neoantigen-predictor

Predict neoantigens that may be recognized by the immune system based on patient HLA typing and tumor mutation data. Trigger conditions: - User provides HLA typing results and mutation data, requesting neoantigen prediction - User inquires about tumor immunotherapy-related neoantigen prediction - Need to provide T-cell epitope prediction and immunogenicity assessment - Input: HLA alleles (HLA-A*02:01, etc.), tumor mutation data (VCF or peptide sequences) - Output: Predicted neoantigen list, HLA binding affinity, immunogenicity scores

Install with Tessl CLI

npx tessl i github:aipoch/medical-research-skills --skill neoantigen-predictor

What are skills?

Review — 82%

Does it follow best practices?

If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:

npx tessl skill review --optimize ./path/to/skill

Learn more

Validation — 10 / 11 Passed

Validation for skill structure

SKILL.md

Review

Evals

Evaluation results

100%

Personalized Neoantigen Analysis for Colorectal Cancer Patient

Python API neoantigen prediction

Criteria

Without context

With context

Uses NeoantigenPredictor class

100%

Uses netmhcpan method

100%

Correct peptide lengths

100%

Calls predict() correctly

100%

Uses filter_by_binding

100%

Correct rank_threshold for strong binders

100%

Full predictions output saved

100%

High-affinity output saved

100%

Output JSON structure correct

100%

Priority score present in neoantigens

100%

Without context: $0.6698 · 2m 23s · 23 turns · 28 in / 10,068 out tokens

With context: $0.6826 · 1m 53s · 26 turns · 30 in / 6,510 out tokens

100%

Automated Neoantigen Screening Pipeline for Tumor Immunotherapy

CLI prediction with binding filter

Criteria

Without context

With context

Uses python scripts/main.py

100%

Correct HLA argument usage

100%

Uses --mutations flag

100%

Includes peptide lengths 9 and 10

100%

Uses rank-cutoff 0.5

100%

JSON format output

100%

Output file specified

100%

results/patient_report.json exists

100%

Output contains neoantigens list

100%

Without context: $0.4880 · 1m 56s · 15 turns · 18 in / 8,472 out tokens

With context: $0.5850 · 1m 42s · 26 turns · 28 in / 4,822 out tokens

100%

Neoantigen Immunogenicity Report for Vaccine Target Selection

Immunogenicity scoring and priority ranking

Criteria

Without context

With context

Uses NeoantigenPredictor

100%

filter_by_binding with rank 2.0

100%

MHC binding weight documented

100%

Immunogenicity weight documented

100%

Clinical weight documented

100%

priority_score in full results

100%

Binding-filtered section present

100%

Top 5 candidates present

100%

Report saved to correct path

100%

peptide_length 9 and 10 used

100%

Without context: $0.6221 · 2m 33s · 23 turns · 27 in / 10,153 out tokens

With context: $0.6802 · 1m 56s · 31 turns · 33 in / 5,910 out tokens

Evaluated: 1 day ago
Agent: Claude Code

Table of Contents

Personalized Neoantigen Analysis for Colorectal Cancer Patient Automated Neoantigen Screening Pipeline for Tumor Immunotherapy Neoantigen Immunogenicity Report for Vaccine Target Selection

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.