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-predictor85
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/skillValidation for skill structure
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an excellent skill description that clearly defines a specialized bioinformatics capability. It provides comprehensive trigger conditions, specific input/output formats, and uses domain-appropriate terminology that users in this field would naturally use. The description is well-structured and leaves no ambiguity about when this skill should be selected.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Predict neoantigens', 'T-cell epitope prediction', 'immunogenicity assessment', with specific inputs (HLA alleles, VCF, peptide sequences) and outputs (neoantigen list, binding affinity, immunogenicity scores). | 3 / 3 |
Completeness | Clearly answers both what (predict neoantigens, T-cell epitope prediction, immunogenicity assessment) and when (explicit 'Trigger conditions' section with multiple specific scenarios including input/output specifications). | 3 / 3 |
Trigger Term Quality | Includes natural domain-specific keywords users would say: 'HLA typing', 'neoantigen prediction', 'tumor immunotherapy', 'T-cell epitope', 'VCF', 'HLA-A*02:01', 'immunogenicity', 'tumor mutation data'. | 3 / 3 |
Distinctiveness Conflict Risk | Highly specialized niche in computational immunology with distinct triggers like 'HLA typing', 'neoantigen', 'tumor immunotherapy' that are unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides strong actionable guidance with executable code examples and comprehensive input/output specifications. However, it suffers from verbosity (explaining concepts like neoantigens, including extensive boilerplate sections) and lacks explicit validation workflows critical for complex bioinformatics pipelines. The content would benefit from splitting reference material into separate files and adding validation checkpoints.
Suggestions
Remove or drastically reduce the 'Function Overview' explanation of what neoantigens are - Claude knows this; focus on the specific implementation details
Add explicit validation steps in the workflow: e.g., 'Validate HLA format before prediction', 'Check VCF parsing succeeded', 'Verify output contains expected fields'
Move the HLA Support List, Scoring Algorithms details, and Risk Assessment/Security Checklist to separate reference files, keeping only essential quick-start content in SKILL.md
Remove boilerplate sections (Lifecycle Status, Evaluation Criteria, Prerequisites) that don't add actionable guidance for this specific skill
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill contains significant verbosity including explanatory sections about what neoantigens are, detailed algorithm explanations Claude likely knows, and extensive boilerplate sections (risk assessment, security checklist, lifecycle status) that add little actionable value. However, the core technical content is reasonably efficient. | 2 / 3 |
Actionability | Provides fully executable Python code examples, complete CLI commands with all flags, concrete input format examples (VCF, table, FASTA), and detailed JSON output schemas. The code is copy-paste ready with realistic parameters. | 3 / 3 |
Workflow Clarity | While the function overview lists 4 steps and the code examples show usage, there are no explicit validation checkpoints or feedback loops for error recovery. For a high-risk bioinformatics workflow involving complex predictions, missing validation steps (e.g., 'verify HLA format before prediction', 'validate VCF parsing') is a gap. | 2 / 3 |
Progressive Disclosure | References to external files exist (references/ directory, scripts/main.py) but the skill is monolithic with extensive inline content that could be split. The 400+ line document includes algorithm details, HLA lists, and boilerplate that would be better in separate reference files. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Reviewed
Table of Contents
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.