Annotating Variants

What it does

When your agent uses it

• The user wants to predict variant consequences
• Map HGVS to genomic coordinates
• Attach allele frequencies
• Pair variants with phenotype/oncology context

Example prompts

• “Use the annotating-variants skill to annotate VCF variants and normalizes HGVS nomenclature with public, license-free annotators (Ensembl VEP REST…”
• “/annotating-variants”

Requirements

• Python 3

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

1. 1Normalize input to a canonical form: left-align/trim VCF alleles; for HGVS,
2. 2Annotate — REST (/vep/human/hgvs or /vep/human/region) for a handful,
3. 3Attach frequencies from gnomAD; flag common variants (e.g. AF > 1%).
4. 4Filter/prioritize by most_severe_consequence, impact, and rarity.
5. 5Join to clinical context from OpenMed (gene/variant mentions, oncology,

What it can do on your machine

Read from SKILL.md and the folder at commit ea920f3. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • curl

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Hosts in commands or code, which the agent is likely to contact:

  • rest.ensembl.org
  • gnomad.broadinstitute.org
  • grch37.rest.ensembl.org

  Also links to:

  • samtools.github.io
  • hgvs-nomenclature.org
  • ensembl.org
  • pcingola.github.io
  • ncbi.nlm.nih.gov

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Annotating Variants loads about 2.1k tokens when it runs. Until then it costs about 195 tokens; SKILL.md has 671 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~195

When it runs · the whole SKILL.md, loaded when a task matches

~2.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from maziyarpanahi/openmed at commit ea920f3, republished under its Apache-2.0 licence (© maziyarpanahi). 671 words, ~2,118 tokens.

name

annotating-variants

description

Annotates VCF variants and normalizes HGVS nomenclature with public, license-free annotators (Ensembl VEP REST, VEP/SnpEff/ANNOVAR offline) and links variants to gnomAD population frequencies and the clinical context OpenMed extracts. Use when the user wants to predict variant consequences, map HGVS to genomic coordinates, annotate a VCF, attach allele frequencies, or pair variants with phenotype/oncology context. Trigger keywords: VCF, HGVS, variant annotation, VEP, SnpEff, ANNOVAR, consequence, missense, gnomAD, allele frequency, GRCh38, rsID, transcript. Pairs adjacent to OpenMed: combine annotated variants with Genomics/Oncology entities and phenotype from openmed.analyze_text. Tools used are free; restricted clinical databases are user-supplied.

license

Apache-2.0

metadata.project

OpenMed

metadata.category

research-genomics

metadata.pairs

adjacent

metadata.version

1.0

import requests

REST = "https://rest.ensembl.org"
HEADERS = {"Content-Type": "application/json", "Accept": "application/json"}

def vep_hgvs(hgvs: str) -> list[dict]:
    """Annotate a single HGVS variant (GET)."""
    r = requests.get(f"{REST}/vep/human/hgvs/{hgvs}", headers=HEADERS, timeout=30)
    r.raise_for_status()
    return r.json()

# Transcript-level HGVS (coding) — note the build-aware default transcript set
ann = vep_hgvs("ENST00000269305.9:c.215C>G")   # TP53 example
v = ann[0]
print(v["most_severe_consequence"])            # e.g. "missense_variant"
for tc in v.get("transcript_consequences", []):
    print(tc["gene_symbol"], tc.get("hgvsp"), tc.get("sift_prediction"),
          tc.get("polyphen_prediction"))

def vep_region_batch(variants: list[str]) -> list[dict]:
    body = {"variants": variants}   # ["17 7676154 . C G . . .", ...] 1-based
    r = requests.post(f"{REST}/vep/human/region", headers=HEADERS,
                      json=body, timeout=60)
    r.raise_for_status()
    return r.json()

curl 'https://rest.ensembl.org/vep/human/hgvs/ENST00000269305.9:c.215C>G' \
  -H 'Content-Type:application/json'

GNOMAD = "https://gnomad.broadinstitute.org/api"

QUERY = """
query Variant($id: String!, $ds: DatasetId!) {
  variant(variantId: $id, dataset: $ds) {
    variant_id rsids
    genome { ac an af homozygote_count }
    exome  { ac an af homozygote_count }
  }
}"""

def gnomad_freq(variant_id: str, dataset: str = "gnomad_r4") -> dict:
    r = requests.post(GNOMAD, json={"query": QUERY,
        "variables": {"id": variant_id, "ds": dataset}}, timeout=30)
    r.raise_for_status()
    return r.json()["data"]["variant"]

# gnomad_freq("17-7676154-C-G")  -> ac/an/af for exome and genome

© maziyarpanahi, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/annotating-variants of maziyarpanahi/openmed.

Open the folder on GitHubat commit ea920f3