Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/clawbio-hla-typing
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: data, data-analysis
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Python package
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/hla-typing
What's inside
- Skill name
hla-typing- Description
- HLA allele typing from WGS/WES VCF data
- License
- MIT
- Metadata
- author: Manuel Corpas · domain: genomics · version: 0.1.0
- Instructions
- 178 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (11)
- SKILL.md
- api.py
- ground_truth.txt · bench_test_cases/ht_01_basic_correct/
- input.txt · bench_test_cases/ht_01_basic_correct/
- ground_truth.txt · bench_test_cases/ht_02_empty_input/
- input.txt · bench_test_cases/ht_02_empty_input/
- ground_truth.txt · bench_test_cases/ht_03_malformed_input/
- input.txt · bench_test_cases/ht_03_malformed_input/
- demo_input.txt
- hla_typing.py
- test_hla_typing.py · tests/
SKILL.md (first lines)
# Hla Typing You are **Hla Typing**, a specialised ClawBio agent for genomics. Your role is to HLA allele genotyping from WGS/WES VCF data. ## Trigger **Fire this skill when the user says any of:** - "HLA allele genotyping from WGS/WES VCF data" - "run hla-typing" - "allele typing" - "HLA haplotype" - "determine HLA genotype" **Do NOT fire when:** - The user asks for general variant annotation (use vcf-annotator) - The user asks for pharmacogenomics (use pharmgx-reporter) **Design notes:** The trigger must be loud, not subtle. Models skip subdued descriptions. Use exact phrases, domain-specific terms, and multiple synonyms. ## Why This Exists - **Without it**: Users must manually perform HLA allele genotyping from WGS/WES VCF data using command-line tools and custom scripts - **With it**: Automated analysis in seconds with a structured, reproducible report - **Why ClawBio**: Grounded in real databases and algorithms, not LLM guessing ## Core Capabilities 1. **Input validation**: Parse and validate input files with format detection 2. **Analysis**: HLA allele typing from WGS/WES VCF data 3. **Reporting**: Generate structured markdown report with machine-readable JSON ## Scope **One skill, one task.** This skill does hla allele typing from wgs/wes vcf data and nothing else. ## Input Formats | Format | Extension | Required Fields | Example | |--------|-----------|--------------------------|------------------| | VCF | `.vcf` | CHROM, POS, REF, ALT, GT | `demo_input.txt` | | TSV | `.tsv` | variant columns | `sample.tsv` | ## Workflow When the user asks for HLA typing: 1. **Validate**: Check input format and required fields 2. **Parse**: Extract relevant variants and annotations 3. **Analyze**: Apply HLA typing algorithm 4. **Generate**: Write result.json with structured findings 5. **Report**: Write report.md with findings, tables, and disclaimer **Freedom level guidance:** - For database lookups and variant classification: be prescriptive. Every step must be exact. - For report narrative and interpretation: give guidance but leave room for reasoning. ## CLI Reference ```bash # Standard usage python skills/hla-typing/hla_typing.py \ --input <input_file> --output <report_dir> # Demo mode (synthetic data, no user files needed) python skills/hla-typing/hla_typing.py --demo --output /tmp/hla_typing_demo # Via ClawBio runner python clawbio.py run hla-typing --input <file> --output <dir> python clawbio.py run hla-typing --demo ``` ## Demo To verify the skill works: ```bash python clawbio.py run hla-typing --demo ``` Expected output: a report covering synthetic input data with structured results. ## Algorithm / Methodology 1. **Parse input**: Read VCF/TSV and extract relevant loci 2. **Lookup**: Query reference databases for annotations 3. **Score**: Apply scoring algorithm to classify findings 4. **Report**: Generate structured output **Key thresholds / parameters**: - TODO: define thresholds with citations ## Example Queries - "HLA allele typing from WGS/WES VCF data" - "run hla-typing on my VCF" - "analyze my sample with hla-typing" ## Example Output ```markdown # Hla Typing Report **Input**: demo_input.txt (5 variants) **Date**: 2026-04-06 | Locus | Finding | Confidence | |-------|---------|------------| | chr6:29942470 | Example finding 1 | High | | chr6:31353872 | Example finding 2 | Medium | ## Summary Analysis completed on 5 variants. 2 findings reported. *ClawBio is a research and educational tool. It is not a medical device and does not provide clinical diagnoses. Consult a healthcare professional before making any medical decisions.* ``` ## Output Structure
From ClawBio/ClawBio, MIT.
More from ClawBio/ClawBio
- 0.825score
polars-bio
ClawBio (adapted from K-Dense scientific-agent-skills/polars-bio)
Fast genomic interval operations (overlap, nearest, merge, coverage, cluster, complement, subtract, count-overlaps), multi-format bioinformatics I/O…
SkillAFreshness: A★ 1.2KClaude Code +9 - 0.822score
ena-fetch
Nikolai Hecker, UK Dementia Research Institute
Query metadata and download sequencing data from the European Nucleotide Archive (ENA) via the Portal and Browser APIs.
SkillAFreshness: A★ 1.2KClaude Code +9 - 0.822score
gi-expression
ClawBio + Genomic Intelligence
Predict tissue / cell-type expression (log TPM + TPM) from 9,198–500,000 bp of DNA around a TSS, at least 4,599 bp each side (anything but exactly 9,198 bp…
SkillAFreshness: A★ 1.2KClaude Code +9 - 0.822score
geo-fetch
Nikolai Hecker, UK Dementia Research Institute
Query metadata and download data from the NCBI Gene Expression Omnibus (GEO).
SkillAFreshness: A★ 1.2KClaude Code +9 - 0.822score
ukb-ppp-region-fetch
ClawBio
Fetch a regional slice of plasma pQTL summary statistics from the UK Biobank Pharma Proteomics Project (UKB-PPP; Sun 2023 Nature) for a specific (protein…
SkillAFreshness: A★ 1.2KClaude Code +9 - 0.822score
eqtl-catalogue-region-fetch
ClawBio
Fetch a region of cis-eQTL summary statistics from EBI eQTL Catalogue v7+ via tabix-on-FTP.
SkillAFreshness: A★ 1.2KClaude Code +9 - 0.822score
protocols-io
ClawBio Contributors
Search, browse, and retrieve scientific protocols from protocols.io via REST API.
SkillAFreshness: A★ 1.2KClaude Code +9 - 0.822score
gwas-sumstats-harmonize
AlsammanAlsamman
Harmonize GWAS summary statistics from any common format (GWAS-Catalog SSF, PLINK 1.9/2, REGENIE, METAL, BOLT, SAIGE) to one canonical table (SNP CHR BP EA…
SkillAFreshness: A★ 1.2KClaude Code +9 - 0.822score
prs-applicability-gate
Rinat Rizvanov
Deterministic gate for ONE already-computed polygenic score result and ONE person: returns SUPPORTED (raw score, standardised score and reference percentile…
SkillAFreshness: A★ 1.2KClaude Code +9 - 0.822score
pride-fetch
Nikolai Hecker, UK Dementia Research Institute
Query metadata and download data from the PRIDE Archive, EMBL-EBI's proteomics identifications database, via the PRIDE Archive REST API v3.
SkillAFreshness: A★ 1.2KClaude Code +9 - 0.822score
wgs-prs
David de Lorenzo
End-to-end WGS to polygenic risk score pipeline.
SkillAFreshness: A★ 1.2KClaude Code +9 - 0.822score
biostudies-fetch
Nikolai Hecker, UK Dementia Research Institute
Query metadata and download data from EMBL-EBI BioStudies, the database that describes biological studies and links their data across collections…
SkillAFreshness: A★ 1.2KClaude Code +9
Signals
- Stars
- 1,166
- Forks
- 288
- Open issues
- 27
- Last commit (this folder)
- Oct 11, 2026 (16 days ago)
- Last release
- Sep 11, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- Version
- 0.1.0
- License
- MIT
- Repository
- github.com/ClawBio/ClawBio
- Website
- clawbio.github.io/ClawBio/
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from Manuel Corpas
- 0.819score
rare-high-impact-variants
Manuel Corpas
Count rare, high-impact loss-of-function variants carried in a VCF, annotated with molecular consequence and population allele frequency
SkillAFreshness: A★ 1.2KClaude Code +9 - 0.819score
profile-report
Manuel Corpas
Unified personal genomic profile report — reads a PatientProfile JSON and synthesizes all skill results into a single "Your Genomic Profile" document.
SkillAFreshness: A★ 1.2KClaude Code +9 - 0.815score
genome-compare
Manuel Corpas
Compare your genome to George Church (PGP-1) and estimate ancestry composition via IBS and EM admixture
SkillAFreshness: A★ 1.2KClaude Code +9 - 0.815score
pharmgx-reporter
Manuel Corpas
Pharmacogenomic report from DTC genetic data (23andMe/AncestryDNA) — 12 genes, 31 SNPs, 51 drugs
SkillAFreshness: A★ 1.2KClaude Code +9 - 0.815score
claw-ancestry-pca
Manuel Corpas
Ancestry decomposition PCA against the Simons Genome Diversity Project
SkillAFreshness: A★ 1.2KClaude Code +9 - 0.815score
archaic-introgression
Manuel Corpas
Detect Neanderthal and Denisovan introgression segments from modern human genomes
SkillAFreshness: A★ 1.2KClaude Code +9
Cite this page
hla-typing skill. Agent Mart. https://agentmart.dev/skills/clawbio-hla-typing (last updated 2026-10-24)