedical and clinical research. Always use this skill when the user needs a treatment-response or resistance prediction study blueprint rather than a prognostic biomarker protocol, diagnostic test design, causal treatment-effect estimation, or a completed manuscript. Focus on responder definition, treatment context, baseline comparability, feature integration strategy, model development logic, validation architecture, and interpretation boundaries. Do not invent response rates, cohort size, assay readiness, regimen uniformity, literature support, or validation access.

skill-auditor

53
from aipoch/medical-research-skills

A comprehensive auditor for any agent skill — including Manus, OpenClaw/ClawHub, Claude, LobeHub, or custom SKILL.md-based skills. Use this skill whenever a user wants to evaluate, audit, review, score, or quality-check an agent skill before publishing, updating, or deploying. Covers two hard veto gates (structural redlines + research integrity redlines), static quality scoring across 25 criteria (ISO 25010 + OpenSSF + Agent), dynamic test input generation, multi-mode execution testing, multi-layer output evaluation with five specialized category rubrics (Evidence Insight / Protocol Design / Data Analysis / Academic Writing / Other), a Research Veto that applies to all four research categories, human eval viewer generation, actionable P0/P1/P2 optimization recommendations, and automatic skill improvement that outputs a polished, production-ready SKILL.md. Also use whenever a user says "audit my skill", "evaluate my skill", "improve my skill", or wants a corrected version after evaluation.

two-sample-mr-research-planner

53
from aipoch/medical-research-skills

Generates complete two-sample Mendelian randomization (MR) research designs from a user-provided research direction. Use when users want to design, plan, or build a study using two-sample MR to test causal relationships. Triggers:"design a two-sample MR study", "build a publishable MR paper", "test whether this biomarker causally affects this disease", "generate Lite/Standard/Advanced MR plans", "screen multiple exposures with MR", "bidirectional MR design", "causal inference using GWAS summary statistics", or "I want to study X and Y using MR". Always outputs four workload configurations (Lite / Standard / Advanced / Publication+) with a recommended primary plan, step-by-step workflow, figure plan, validation strategy, minimal executable version, and publication upgrade path.

research-proposal-generator

53
from aipoch/medical-research-skills

Generates a comprehensive research proposal design based on input literature, including hypothesis, mechanism verification, and budget. Use when the user wants to design a research project from a paper.

research-grants

53
from aipoch/medical-research-skills

Write competitive research proposals for NSF, NIH, DOE, DARPA, and Taiwan's NSTC when you need agency-compliant narratives, budgets, and review-criteria alignment for a specific solicitation/FOA/BAA.

protocol-standardization

53
from aipoch/medical-research-skills

Standardize fragmented experimental steps into reproducible protocol documents when you need method organization, lab SOP drafting, or cross-operator reproducibility; missing parameters must be explicitly marked as "To be supplemented/Not provided".

prospero-registration-helper

53
from aipoch/medical-research-skills

Assists researchers in generating PROSPERO registration content for meta-analyses from a title and optional protocol. Use when the user wants to draft a PROSPERO registration form.

non-tumor-ml-research-planner

53
from aipoch/medical-research-skills

Generates complete non-tumor biomedical machine learning research designs from a user-provided research direction. Always use this skill when users want to plan bioinformatics + ML papers for non-cancer diseases (metabolic, cardiovascular, kidney, inflammatory, autoimmune, infectious, neurological, endocrine, wound healing, chronic multifactor), design diagnostic biomarker studies, combine GEO datasets with feature selection and ML modeling, or generate Lite/Standard/Advanced/Publication+ workload plans. Trigger for:"non-tumor ML study", "bioinformatics paper outside oncology", "key genes and diagnostic model for a disease", "pyroptosis/ferroptosis/senescence/autophagy + disease", "GEO datasets + machine learning", "RF + LASSO diagnostic model", "DEG + feature selection + validation", "immune infiltration + biomarker", "non-cancer biomarker paper". Trigger even for casual phrasings like "I want to study X using machine learning", "help me design a non-tumor bioinformatics paper", or "how do I build a diagnostic model for disease Y".

network-tox-docking-research-planner

53
from aipoch/medical-research-skills

Generates complete network toxicology + molecular docking research designs from a user-provided toxicant and disease/phenotype. Always use this skill when users want to investigate how an environmental toxicant, endocrine disruptor, heavy metal, food contaminant, pharmaceutical residue, or consumer product chemical may contribute to a disease through shared molecular targets, hub genes, pathways, and docking evidence. Trigger for:"network toxicology study", "toxicology mechanism paper", "target prediction + PPI + docking", "environmental pollutant and disease mechanism", "hub genes and docking for toxicant", "Lite/Standard/Advanced toxicology plan", "CTD + SwissTargetPrediction + GeneCards + STRING", "CB-Dock2 docking study", "triclosan/BPA/cadmium/PFAS + disease". Also triggers for Chinese phrasings:"网络毒理学研究设计"、"毒物机制论文"、"靶点预测+PPI+对接"、"环境污染物与疾病机制". Trigger even for casual phrasings like "I want to study how chemical X affects disease Y" or "help me design a toxicology paper". Always output four workload configurations (Lite / Standard / Advanced / Publication+) with a recommended primary plan, step-by-step workflow, figure plan, validation strategy, minimal executable version, and publication upgrade path.

meta-protocol-writer

53
from aipoch/medical-research-skills

Generates a PROSPERO-compliant Meta-analysis protocol based on Title and PICOS. Use when the user wants to write a protocol for a systematic review or meta-analysis.

hypothesis-generation

53
from aipoch/medical-research-skills

Structured scientific hypothesis formulation from observations; use when you have experimental observations or preliminary data and need testable hypotheses with predictions, mechanisms, and validation experiments.

hypogenic

53
from aipoch/medical-research-skills

Automated LLM-driven hypothesis generation and testing for tabular datasets; use when you need systematic exploration of empirical patterns (e.g., fraud detection, content analysis) and want to combine literature insights with data-driven hypothesis evaluation.