dbsnp-database
Use when you want to look up, map, and search for short genetic variants (SNPs, indels) in NCBI's dbSNP database. Resolves between rsIDs, genomic coordinates in VCF format, and HGVS strings.
Install / Use
npx skills add google-deepmind/science-skills --skill dbsnp_databaseInstalls into whichever agent you are using.
SKILL.md
Installable skill definition
Quality Score
Category
CommunicationSupported Platforms
Our assessment of dbsnp-database
dbsnp-database scores 95/100 on our quality scale, 59th of 394 Communication skills we index (top 15%).
Its SKILL.md is 13 KB long, well organised into 29 sections with 10 code examples: a thorough specification that gives an agent plenty to work with.
With 3,137 GitHub stars, it is one of the more widely adopted skills in the catalogue.
Maintenance, license and trust
- The repository was last updated about 2 months ago, so dbsnp-database is actively maintained.
- Our last check on 2026-11-16 found the source still online.
- It is released under the Apache-2.0 license, a permissive license that allows use, modification and commercial use with attribution.
- Its trust signals score 100/100, with no cautions. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.
Safety scan
No issues foundOur scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.
AI review by kimi-k2.7-code on 2026-09-29. Automated pattern scan on 2026-09-29. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.
dbsnp-database compared with similar skills
All 4 of these similar skills score higher than dbsnp-database; compare them before choosing.
| Skill | Score | Stars | Updated | Format |
|---|---|---|---|---|
| dbsnp-database (this skill)by google-deepmind | 95 | 3.1k | 2mo ago | SKILL.md |
| x402by browser-use | 100 | 121.0k | 3d ago | SKILL.md |
| algorithmic-artby anthropics | 100 | 177.9k | 55d ago | SKILL.md |
| pptxby anthropics | 100 | 177.9k | 55d ago | SKILL.md |
| designby nextlevelbuilder | 100 | 149.0k | 6d ago | SKILL.md |
Frequently asked questions
- How do I install dbsnp-database?
- Run
npx skills add google-deepmind/science-skills --skill dbsnp-database. The install tabs above show the steps for each supported agent. - Which AI agents does dbsnp-database work with?
- It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
- Is dbsnp-database safe to use?
- Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It is Apache-2.0-licensed and scores 100/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
- Is dbsnp-database still maintained?
- The repository was last updated about 2 months ago, so dbsnp-database is actively maintained.
Skill content
View source on GitHubname: dbsnp-database description: > Use when you want to look up, map, and search for short genetic variants (SNPs, indels) in NCBI's dbSNP database. Resolves between rsIDs, genomic coordinates in VCF format, and HGVS strings. For an rsID, returns variant type, gene associations, clinical significance, allele frequencies, and genomic coordinates (GRCh38).
dbSNP Database Integration
Prerequisites
uv: Read theuvskill and follow its Setup instructions to ensureuvis installed and on PATH.- User Notification: If .licenses/dbsnp_database_LICENSE.txt does not already exist in the workspace root directory then (1) prominently notify the user to check the terms at https://www.ncbi.nlm.nih.gov/snp/, then (2) create the file recording the notification text and timestamp.
.envfile: Make sure the.envfile exists in your home directory. Create one if it does not exist.NCBI_API_KEY(optional): Raises the NCBI rate limit from 3 to 10 requests/second. The skill works without it, but a key is recommended if the user plans many queries or encounters a 429 error. You can register for a key for free at https://www.ncbi.nlm.nih.gov/account/settings/. You MUST use the safe credentials protocol in thecredentialsskill to check for and request this key if this skill looks relevant to the user's request.
Core Rules
- Use the Wrapper: ALWAYS execute the provided wrapper script
scripts/dbsnp_cli.pyto query the database rather than constructing custom HTTP or curl requests. The script automatically handles rate limiting, retries, and JSON parsing. - Command Choice: Do NOT use
search-regionto find the rsID of a specific variant; useresolve-variantinstead. - Output Size: Avoid using
--fullonget-variantunless specifically needed, as raw payloads can exceed 1 MB. - Shell Safety: Always wrap HGVS strings in single quotes to prevent shell expansion errors.
- Notification: If this skill is used, ensure this is mentioned in the output.
When to Use
Use this skill when you need to:
- Map a genomic variant to its canonical rsID (from VCF coordinates or HGVS notation).
- Retrieve summary data for an rsID: variant type, gene associations, clinical significance, and population allele frequencies.
- Convert an rsID back to genomic coordinates on a specific assembly.
- Find all known variants within a chromosomal region.
Do NOT use when you need to:
- Obtain clinical pathogenicity classifications with submitter rationales (use clinvar-database).
- Get precise population-level allele frequencies stratified by ancestry (use gnomad-database).
- Predict the functional effect of a novel mutation (use alphagenome-single-variant-analysis).
- View 3D protein structures affected by a variant (use alphafold-database-fetch-and-analyze / pdb-database).
Command Selection Guide
Pick the right command on the first try. Match the user's input to the correct subcommand below — one command call is almost always sufficient.
- User gives you…: Run this command
- An rsID (e.g.
rs7412,rs268):get-variant - Genomic coordinates: chrom pos ref alt (e.g.
8 19962213 C T):resolve-variant - An HGVS string (e.g.
NC_000008.11:g.19962213del):resolve-hgvs - An rsID and they want coordinates back:
resolve-rsid - A chromosomal region (chrom start end):
search-region
[!CAUTION] Do NOT use
search-regionto find the rsID of a specific variant. If the user provides a chromosome, position, reference allele, and alternate allele (four values), useresolve-variant— it is a direct, single-API-call lookup.search-regionis only for surveying all variants within a positional range and returns hundreds/thousands of results.
Quick Start
# Look up variant rs7412: type, gene, clinical significance, MAF
uv run scripts/dbsnp_cli.py get-variant rs7412 --output /tmp/rs7412.json
# Find the rsID for a variant at chr8:19962213 C>T
uv run scripts/dbsnp_cli.py resolve-variant 8 19962213 C T \
--output /tmp/resolve.json
All subcommands write JSON to disk. Always save output in the /tmp/ directory.
The --output flag is required.
Commands
1. get-variant — Fetch Variant Record
Retrieve the RefSNP record for one rsID. By default the output is abbreviated to
the most useful fields. Both rs268 and 268 are accepted.
uv run scripts/dbsnp_cli.py get-variant rs268 --output /tmp/rs268.json
uv run scripts/dbsnp_cli.py get-variant 268 --assembly GCF_000001405.40 \
--output /tmp/rs268.json
Arguments:
rsid(positional, required): The RefSNP identifier.--assembly: RefSeq assembly accession (default:GCF_000001405.40= GRCh38).--full: Return the complete raw JSON payload — see warning below.--output: Output file path (default:/tmp/dbsnp_output.json).
Abbreviated output fields:
refsnp_id: Numeric rsIDvariant_type: e.g.snv,ins,del,delinsgenes: Sorted list of gene symbols (locus names)clinical_significances: List of clinical significance labelsminor_allele_frequencies: Study name, allele count, total countplacements: Genomic placements for the requested assembly
[!WARNING] About
--full: The raw RefSNP payload is typically 50–500 KB and can exceed 1 MB for clinically significant variants with many submissions. Only use--fullwhen you specifically need data absent from the abbreviated output — for example:
- The complete HGVS nomenclature across every transcript and protein isoform.
- Full submission history with individual submitter details and timestamps.
- Population-level allele frequency breakdowns by sub-population within a study (e.g. per-population gnomAD counts).
- The full set of genomic placements across multiple assemblies (GRCh37 and GRCh38 simultaneously).
- Merge history showing which older rsIDs were merged into this one.
2. resolve-variant — Genomic Coordinates → rsID
Determine the rsID(s) for a variant given its genomic coordinates (chromosome,
position, reference allele, alternate allele). This is the command to use when
the user provides a variant as space-separated coordinates like 8 19962213 C T.
uv run scripts/dbsnp_cli.py resolve-variant 8 19962213 C T \
--output /tmp/resolve.json
Arguments:
chrom(positional): Chromosome number (e.g.8) or RefSeq sequence accession (e.g.NC_000008.11). Chromosomes X and Y must be passed as their numeric equivalents:23for X and24for Y.pos(positional): 1-based genomic position.ref(positional): Reference allele (e.g.C).alts(positional): Alternate allele(s), comma-separated (e.g.T).--assembly: RefSeq assembly accession (default:GCF_000001405.40).--output: Output file path (default:/tmp/dbsnp_output.json).
Output: {"rsids": ["12345", "67890"]}
3. resolve-rsid — rsID → Genomic Coordinates
Get the genomic placement (sequence ID and allele details) for a known rsID on a specific assembly.
uv run scripts/dbsnp_cli.py resolve-rsid rs7412 --output /tmp/coords.json
Arguments:
rsid(positional): The RefSNP identifier.--assembly: RefSeq assembly accession (default:GCF_000001405.40).--output: Output file path (default:/tmp/dbsnp_output.json).
Output: {"rsid": "7412", "assembly": "...", "placements": [...]}
4. resolve-hgvs — HGVS → rsID
Find the rsID(s) corresponding to an HGVS expression.
uv run scripts/dbsnp_cli.py resolve-hgvs 'NC_000008.11:g.19962213del' \
--output /tmp/hgvs.json
Arguments:
hgvs(positional): The HGVS string.--assembly: RefSeq assembly accession (default:GCF_000001405.40).--output: Output file path (default:/tmp/dbsnp_output.json).
Output: {"rsids": ["12345"]}
[!TIP] HGVS strings often contain characters that shells interpret (colons, greater-than signs). Always wrap them in single quotes to prevent shell expansion.
5. search-region — Regional Variant Search
Find all rsIDs within a bounded chromosomal region.
uv run scripts/dbsnp_cli.py search-region 7 117100000 117300000 \
--output /tmp/region.json
Arguments:
chrom(positional): Chromosome (e.g.7). Use23for chromosome X and24for chromosome Y.start(positional): Start position.end(positional): End position.--retmax: Maximum rsIDs to return (default: 500, ceiling: 5 000).--output: Output file path (default:/tmp/dbsnp_output.json).
Output:
{
"rsids": ["12345", "67890", "..."],
"returned": 500,
"total_available": 1423,
"truncated": true,
"note": "Only 500 of 1423 variants returned. Increase --retmax ..."
}
When total_available exceeds the returned count, the output includes a
truncated flag and a note. Increase --retmax to retrieve more (up to 5
000).
Typical Workflows
Identify a known variant from coordinates
# Step 1: Map VCF coordinates to rsID
uv run scripts/dbsnp_cli.py resolve-variant 19 44908684 T C \
--output /tmp/step1.json
# Step 2: Get the full details for the resolved rsID
uv run scripts/dbsnp_cli.py get-variant <rsid_from_step1> \
--output /tmp/step2.json
Survey variants in a gene region
# Step 1: Find all variants in a region spanning the CFTR gene
uv run scripts/dbsnp_cli.py search-region 7 117100000 117300000 \
--retmax 1000 --output /tmp/region.json
# Step 2: Retrieve details on individual rsIDs of interest
uv run scripts/dbsnp_cli.py get-variant <rsid> --output /tmp/detail.json
Translate HGVS notation to genomic coordinates
# Step 1: Get the rsID for an HGVS expression
uv run scripts/dbsnp_cli.py resolve-hgvs 'NC_000019.10:g.44908684T>C' \
--output /tmp/hgvs.json
# Step 2: Resolve that rsID to VCF-style coordinates
uv run scripts/dbsnp_cli.py resolve-rsid <rsid> --output /tmp/coords.json
Assembly Defaults and Automatic Fallback
The Variation Services endpoints (used by get-variant, resolve-variant,
resolve-rsid, resolve-hgvs) expect a RefSeq assembly accession. The
RefSeq accession for GRCh38 is GCF_000001405.40, and for GRCh37 it is
GCF_000001405.25.
The search-region subcommand always searches GRCh38 positions.
[!IMPORTANT] Automatic assembly fallback: The
resolve-variantandresolve-hgvscommands automatically try GRCh38 first. If no rsIDs are found, they retry with GRCh37 before reporting failure. When a fallback occurs the output JSON includes a"note"field explaining which assembly succeeded. You do NOT need to manually retry with a different assembly — the script handles this transparently.
You only need to override --assembly when you specifically want to
restrict the lookup to one assembly (e.g. because the user's coordinates are
known to be GRCh37).
NCBI API Key and Rate Limiting
Without an API key the script is limited to 3 requests per second. With a key this increases to 10 requests per second.
You can register for a key for free at
https://www.ncbi.nlm.nih.gov/account/settings/. You MUST use the safe
credentials protocol in the credentials skill to check for and request this
key if this skill looks relevant to the user's request.
Troubleshooting HTTP 500 Errors
Reference Allele Mismatch
If you receive an HTTP 500 error with a message detailing that the asserted reference allele is not equal to the reference sequence:
What it means: The coordinate position is likely valid, but the reference
allele (ref) you provided does not match the base at that position in the
requested assembly.
**Actio
Truncated for display — read the full file on GitHub.
Related Skills
x402
121.0kSet up Browser Use Cloud payments with x402 — pay per request from a crypto wallet (USDC on Base mainnet), no signup or API key.
algorithmic-art
177.9kCreating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems.
pptx
177.9kUse this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an em…
design
149.0kComprehensive design skill: brand identity, design tokens, UI styling, logo generation (55 styles, Gemini, Atlas Cloud, or MuAPI AI), corporate identity program (50 deliverables, CIP mockups), HTML presentations (Chart.js), banner design (22 styles, social/ads/web/print), icon design (15 styles, SVG…
Languages
Trust signals
From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.
