Delegate independent tasks to specialized agents working concurrently with isolated context.
295.4K 206.3K
View 
Armored CAR-T Design Agent
---name: armored-cart-design-agent description: AI-powered design of armored CAR-T cells with cytokine/chemokine expression for enhanced solid tumor efficacy, including IL-12, IL-15, IL-18, and IL-7 armoring strategies. license: MIT metadata: author: AI Group version: "1.0.0" created: "2026-01-20...
SKILL.md
Full skill instructions
"
Armored CAR-T Design Agent
The Armored CAR-T Design Agent provides AI-assisted design of next-generation armored CAR-T cells engineered to express cytokines, chemokines, or other enhancing factors. These armored T cells overcome solid tumor challenges including immunosuppressive TME, poor trafficking, and T cell exhaustion, with recent clinical success in lymphoma (IL-18) and ongoing trials with IL-12, IL-15, and IL-7.
When to Use This Skill
- When designing CAR-T cells for solid tumor applications.
- For selecting optimal armoring payloads (cytokines, chemokines).
- To optimize cytokine expression levels and regulation.
- When engineering safety switches for armored constructs.
- For predicting armored CAR-T efficacy and safety profiles.
Core Capabilities
-
Armoring Payload Selection: Choose optimal cytokines for tumor type.
-
Expression Level Optimization: Balance efficacy vs toxicity.
-
Inducible System Design: Engineer regulated expression systems.
-
Safety Switch Integration: Design kill switches and controls.
-
Construct Optimization: Optimize transgene configuration.
-
Efficacy Prediction: Predict enhanced tumor killing.
Armoring Strategies
| Cytokine | Mechanism | Clinical Status | Tumor Types |
|---|---|---|---|
| IL-12 | Th1 polarization, IFN-gamma | Phase I/II | Solid tumors |
| IL-15 | T/NK persistence | Phase I/II | Hematologic, solid |
| IL-18 | Inflammasome, IFN-gamma | Phase I (promising) | Lymphoma |
| IL-7 | T cell survival | Phase I | Multiple |
| IL-21 | T cell proliferation | Preclinical | Multiple |
| CCL19/21 | T cell trafficking | Preclinical | Solid tumors |
Construct Architecture Options
| Component | Options | Consideration |
|---|---|---|
| Promoter | EF1a, PGK, CAG, NFAT-inducible | Expression level/timing |
| Signal Peptide | Native, IL-2ss, IgK | Secretion efficiency |
| Cytokine | Membrane-bound vs secreted | Local vs systemic |
| Linker | T2A, P2A, IRES | Co-expression efficiency |
| Kill Switch | iCasp9, HSV-TK, CD20 | Safety control |
| Position | Before/after CAR | Expression balance |
Workflow
-
Input: Target tumor type, TME characteristics, CAR design.
-
Payload Selection: Rank armoring strategies for tumor context.
-
Expression Design: Optimize promoter, levels, regulation.
-
Safety Engineering: Add appropriate control switches.
-
Construct Assembly: Generate optimized DNA sequence.
-
Efficacy Prediction: Model enhanced killing and persistence.
-
Output: Optimized armored CAR construct with annotations.
Example Usage
User: "Design an armored CAR-T for pancreatic cancer targeting mesothelin with IL-12 armoring for TME remodeling."
Agent Action:
python3 Skills/Immunology_Vaccines/Armored_CART_Design_Agent/design_armored_cart.py \
--car_target mesothelin \
--tumor_type pancreatic \
--armoring_payload IL-12 \
--expression_system NFAT_inducible \
--safety_switch iCasp9 \
--backbone lentiviral \
--optimize_codon human \
--output armored_cart_design/
Output Components
| Output | Description | Format |
|---|---|---|
| Construct Sequence | Full transgene DNA | .fasta, .gb |
| Construct Map | Annotated visualization | .png, .pdf |
| Expression Model | Predicted levels | .json |
| Safety Analysis | Risk assessment | .json |
| Manufacturing Guide | Production recommendations | .md |
| Predicted Efficacy | Tumor killing model | .json |
IL-12 Armoring Details
| Aspect | Design Choice | Rationale |
|---|---|---|
| Configuration | Tethered IL-12 (p70) | Localized, reduced toxicity |
| Expression | NFAT-inducible | Activation-dependent |
| Dose | Low-level expression | Safety optimization |
| Combination | With PD-1 knockout | Enhanced activity |
IL-18 Armoring Details
| Aspect | Design Choice | Rationale |
|---|---|---|
| Configuration | Secreted mature IL-18 | Enhanced IFN-gamma |
| Expression | Constitutive or inducible | Context-dependent |
| Clinical Results | Lymphoma responses | Validated approach |
| Combination | With IL-21 | Synergistic |
IL-15 Armoring Details
| Aspect | Design Choice | Rationale |
|---|---|---|
| Configuration | Membrane-tethered IL-15/IL-15Ra | Cis-presentation |
| Expression | Constitutive moderate | Persistence without toxicity |
| Benefit | Reduced IL-2 dependence | Manufacturing advantage |
| Safety | Lower CRS risk | Clinical benefit |
AI/ML Components
Payload Selection:
- TME profiling to match cytokine needs
- Multi-objective optimization
- Clinical outcome modeling
Expression Optimization:
- Promoter strength prediction
- Codon optimization
- mRNA stability modeling
Safety Prediction:
- CRS/ICANS risk modeling
- Off-tumor activity prediction
- Systemic cytokine levels
Safety Considerations
| Risk | Mitigation | Implementation |
|---|---|---|
| Cytokine storm | Inducible expression | NFAT promoter |
| Systemic toxicity | Membrane tethering | Localized effect |
| Uncontrolled proliferation | Kill switch | iCasp9 |
| On-target off-tumor | Regulatable CAR | Logic gates |
Clinical Trials (2025-2026)
| Trial | Armoring | Target | Cancer | Status |
|---|---|---|---|---|
| NCT03721068 | IL-18 | CD19 | Lymphoma | Phase I (positive) |
| NCT04119024 | IL-12 | GD2 | Neuroblastoma | Phase I |
| NCT03932565 | IL-15/21 | CD19 | B-ALL | Phase I |
| Multiple | IL-7/CCL19 | Various | Solid | Preclinical |
Prerequisites
- Python 3.10+
- Biopython for sequence handling
- CAR design databases
- Codon optimization tools
- Structure prediction (optional)
Related Skills
- CART_Design_Optimizer_Agent - Base CAR optimization
- NK_Cell_Therapy_Agent - NK cell engineering
- Cytokine_Storm_Analysis_Agent - Safety analysis
- TCell_Exhaustion_Analysis_Agent - Exhaustion prevention
Manufacturing Considerations
| Aspect | Armored CAR Challenge | Solution |
|---|---|---|
| Vector Size | Larger transgene | Optimize construct |
| Transduction | Lower efficiency | Increase MOI |
| Expansion | Cytokine effects | Tune expression |
| Characterization | Complex phenotype | Enhanced QC |
Special Considerations
- Tumor Type Matching: Different tumors need different armoring
- Expression Timing: Constitutive vs inducible tradeoffs
- Dose Finding: Balance efficacy vs toxicity
- Combination: Consider with checkpoint knockout
- Manufacturing: Larger constructs affect production
Efficacy Enhancement Mechanisms
| Mechanism | Cytokine | Effect |
|---|---|---|
| Persistence | IL-15, IL-7 | Longer survival |
| TME Remodeling | IL-12 | M2→M1, DC activation |
| Bystander Killing | IL-18 | Enhanced IFN-gamma |
| Trafficking | CCL19/21 | T cell recruitment |
| Anti-exhaustion | IL-21 | Stem-like maintenance |
Author
AI Group - Biomedical AI Platform
More Other skills
Other
brand-guidelines
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
179.7K 100.1K
View Other
theme-factory
Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.
179.7K 89.5K
View Other
internal-comms
A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).
179.7K 76.1K
View Fundamental design principles for writing maintainable, testable Python code.
40.2K 21.9K
View 
Other
responsive-design
Modern responsive layouts using container queries, fluid typography, CSS Grid, and mobile-first strategies.
40.2K 20K
View Generate Playwright tests from scenarios using interactive browser exploration and validation.
39.7K 18.2K
View Automated website exploration and test case generation using Playwright.
39.7K 14.9K
View Modern React state management with Redux Toolkit, Zustand, Jotai, and React Query for every state category.
40.2K 14.7K
View Other
gdpr-data-handling
GDPR-compliant data handling with consent management, data subject rights, and privacy controls.
40.2K 14.3K
View Python error handling patterns including input validation, exception hierarchies, and partial failure handling. Use when implementing validation logic, designing exception strategies, handling batch processing failures, or building robust APIs.
40.2K 13.5K
View 
Other
refactor-plan
Detailed multi-file refactor planning with safety checks and rollback guidance.
39.7K 13K
View