[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7F5F878H5VDSZ3M7RAZWWRC":3,"skill-same:01M7F5F878H5VDSZ3M7RAZWWRC":77},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":31,"commitSha":32,"skillDirectory":33,"forksCount":13,"repositoryHtmlUrl":34,"repositoryHomepageUrl":6,"ownerHtmlUrl":35,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":36,"install":37,"resources":50},"01M7F5F878H5VDSZ3M7RAZWWRC","onekgpd",null,"Queries the 1000 Genomes Project dataset (3,202 whole-genome-sequenced individuals, GRCh38) at the level of individual participants. Use when a question is about individuals or variants in the 1000 Genomes Project cohort: which individuals carry variants matching specific criteria in a gene or region, which individuals are homozygous-reference at a position, which variants exist in the dataset or carried by specified individuals in a gene or region, the relatedness between two specified individuals. Variants are returned with 1000 Genomes allele frequencies (AF), gnomAD v4.1 exome and genome AF, AlphaMissense score, and HGVSp annotations.","beanspowt\u002Fbeancode","beanspowt","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F333943283?v=4","01M7F39F0GDWKS57BCKW8JJH7F","01M7F39F1B1TVPDJMS37BZQHWM",0,"MIT","https:\u002F\u002Fgithub.com\u002Fbeanspowt\u002Fbeancode\u002Fblob\u002Fmain\u002Fhermes\u002Fprofiles\u002Fworker-research\u002Fskills\u002Fonekgpd\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: onekgpd\ndescription: >\n  Queries the 1000 Genomes Project dataset (3,202 whole-genome-sequenced\n  individuals, GRCh38) at the level of individual participants.\n  Use when a question is about individuals or variants in the 1000 Genomes\n  Project cohort: which individuals carry variants matching specific criteria\n  in a gene or region, which individuals are homozygous-reference at a position,\n  which variants exist in the dataset or carried by specified individuals\n  in a gene or region, the relatedness between two specified individuals.\n  Variants are returned with 1000 Genomes allele frequencies (AF),\n  gnomAD v4.1 exome and genome AF, AlphaMissense score, and HGVSp annotations.\nlicense: MIT\ncompatibility: Requires Python >=3.11. Variant and sample queries require outbound network access to the public 1000 Genomes query endpoint over TLS; the sample\u002Fpopulation metadata commands run fully offline over a data file bundled in the skill. No credentials, API keys, or environment variables are used.\nallowed-tools: Write Bash\nmetadata:\n  version: \"1.4\"\n  last-reviewed: \"2026-09-30\"\n  upstream-version: \"dnaerys 0.2.1; proto R1.20.0\"\n  skill-author: Dnaerys\n---\n\n# OneKGPd: Individual-Level Queries over the 1000 Genomes Project\n\n## Scope\n\nThis skill queries the 1000 Genomes Project dataset — the extended high-coverage cohort\nof 3,202 whole-genome-sequenced individuals, on the GRCh38 assembly. All results\nare drawn from this cohort, and sample names returned by the skill (for example\n`HG00096` or `NA21130`) identify its participants.\n\nQueries resolve against the cohort's per-individual genotype data. This supports\ntwo complementary classes of question: selecting **variants** carried within a\nregion (across the whole cohort or within a specified set of individuals), and\nselecting the **individuals** who carry variants matching given criteria.\nVariant selection can be filtered by allele frequency, predicted consequence,\nclinical significance, AlphaMissense classification, and the other annotation\naxes listed below. Relatedness between two named individuals is also available.\n\nThe genotype state in which a variant is carried — heterozygous or homozygous —\nis a criterion that queries may specify; results are returned as variants or as\nsample names, not as raw genotypes.\n\nThe public service is **TLS gRPC at `db.dnaerys.org:443`**, accessed with\n`dnaerys 0.2.1` (Python 3.11+); it is not a REST base URL. The maintained\nservice snapshot advertises VEP 115 \u002F GENCODE 49, ClinVar 202502, and gnomAD\n4.1. These are the service's annotation releases, not the latest release of\neach upstream resource. Record them when interpreting results.\n\n## When to Use\n\n**Use this skill when you need to:**\n\n-   Find **variants** carried in a region or set of regions matching some criteria\n    across the whole cohort (`select-variants`).\n-   Find **variants** carried in a region or set of regions matching some criteria\n    in specific set of individuals (`select-variants-in-samples`).\n-   Find **which 1000 Genomes individuals** carry variants matching some criteria\n    in a region or set of regions (`select-samples`).\n-   Count how many individuals carry specific variants (`count-samples`).\n-   Restrict any variant query to **heterozygous-only or homozygous-only**\n    carriage, or query both together (default).\n-   Identify which individuals are **homozygous reference** at a single position\n    (`select-samples-hom-ref`).\n-   Determine the **relatedness** between two named 1000 Genomes individuals —\n    both the degree (twin \u002F 1st \u002F 2nd \u002F 3rd \u002F unrelated) and the KING kinship\n    coefficient (`kinship`).\n-   Get **dataset totals** — sample count, sex split, variant count, assembly\n    (`dataset-info`).\n-   Variant selection can be specified by KGP allele frequency, gnomAD 4.1 exome and\n    gnomAD 4.1 genome allele frequency, AlphaMissense Score and AlphaMissense Class,\n    ClinVar significance (202502), and VEP annotations (impact, biotype, feature type,\n    variant class, consequences).\n\n**Do NOT use this skill for:**\n\n-   Resolving a gene symbol, rsID, or transcript to coordinates, or fetching\n    reference sequence. Resolve coordinates first (see Coordinate Provenance\n    below), then query this skill with the resolved GRCh38 region.\n-   Any cohort other than the 1000 Genomes Project — this skill serves only that\n    dataset.\n\n## Prerequisites\n\n1.  **`uv`**: This skill's script is run with `uv run`, which reads the script's\n    inline dependency metadata and provisions an ephemeral environment. Ensure\n    `uv` is installed and on PATH (https:\u002F\u002Fdocs.astral.sh\u002Fuv\u002F).\n2.  **Data use terms**: The 1000 Genomes Project data is open; users should be\n    aware of the 1000 Genomes Project \u002F IGSR data-use terms\n    (https:\u002F\u002Fwww.internationalgenome.org\u002Fdata).\n3.  **Access constraints**: There is no API key, no `.env` file, and no\n    rate-limit token to configure.\n4.  **Timeouts**: network commands use `--timeout 30` seconds per RPC by default.\n    A positive finite override is allowed. Pagination makes several RPCs and\n    retryable failures retry the whole fetch up to three times, so this is not\n    a deadline for the whole command.\n\n## Core Rules\n\n-   **Use the Wrappers**: ALWAYS execute the provided helper scripts rather than\n    constructing your own client calls or network requests. Use\n    `scripts\u002Fonekgpd_api.py` for variant\u002Fsample\u002Fkinship queries (it handles the\n    connection, streaming, pagination, and JSON serialization), and\n    `scripts\u002Fonekgpd_meta.py` for sample\u002Fpopulation metadata (offline, see\n    [Sample & population metadata](#sample--population-metadata-offline)).\n-   **Coordinates MUST be resolved against an authoritative source first** — see\n    [Coordinate Provenance](#coordinate-provenance-mandatory-first-step). This\n    is mandatory, not advisory.\n-   **Count before you select**: every variant and sample selection has a paired\n    counting command. Call the count command FIRST to size the result set, then\n    select only if the count is manageable.\n-   **Zygosity defaults to both**: selection and counting commands include both\n    heterozygous and homozygous carriage by default. Narrow with `--het-only`\n    or `--hom-only` when the question is specifically about one state. (You do\n    not need to pass anything to get both.)\n-   **Output**: scripts write full JSON to a file (`--output`, default under\n    `\u002Ftmp\u002F`) and print a concise summary to stdout. Do not read large JSON files\n    into context — use `jq` or a small disposable `uv run python` snippet to\n    extract fields. `--page-size` retrieves every page but accumulates all\n    variants in RAM; it is not a bounded-memory export. Size the query first.\n-   **Check completeness**: `result_incomplete=true` means results cannot support\n    a definitive zero\u002Fabsence claim. Re-run after service recovery. For capped\n    variant selections, `truncated=true` means the limit was reached and more\n    records may exist, even if the cluster result itself was complete.\n\n## Coordinate Provenance (MANDATORY FIRST STEP)\n\nBefore any region-based query, resolve the gene or feature to **GRCh38**\ncoordinates against an authoritative source (for example Ensembl or NCBI), and query\nwith those resolved coordinates. Inputs are **1-based, inclusive**: a BED interval\n`[start0, end0)` becomes `start=start0+1, end=end0`. Record the source accession,\nannotation release, and retrieval date; gene boundaries can differ by annotation\nrelease even on the same assembly. The assembly must be explicit, and a gene-range\nmust be resolved to precise positions before use. This is structural, not\nadvisory: there is no source-side guardrail that would catch a misplaced region,\nso an unverified coordinate produces results for an unintended location with no\nerror.\n\n```bash\n# Resolve gene symbol -> GRCh38 region with an authoritative source FIRST,\n# then pass the verified coordinates to the OneKGPd query below.\n```\n\n> [!CAUTION]\n> The dataset is GRCh38. A GRCh37 coordinate, or any region that does not\n> correctly correspond to the intended feature on GRCh38, will return\n> results for an unintended location without raising an error. Verify the\n> assembly and the resolved coordinates before querying.\n\n## Command Selection Guide\n\nMatch the question to the command. Counting commands are cheap and should\nprecede their selection counterpart.\n\n-   Which individuals carry matching variants in a region → `count-samples`\n    then `select-samples`\n-   Which variants are carried in a region, cohort-wide → `count-variants`\n    then `select-variants`\n-   Which variants are carried in a region, within a named set of individuals →\n    `count-variants-in-samples` then `select-variants-in-samples`\n-   Who is homozygous-reference at a single position → `count-samples-hom-ref`\n    then `select-samples-hom-ref`\n-   Relatedness (degree + coefficient) between two named individuals →\n    `kinship`\n-   Dataset totals (sample count, sex split, variant total, assembly) →\n    `dataset-info`\n\n## Cohort interpretation\n\nThe 3,202-sample cohort includes relatives: the additional 698 high-coverage\nsamples extend the original 2,504-sample panel. Carrier counts therefore are\nnot counts of independent observations, and cohort AF is not a population\nprevalence estimate. For association or frequency comparisons, document the\nselected populations and relatedness policy; use the bundled pedigree metadata\nand `kinship` when choosing or auditing the analysis set. See the\n[IGSR cohort announcement](https:\u002F\u002Fwww.internationalgenome.org\u002Fannouncements\u002F3202-samples-at-high-coverage-from-NYGC\u002F).\n\n## Annotation filters (shared across variant and sample selection\u002Fcounting)\n\nAll variant- and sample-selection commands (`count-variants`,\n`select-variants`, their `-in-samples` forms, `count-samples`, `select-samples`)\naccept the same annotation filters. Different filter fields are combined with\n**AND**; multiple values within one field are combined with **OR**. Enum values\nare case-insensitive (e.g. `missense_variant` or `MISSENSE_VARIANT`).\n\nThese are selection criteria applied on the server. The fields returned on a\nselected variant are listed under\n[Variant-returning commands](#variant-returning-commands); a criterion used for\nfiltering is not necessarily echoed back on the returned variant.\n\n-   `--af-lt` \u002F `--af-gt`: 1000 Genomes dataset allele frequency bounds\n-   `--gnomad-exomes-af-lt` \u002F `--gnomad-exomes-af-gt`: gnomAD v4.1 exome AF bounds\n-   `--gnomad-genomes-af-lt` \u002F `--gnomad-genomes-af-gt`: gnomAD v4.1 genome AF bounds\n-   `--clin-significance`: ClinVar significance terms, CSV (e.g. `PATHOGENIC,LIKELY_PATHOGENIC`)\n-   `--consequence`: Sequence Ontology consequence terms, CSV (e.g. `MISSENSE_VARIANT,STOP_GAINED`)\n-   `--impact`: VEP impact, CSV (`HIGH,MODERATE,LOW,MODIFIER`)\n-   `--variant-type`, `--feature-type`, `--bio-type`: SO variant class \u002F VEP feature \u002F VEP biotype, CSV\n-   `--alpha-missense-class`: `AM_LIKELY_BENIGN,AM_LIKELY_PATHOGENIC,AM_AMBIGUOUS` (CSV)\n-   `--alpha-missense-score-lt` \u002F `--alpha-missense-score-gt`: AlphaMissense score bounds\n-   `--biallelic-only` \u002F `--multiallelic-only`\n-   `--exclude-males` \u002F `--exclude-females`\n-   `--min-len-bp` \u002F `--max-len-bp`: alternate-allele length bounds (bp)\n\n> [!NOTE]\n> `--alpha-missense-class` and `--alpha-missense-score-*` are mutually exclusive\n> (the engine ignores the class when a score bound is set). `--biallelic-only`\n> and `--multiallelic-only` are mutually exclusive. `--exclude-males` and\n> `--exclude-females` are mutually exclusive. Setting a `*-gt` bound greater than\n> or equal to its matching `*-lt` bound defines an empty range and will return\n> nothing.\n\n> [!NOTE]\n> `gnomad_exomes_af`, `gnomad_genomes_af`, and `am_score` use `0.0` for\n> **not annotated in this service snapshot**. This does not establish absence\n> from the current gnomAD release, biological rarity, or a benign prediction.\n> The dataset's own `af` field is a different statistic, not this sentinel.\n\n> [!CAUTION]\n> **A zero numeric filter is unset on the server**, so `--gnomad-exomes-af-gt 0`\n> does not exclude missing annotations. The wrapper rejects zero, nonfinite,\n> out-of-range, and float32-underflowing bounds. Choose an explicit positive\n> threshold (for example `--gnomad-exomes-af-gt 0.000001` means AF > 1e-6,\n> not merely annotation presence). For exact `> 0`, retrieve a complete variant\n> set and post-filter the returned AF locally. A `\u003C X` filter alone includes\n> unannotated zero values. Apply the same missing-score caution to AlphaMissense.\n\nCategorical annotations are retained across transcripts. Combining consequence\nand impact filters does not establish that they describe the same transcript.\n`amino_acids` may contain multiple HGVSp entries; the generic gRPC service places\ncanonical annotations first, whereas the separate MCP layer trims its output.\nPreserve transcript identifiers, and do not treat a model's likely-pathogenic\nclass as a clinical diagnosis or a participant phenotype.\n\n## Quick Start\n\n```bash\n# Step 1. NCBI Gene 672, GRCh38.p14 \u002F NC_000017.11, RS_2025_08:\n# BRCA1 spans chr17:43044295-43170327 (1-based inclusive).\n# Source: https:\u002F\u002Fwww.ncbi.nlm.nih.gov\u002Fgene\u002F672 ; re-resolve for your analysis.\n# Step 2. Size the result set: how many individuals carry predicted likely-pathogenic\n#    missense variants in this region?\nuv run scripts\u002Fonekgpd_api.py count-samples \\\n  --chrom chr17 --start 43044295 --end 43170327 \\\n  --consequence MISSENSE_VARIANT \\\n  --alpha-missense-class AM_LIKELY_PATHOGENIC \\\n  --output \u002Ftmp\u002Fcount.json\n# Step 3. If the count is manageable, list those individuals.\nuv run scripts\u002Fonekgpd_api.py select-samples \\\n  --chrom chr17 --start 43044295 --end 43170327 \\\n  --consequence MISSENSE_VARIANT \\\n  --alpha-missense-class AM_LIKELY_PATHOGENIC \\\n  --output \u002Ftmp\u002Fsamples.json\n# Step 4. Count then select variants for actual returned sample IDs.\n# HG03169,NA20506 below are illustrative IDs; substitute the Step 3 results.\nuv run scripts\u002Fonekgpd_api.py count-variants-in-samples \\\n  --chrom chr17 --start 43044295 --end 43170327 \\\n  --samples HG03169,NA20506 \\\n  --consequence MISSENSE_VARIANT --alpha-missense-class AM_LIKELY_PATHOGENIC \\\n  --output \u002Ftmp\u002Fvariant_count.json\nuv run scripts\u002Fonekgpd_api.py select-variants-in-samples \\\n  --chrom chr17 --start 43044295 --end 43170327 \\\n  --samples HG03169,NA20506 \\\n  --consequence MISSENSE_VARIANT --alpha-missense-class AM_LIKELY_PATHOGENIC \\\n  --output \u002Ftmp\u002Fvariants.json\n```\n\n## Commands\n\nEach command writes full JSON to a file (`--output PATH`, default a temp file)\nand prints a concise stdout summary. All region\u002Fsample commands share: the\nregion input (`--chrom`\u002F`--start`\u002F`--end` with optional `--ref`\u002F`--alt`, or one\nor more repeated `--region CHR:START-END`), the zygosity flags\n(`--het-only`\u002F`--hom-only`, default both), and the annotation filters above.\nThe full per-flag tables live in\n[references\u002Fonekgpd_commands.md](references\u002Fonekgpd_commands.md).\n\n### Variant-returning commands\n\n`select-*` return matching variants; `count-*` return an integer count.\n\n-   `count-variants` — count variants in a region, cohort-wide.\n-   `select-variants` — select variants in a region, cohort-wide. Use `--limit N`\n    (hard cap, default 200) **or** `--page-size N` (retrieve the full set in\n    pages); the two are mutually exclusive. The summary flags `truncated` when\n    the cap is reached.\n-   `count-variants-in-samples` — as `count-variants`, restricted to\n    `--samples NAME1,NAME2,...` (required).\n-   `select-variants-in-samples` — as `select-variants`, restricted to\n    `--samples NAME1,NAME2,...` (required).\n\nEach returned variant carries these 22 keys: `chr`, `start`, `end`, `ref`,\n`alt`, `af`, `ac`, `an`, `hom_samples`, `het_samples`, `mis_samples`,\n`hom_samples_fx`, `het_samples_fx`, `mis_samples_fx`, `hom_samples_mxy`,\n`het_samples_mxy`, `mis_samples_mxy`, `gnomad_exomes_af`, `gnomad_genomes_af`,\n`am_score`, `amino_acids`, `biallelic`.\nClinVar significance and VEP consequence are filter criteria only and are not\nreturned. Full schema:\n[references\u002Fonekgpd_commands.md](references\u002Fonekgpd_commands.md).\n\n### Sample-returning commands\n\n-   `count-samples` — count individuals carrying a matching variant in a region.\n-   `select-samples` — list the names of individuals carrying a matching variant.\n    Supports `--skip N` and `--limit N`. Returns names only; to see which\n    variants qualified an individual, feed the names into\n    `select-variants-in-samples`.\n\n### Homozygous-reference commands\n\nSingle position via `--chrom` + `--position` (not a region).\n\n-   `count-samples-hom-ref` — count individuals with a 0\u002F0 call at the position.\n    The count uses a sentinel: `-1` = no variant exists at that position at all;\n    `0` = a variant exists but no individual is homozygous reference; `>0` = the\n    number of homozygous-reference individuals. These interpretations require\n    `result_incomplete=false`; otherwise `variant_present` is `null`. No variant\n    record is not evidence that all 3,202 individuals have callable 0\u002F0 genotypes.\n-   `select-samples-hom-ref` — list the individuals with a 0\u002F0 call at the position.\n\n### Relatedness command\n\n-   `kinship --sample1 NAME --sample2 NAME` — relatedness between two named\n    individuals: the degree (`TWINS_MONOZYGOTIC` \u002F `FIRST_DEGREE` \u002F\n    `SECOND_DEGREE` \u002F `THIRD_DEGREE` \u002F `UNRELATED`) and the KING kinship\n    coefficient (`phi_bwf`).\n\n### Dataset metadata command\n\n-   `dataset-info` — dataset totals: `samples_total` (3,202), female\u002Fmale split,\n    `variants_total`, `assembly` (GRCh38), and the cohort breakdown. No region\n    required; doubles as a connectivity check.\n\n## Sample & population metadata (offline)\n\nPopulation, sex, pedigree, and superpopulation questions are answered by a second\nscript, `scripts\u002Fonekgpd_meta.py`, from a data file bundled in the skill — **no\nnetwork, no credentials, no coordinates**. The sample IDs are the same names the\nvariant commands use, so the two layers compose (e.g. pick a cohort by population,\nthen query its variants). Run `uv run scripts\u002Fonekgpd_meta.py \u003Ccommand>`.\n\nThe cohort has 5 superpopulations (`AFR`, `AMR`, `EAS`, `EUR`, `SAS`) and 26\npopulations. Population\u002Fsuperpopulation values match **case-insensitively** by\nshort code or full name; **sample IDs are case-sensitive**.\n\n-   `sample-metadata --samples NA19240,HG00096` — family, gender, parents,\n    children, population, superpopulation, and phase3 status for the given samples.\n-   `list-populations` — all 26 populations with superpopulation and sample count\n    (use to discover valid values).\n-   `list-superpopulations` — the 5 superpopulations with sample count and\n    constituent populations.\n-   `population-stats --populations YRI [--populations CHS …]` — per-population sex\n    split, phase3 count, and trio membership. Repeat `--populations` for multiple\n    values (full names contain commas, so they are not comma-separated).\n-   `superpopulation-summary --superpopulations EAS [--superpopulations EUR …]` —\n    per-superpopulation totals with a per-population breakdown.\n-   `select-samples-by-population --population YRI` and\u002For `--superpopulation AFR`,\n    with optional `--skip`\u002F`--limit` (default 0 \u002F 50, max 3202) — the sample IDs in\n    a population and\u002For superpopulation; both given intersects. Feed the names into\n    `select-variants-in-samples` to see their variants.\n\nSee [references\u002Fonekgpd_commands.md](references\u002Fonekgpd_commands.md) for full\nargument tables and JSON output schemas.\n\n## Typical Workflows\n\n### Which individuals, then which variants they carry\n\nThe following is an illustrative template; replace all angle-bracket placeholders.\n\n```bash\n# Step 1: resolve gene -> verified GRCh38 region (authoritative source).\n# Step 2: count individuals carrying a qualifying variant in the region.\nuv run scripts\u002Fonekgpd_api.py count-samples \\\n  --chrom \u003Cchr> --start \u003Cstart> --end \u003Cend> \\\n  --consequence MISSENSE_VARIANT --alpha-missense-class AM_LIKELY_PATHOGENIC \\\n  --output \u002Ftmp\u002Fn.json\n# Step 3: list those individuals.\nuv run scripts\u002Fonekgpd_api.py select-samples \\\n  --chrom \u003Cchr> --start \u003Cstart> --end \u003Cend> \\\n  --consequence MISSENSE_VARIANT --alpha-missense-class AM_LIKELY_PATHOGENIC \\\n  --output \u002Ftmp\u002Fwho.json\n# Step 4: count variants for those individuals before selecting.\nuv run scripts\u002Fonekgpd_api.py count-variants-in-samples \\\n  --chrom \u003Cchr> --start \u003Cstart> --end \u003Cend> \\\n  --samples \u003Cname1,name2,...> \\\n  --consequence MISSENSE_VARIANT --alpha-missense-class AM_LIKELY_PATHOGENIC \\\n  --output \u002Ftmp\u002Fvariant_count.json\nuv run scripts\u002Fonekgpd_api.py select-variants-in-samples \\\n  --chrom \u003Cchr> --start \u003Cstart> --end \u003Cend> \\\n  --samples \u003Cname1,name2,...> \\\n  --consequence MISSENSE_VARIANT --alpha-missense-class AM_LIKELY_PATHOGENIC \\\n  --output \u002Ftmp\u002Fvariants.json\n```\n\n### Homozygous-reference carriers at a position of interest\n\nIllustrative template; replace the placeholders with verified coordinates.\n\n```bash\n# After identifying a position of interest (verified coordinate):\nuv run scripts\u002Fonekgpd_api.py count-samples-hom-ref \\\n  --chrom \u003Cchr> --position \u003Cpos> --output \u002Ftmp\u002Fhomref_n.json\nuv run scripts\u002Fonekgpd_api.py select-samples-hom-ref \\\n  --chrom \u003Cchr> --position \u003Cpos> --output \u002Ftmp\u002Fhomref.json\n```\n\n## Common Mistakes\n\n-   **Mistake:** Querying with an unverified coordinate.\n    **Fix:** Always resolve gene\u002Ffeature → GRCh38 against an authoritative\n    source first.\n    A misplaced region returns results for an unintended location without error.\n-   **Mistake:** Calling a selection command before its counting command.\n    **Fix:** Count first; selection result sets can be large.\n-   **Mistake:** Assuming a GRCh37 coordinate will work.\n    **Fix:** The dataset is GRCh38 only.\n\n## References\n\n-   [references\u002Fonekgpd_commands.md](references\u002Fonekgpd_commands.md) — full\n    per-command argument tables and the returned-variant output schema.\n-   [references\u002Fannotation_vocabularies.md](references\u002Fannotation_vocabularies.md)\n    — the controlled-vocabulary terms accepted by the CSV filter flags\n    (consequence, impact, biotype, feature type, ClinVar significance,\n    AlphaMissense class, variant class).\n-   Current API contract and live-check scope: the\n    [command reference](references\u002Fonekgpd_commands.md#verified-api-contract).\n-   1000 Genomes Project \u002F IGSR: https:\u002F\u002Fwww.internationalgenome.org\u002F\n-   1000 Genomes Project dataset online: https:\u002F\u002Fdnaerys.org\u002Fonline\u002F\n","# OneKGPd: Individual-Level Queries over the 1000 Genomes Project\n\n## Scope\n\nThis skill queries the 1000 Genomes Project dataset — the extended high-coverage cohort\nof 3,202 whole-genome-sequenced individuals, on the GRCh38 assembly. All results\nare drawn from this cohort, and sample names returned by the skill (for example\n`HG00096` or `NA21130`) identify its participants.\n\nQueries resolve against the cohort's per-individual genotype data. This supports\ntwo complementary classes of question: selecting **variants** carried within a\nregion (across the whole cohort or within a specified set of individuals), and\nselecting the **individuals** who carry variants matching given criteria.\nVariant selection can be filtered by allele frequency, predicted consequence,\nclinical significance, AlphaMissense classification, and the other annotation\naxes listed below. Relatedness between two named individuals is also available.\n\nThe genotype state in which a variant is carried — heterozygous or homozygous —\nis a criterion that queries may specify; results are returned as variants or as\nsample names, not as raw genotypes.\n\nThe public service is **TLS gRPC at `db.dnaerys.org:443`**, accessed with\n`dnaerys 0.2.1` (Python 3.11+); it is not a REST base URL. The maintained\nservice snapshot advertises VEP 115 \u002F GENCODE 49, ClinVar 202502, and gnomAD\n4.1. These are the service's annotation releases, not the latest release of\neach upstream resource. Record them when interpreting results.\n\n## When to Use\n\n**Use this skill when you need to:**\n\n-   Find **variants** carried in a region or set of regions matching some criteria\n    across the whole cohort (`select-variants`).\n-   Find **variants** carried in a region or set of regions matching some criteria\n    in specific set of individuals (`select-variants-in-samples`).\n-   Find **which 1000 Genomes individuals** carry variants matching some criteria\n    in a region or set of regions (`select-samples`).\n-   Count how many individuals carry specific variants (`count-samples`).\n-   Restrict any variant query to **heterozygous-only or homozygous-only**\n    carriage, or query both together (default).\n-   Identify which individuals are **homozygous reference** at a single position\n    (`select-samples-hom-ref`).\n-   Determine the **relatedness** between two named 1000 Genomes individuals —\n    both the degree (twin \u002F 1st \u002F 2nd \u002F 3rd \u002F unrelated) and the KING kinship\n    coefficient (`kinship`).\n-   Get **dataset totals** — sample count, sex split, variant count, assembly\n    (`dataset-info`).\n-   Variant selection can be specified by KGP allele frequency, gnomAD 4.1 exome and\n    gnomAD 4.1 genome allele frequency, AlphaMissense Score and AlphaMissense Class,\n    ClinVar significance (202502), and VEP annotations (impact, biotype, feature type,\n    variant class, consequences).\n\n**Do NOT use this skill for:**\n\n-   Resolving a gene symbol, rsID, or transcript to coordinates, or fetching\n    reference sequence. Resolve coordinates first (see Coordinate Provenance\n    below), then query this skill with the resolved GRCh38 region.\n-   Any cohort other than the 1000 Genomes Project — this skill serves only that\n    dataset.\n\n## Prerequisites\n\n1.  **`uv`**: This skill's script is run with `uv run`, which reads the script's\n    inline dependency metadata and provisions an ephemeral environment. Ensure\n    `uv` is installed and on PATH (https:\u002F\u002Fdocs.astral.sh\u002Fuv\u002F).\n2.  **Data use terms**: The 1000 Genomes Project data is open; users should be\n    aware of the 1000 Genomes Project \u002F IGSR data-use terms\n    (https:\u002F\u002Fwww.internationalgenome.org\u002Fdata).\n3.  **Access constraints**: There is no API key, no `.env` file, and no\n    rate-limit token to configure.\n4.  **Timeouts**: network commands use `--timeout 30` seconds per RPC by default.\n    A positive finite override is allowed. Pagination makes several RPCs and\n    retryable failures retry the whole fetch up to three times, so this is not\n    a deadline for the whole command.\n\n## Core Rules\n\n-   **Use the Wrappers**: ALWAYS execute the provided helper scripts rather than\n    constructing your own client calls or network requests. Use\n    `scripts\u002Fonekgpd_api.py` for variant\u002Fsample\u002Fkinship queries (it handles the\n    connection, streaming, pagination, and JSON serialization), and\n    `scripts\u002Fonekgpd_meta.py` for sample\u002Fpopulation metadata (offline, see\n    [Sample & population metadata](#sample--population-metadata-offline)).\n-   **Coordinates MUST be resolved against an authoritative source first** — see\n    [Coordinate Provenance](#coordinate-provenance-mandatory-first-step). This\n    is mandatory, not advisory.\n-   **Count before you select**: every variant and sample selection has a paired\n    counting command. Call the count command FIRST to size the result set, then\n    select only if the count is manageable.\n-   **Zygosity defaults to both**: selection and counting commands include both\n    heterozygous and homozygous carriage by default. Narrow with `--het-only`\n    or `--hom-only` when the question is specifically about one state. (You do\n    not need to pass anything to get both.)\n-   **Output**: scripts write full JSON to a file (`--output`, default under\n    `\u002Ftmp\u002F`) and print a concise summary to stdout. Do not read large JSON files\n    into context — use `jq` or a small disposable `uv run python` snippet to\n    extract fields. `--page-size` retrieves every page but accumulates all\n    variants in RAM; it is not a bounded-memory export. Size the query first.\n-   **Check completeness**: `result_incomplete=true` means results cannot support\n    a definitive zero\u002Fabsence claim. Re-run after service recovery. For capped\n    variant selections, `truncated=true` means the limit was reached and more\n    records may exist, even if the cluster result itself was complete.\n\n## Coordinate Provenance (MANDATORY FIRST STEP)\n\nBefore any region-based query, resolve the gene or feature to **GRCh38**\ncoordinates against an authoritative source (for example Ensembl or NCBI), and query\nwith those resolved coordinates. Inputs are **1-based, inclusive**: a BED interval\n`[start0, end0)` becomes `start=start0+1, end=end0`. Record the source accession,\nannotation release, and retrieval date; gene boundaries can differ by annotation\nrelease even on the same assembly. The assembly must be explicit, and a gene-range\nmust be resolved to precise positions before use. This is structural, not\nadvisory: there is no source-side guardrail that would catch a misplaced region,\nso an unverified coordinate produces results for an unintended location with no\nerror.\n\n```bash\n# Resolve gene symbol -> GRCh38 region with an authoritative source FIRST,\n# then pass the verified coordinates to the OneKGPd query below.\n```\n\n> [!CAUTION]\n> The dataset is GRCh38. A GRCh37 coordinate, or any region that does not\n> correctly correspond to the intended feature on GRCh38, will return\n> results for an unintended location without raising an error. Verify the\n> assembly and the resolved coordinates before querying.\n\n## Command Selection Guide\n\nMatch the question to the command. Counting commands are cheap and should\nprecede their selection counterpart.\n\n-   Which individuals carry matching variants in a region → `count-samples`\n    then `select-samples`\n-   Which variants are carried in a region, cohort-wide → `count-variants`\n    then `select-variants`\n-   Which variants are carried in a region, within a named set of individuals →\n    `count-variants-in-samples` then `select-variants-in-samples`\n-   Who is homozygous-reference at a single position → `count-samples-hom-ref`\n    then `select-samples-hom-ref`\n-   Relatedness (degree + coefficient) between two named individuals →\n    `kinship`\n-   Dataset totals (sample count, sex split, variant total, assembly) →\n    `dataset-info`\n\n## Cohort interpretation\n\nThe 3,202-sample cohort includes relatives: the additional 698 high-coverage\nsamples extend the original 2,504-sample panel. Carrier counts therefore are\nnot counts of independent observations, and cohort AF is not a population\nprevalence estimate. For association or frequency comparisons, document the\nselected populations and relatedness policy; use the bundled pedigree metadata\nand `kinship` when choosing or auditing the analysis set. See the\n[IGSR cohort announcement](https:\u002F\u002Fwww.internationalgenome.org\u002Fannouncements\u002F3202-samples-at-high-coverage-from-NYGC\u002F).\n\n## Annotation filters (shared across variant and sample selection\u002Fcounting)\n\nAll variant- and sample-selection commands (`count-variants`,\n`select-variants`, their `-in-samples` forms, `count-samples`, `select-samples`)\naccept the same annotation filters. Different filter fields are combined with\n**AND**; multiple values within one field are combined with **OR**. Enum values\nare case-insensitive (e.g. `missense_variant` or `MISSENSE_VARIANT`).\n\nThese are selection criteria applied on the server. The fields returned on a\nselected variant are listed under\n[Variant-returning commands](#variant-returning-commands); a criterion used for\nfiltering is not necessarily echoed back on the returned variant.\n\n-   `--af-lt` \u002F `--af-gt`: 1000 Genomes dataset allele frequency bounds\n-   `--gnomad-exomes-af-lt` \u002F `--gnomad-exomes-af-gt`: gnomAD v4.1 exome AF bounds\n-   `--gnomad-genomes-af-lt` \u002F `--gnomad-genomes-af-gt`: gnomAD v4.1 genome AF bounds\n-   `--clin-significance`: ClinVar significance terms, CSV (e.g. `PATHOGENIC,LIKELY_PATHOGENIC`)\n-   `--consequence`: Sequence Ontology consequence terms, CSV (e.g. `MISSENSE_VARIANT,STOP_GAINED`)\n-   `--impact`: VEP impact, CSV (`HIGH,MODERATE,LOW,MODIFIER`)\n-   `--variant-type`, `--feature-type`, `--bio-type`: SO variant class \u002F VEP feature \u002F VEP biotype, CSV\n-   `--alpha-missense-class`: `AM_LIKELY_BENIGN,AM_LIKELY_PATHOGENIC,AM_AMBIGUOUS` (CSV)\n-   `--alpha-missense-score-lt` \u002F `--alpha-missense-score-gt`: AlphaMissense score bounds\n-   `--biallelic-only` \u002F `--multiallelic-only`\n-   `--exclude-males` \u002F `--exclude-females`\n-   `--min-len-bp` \u002F `--max-len-bp`: alternate-allele length bounds (bp)\n\n> [!NOTE]\n> `--alpha-missense-class` and `--alpha-missense-score-*` are mutually exclusive\n> (the engine ignores the class when a score bound is set). `--biallelic-only`\n> and `--multiallelic-only` are mutually exclusive. `--exclude-males` and\n> `--exclude-females` are mutually exclusive. Setting a `*-gt` bound greater than\n> or equal to its matching `*-lt` bound defines an empty range and will return\n> nothing.\n\n> [!NOTE]\n> `gnomad_exomes_af`, `gnomad_genomes_af`, and `am_score` use `0.0` for\n> **not annotated in this service snapshot**. This does not establish absence\n> from the current gnomAD release, biological rarity, or a benign prediction.\n> The dataset's own `af` field is a different statistic, not this sentinel.\n\n> [!CAUTION]\n> **A zero numeric filter is unset on the server**, so `--gnomad-exomes-af-gt 0`\n> does not exclude missing annotations. The wrapper rejects zero, nonfinite,\n> out-of-range, and float32-underflowing bounds. Choose an explicit positive\n> threshold (for example `--gnomad-exomes-af-gt 0.000001` means AF > 1e-6,\n> not merely annotation presence). For exact `> 0`, retrieve a complete variant\n> set and post-filter the returned AF locally. A `\u003C X` filter alone includes\n> unannotated zero values. Apply the same missing-score caution to AlphaMissense.\n\nCategorical annotations are retained across transcripts. Combining consequence\nand impact filters does not establish that they describe the same transcript.\n`amino_acids` may contain multiple HGVSp entries; the generic gRPC service places\ncanonical annotations first, whereas the separate MCP layer trims its output.\nPreserve transcript identifiers, and do not treat a model's likely-pathogenic\nclass as a clinical diagnosis or a participant phenotype.\n\n## Quick Start\n\n```bash\n# Step 1. NCBI Gene 672, GRCh38.p14 \u002F NC_000017.11, RS_2025_08:\n# BRCA1 spans chr17:43044295-43170327 (1-based inclusive).\n# Source: https:\u002F\u002Fwww.ncbi.nlm.nih.gov\u002Fgene\u002F672 ; re-resolve for your analysis.\n# Step 2. Size the result set: how many individuals carry predicted likely-pathogenic\n#    missense variants in this region?\nuv run scripts\u002Fonekgpd_api.py count-samples \\\n  --chrom chr17 --start 43044295 --end 43170327 \\\n  --consequence MISSENSE_VARIANT \\\n  --alpha-missense-class AM_LIKELY_PATHOGENIC \\\n  --output \u002Ftmp\u002Fcount.json\n# Step 3. If the count is manageable, list those individuals.\nuv run scripts\u002Fonekgpd_api.py select-samples \\\n  --chrom chr17 --start 43044295 --end 43170327 \\\n  --consequence MISSENSE_VARIANT \\\n  --alpha-missense-class AM_LIKELY_PATHOGENIC \\\n  --output \u002Ftmp\u002Fsamples.json\n# Step 4. Count then select variants for actual returned sample IDs.\n# HG03169,NA20506 below are illustrative IDs; substitute the Step 3 results.\nuv run scripts\u002Fonekgpd_api.py count-variants-in-samples \\\n  --chrom chr17 --start 43044295 --end 43170327 \\\n  --samples HG03169,NA20506 \\\n  --consequence MISSENSE_VARIANT --alpha-missense-class AM_LIKELY_PATHOGENIC \\\n  --output \u002Ftmp\u002Fvariant_count.json\nuv run scripts\u002Fonekgpd_api.py select-variants-in-samples \\\n  --chrom chr17 --start 43044295 --end 43170327 \\\n  --samples HG03169,NA20506 \\\n  --consequence MISSENSE_VARIANT --alpha-missense-class AM_LIKELY_PATHOGENIC \\\n  --output \u002Ftmp\u002Fvariants.json\n```\n\n## Commands\n\nEach command writes full JSON to a file (`--output PATH`, default a temp file)\nand prints a concise stdout summary. All region\u002Fsample commands share: the\nregion input (`--chrom`\u002F`--start`\u002F`--end` with optional `--ref`\u002F`--alt`, or one\nor more repeated `--region CHR:START-END`), the zygosity flags\n(`--het-only`\u002F`--hom-only`, default both), and the annotation filters above.\nThe full per-flag tables live in\n[references\u002Fonekgpd_commands.md](references\u002Fonekgpd_commands.md).\n\n### Variant-returning commands\n\n`select-*` return matching variants; `count-*` return an integer count.\n\n-   `count-variants` — count variants in a region, cohort-wide.\n-   `select-variants` — select variants in a region, cohort-wide. Use `--limit N`\n    (hard cap, default 200) **or** `--page-size N` (retrieve the full set in\n    pages); the two are mutually exclusive. The summary flags `truncated` when\n    the cap is reached.\n-   `count-variants-in-samples` — as `count-variants`, restricted to\n    `--samples NAME1,NAME2,...` (required).\n-   `select-variants-in-samples` — as `select-variants`, restricted to\n    `--samples NAME1,NAME2,...` (required).\n\nEach returned variant carries these 22 keys: `chr`, `start`, `end`, `ref`,\n`alt`, `af`, `ac`, `an`, `hom_samples`, `het_samples`, `mis_samples`,\n`hom_samples_fx`, `het_samples_fx`, `mis_samples_fx`, `hom_samples_mxy`,\n`het_samples_mxy`, `mis_samples_mxy`, `gnomad_exomes_af`, `gnomad_genomes_af`,\n`am_score`, `amino_acids`, `biallelic`.\nClinVar significance and VEP consequence are filter criteria only and are not\nreturned. Full schema:\n[references\u002Fonekgpd_commands.md](references\u002Fonekgpd_commands.md).\n\n### Sample-returning commands\n\n-   `count-samples` — count individuals carrying a matching variant in a region.\n-   `select-samples` — list the names of individuals carrying a matching variant.\n    Supports `--skip N` and `--limit N`. Returns names only; to see which\n    variants qualified an individual, feed the names into\n    `select-variants-in-samples`.\n\n### Homozygous-reference commands\n\nSingle position via `--chrom` + `--position` (not a region).\n\n-   `count-samples-hom-ref` — count individuals with a 0\u002F0 call at the position.\n    The count uses a sentinel: `-1` = no variant exists at that position at all;\n    `0` = a variant exists but no individual is homozygous reference; `>0` = the\n    number of homozygous-reference individuals. These interpretations require\n    `result_incomplete=false`; otherwise `variant_present` is `null`. No variant\n    record is not evidence that all 3,202 individuals have callable 0\u002F0 genotypes.\n-   `select-samples-hom-ref` — list the individuals with a 0\u002F0 call at the position.\n\n### Relatedness command\n\n-   `kinship --sample1 NAME --sample2 NAME` — relatedness between two named\n    individuals: the degree (`TWINS_MONOZYGOTIC` \u002F `FIRST_DEGREE` \u002F\n    `SECOND_DEGREE` \u002F `THIRD_DEGREE` \u002F `UNRELATED`) and the KING kinship\n    coefficient (`phi_bwf`).\n\n### Dataset metadata command\n\n-   `dataset-info` — dataset totals: `samples_total` (3,202), female\u002Fmale split,\n    `variants_total`, `assembly` (GRCh38), and the cohort breakdown. No region\n    required; doubles as a connectivity check.\n\n## Sample & population metadata (offline)\n\nPopulation, sex, pedigree, and superpopulation questions are answered by a second\nscript, `scripts\u002Fonekgpd_meta.py`, from a data file bundled in the skill — **no\nnetwork, no credentials, no coordinates**. The sample IDs are the same names the\nvariant commands use, so the two layers compose (e.g. pick a cohort by population,\nthen query its variants). Run `uv run scripts\u002Fonekgpd_meta.py \u003Ccommand>`.\n\nThe cohort has 5 superpopulations (`AFR`, `AMR`, `EAS`, `EUR`, `SAS`) and 26\npopulations. Population\u002Fsuperpopulation values match **case-insensitively** by\nshort code or full name; **sample IDs are case-sensitive**.\n\n-   `sample-metadata --samples NA19240,HG00096` — family, gender, parents,\n    children, population, superpopulation, and phase3 status for the given samples.\n-   `list-populations` — all 26 populations with superpopulation and sample count\n    (use to discover valid values).\n-   `list-superpopulations` — the 5 superpopulations with sample count and\n    constituent populations.\n-   `population-stats --populations YRI [--populations CHS …]` — per-population sex\n    split, phase3 count, and trio membership. Repeat `--populations` for multiple\n    values (full names contain commas, so they are not comma-separated).\n-   `superpopulation-summary --superpopulations EAS [--superpopulations EUR …]` —\n    per-superpopulation totals with a per-population breakdown.\n-   `select-samples-by-population --population YRI` and\u002For `--superpopulation AFR`,\n    with optional `--skip`\u002F`--limit` (default 0 \u002F 50, max 3202) — the sample IDs in\n    a population and\u002For superpopulation; both given intersects. Feed the names into\n    `select-variants-in-samples` to see their variants.\n\nSee [references\u002Fonekgpd_commands.md](references\u002Fonekgpd_commands.md) for full\nargument tables and JSON output schemas.\n\n## Typical Workflows\n\n### Which individuals, then which variants they carry\n\nThe following is an illustrative template; replace all angle-bracket placeholders.\n\n```bash\n# Step 1: resolve gene -> verified GRCh38 region (authoritative source).\n# Step 2: count individuals carrying a qualifying variant in the region.\nuv run scripts\u002Fonekgpd_api.py count-samples \\\n  --chrom \u003Cchr> --start \u003Cstart> --end \u003Cend> \\\n  --consequence MISSENSE_VARIANT --alpha-missense-class AM_LIKELY_PATHOGENIC \\\n  --output \u002Ftmp\u002Fn.json\n# Step 3: list those individuals.\nuv run scripts\u002Fonekgpd_api.py select-samples \\\n  --chrom \u003Cchr> --start \u003Cstart> --end \u003Cend> \\\n  --consequence MISSENSE_VARIANT --alpha-missense-class AM_LIKELY_PATHOGENIC \\\n  --output \u002Ftmp\u002Fwho.json\n# Step 4: count variants for those individuals before selecting.\nuv run scripts\u002Fonekgpd_api.py count-variants-in-samples \\\n  --chrom \u003Cchr> --start \u003Cstart> --end \u003Cend> \\\n  --samples \u003Cname1,name2,...> \\\n  --consequence MISSENSE_VARIANT --alpha-missense-class AM_LIKELY_PATHOGENIC \\\n  --output \u002Ftmp\u002Fvariant_count.json\nuv run scripts\u002Fonekgpd_api.py select-variants-in-samples \\\n  --chrom \u003Cchr> --start \u003Cstart> --end \u003Cend> \\\n  --samples \u003Cname1,name2,...> \\\n  --consequence MISSENSE_VARIANT --alpha-missense-class AM_LIKELY_PATHOGENIC \\\n  --output \u002Ftmp\u002Fvariants.json\n```\n\n### Homozygous-reference carriers at a position of interest\n\nIllustrative template; replace the placeholders with verified coordinates.\n\n```bash\n# After identifying a position of interest (verified coordinate):\nuv run scripts\u002Fonekgpd_api.py count-samples-hom-ref \\\n  --chrom \u003Cchr> --position \u003Cpos> --output \u002Ftmp\u002Fhomref_n.json\nuv run scripts\u002Fonekgpd_api.py select-samples-hom-ref \\\n  --chrom \u003Cchr> --position \u003Cpos> --output \u002Ftmp\u002Fhomref.json\n```\n\n## Common Mistakes\n\n-   **Mistake:** Querying with an unverified coordinate.\n    **Fix:** Always resolve gene\u002Ffeature → GRCh38 against an authoritative\n    source first.\n    A misplaced region returns results for an unintended location without error.\n-   **Mistake:** Calling a selection command before its counting command.\n    **Fix:** Count first; selection result sets can be large.\n-   **Mistake:** Assuming a GRCh37 coordinate will work.\n    **Fix:** The dataset is GRCh38 only.\n\n## References\n\n-   [references\u002Fonekgpd_commands.md](references\u002Fonekgpd_commands.md) — full\n    per-command argument tables and the returned-variant output schema.\n-   [references\u002Fannotation_vocabularies.md](references\u002Fannotation_vocabularies.md)\n    — the controlled-vocabulary terms accepted by the CSV filter flags\n    (consequence, impact, biotype, feature type, ClinVar significance,\n    AlphaMissense class, variant class).\n-   Current API contract and live-check scope: the\n    [command reference](references\u002Fonekgpd_commands.md#verified-api-contract).\n-   1000 Genomes Project \u002F IGSR: https:\u002F\u002Fwww.internationalgenome.org\u002F\n-   1000 Genomes Project dataset online: https:\u002F\u002Fdnaerys.org\u002Fonline\u002F\n",{"name":5,"license":14,"metadata":23,"description":28,"allowed-tools":29,"compatibility":30},{"version":24,"skill-author":25,"last-reviewed":26,"upstream-version":27},"1.4","Dnaerys","2026-09-30","dnaerys 0.2.1; proto R1.20.0","Queries the 1000 Genomes Project dataset (3,202 whole-genome-sequenced individuals, GRCh38) at the level of individual participants. Use when a question is about individuals or variants in the 1000 Genomes Project cohort: which individuals carry variants matching specific criteria in a gene or region, which individuals are homozygous-reference at a position, which variants exist in the dataset or carried by specified individuals in a gene or region, the relatedness between two specified individuals. Variants are returned with 1000 Genomes allele frequencies (AF), gnomAD v4.1 exome and genome AF, AlphaMissense score, and HGVSp annotations.\n","Write Bash","Requires Python >=3.11. Variant and sample queries require outbound network access to the public 1000 Genomes query endpoint over TLS; the sample\u002Fpopulation metadata commands run fully offline over a data file bundled in the skill. No credentials, API keys, or environment variables are used.","main","66c9bd32ac14a921980362cf85872a1c402101c2","hermes\u002Fprofiles\u002Fworker-research\u002Fskills\u002Fonekgpd","https:\u002F\u002Fgithub.com\u002Fbeanspowt\u002Fbeancode","https:\u002F\u002Fgithub.com\u002Fbeanspowt","2026-11-10 23:22:33",{"source":8,"skillName":5,"commands":38,"prompt":48,"zipAvailable":49},[39,42,45],{"tool":40,"command":41},"npx","npx skills add beanspowt\u002Fbeancode --skill onekgpd",{"tool":43,"command":44},"bunx","bunx skills add beanspowt\u002Fbeancode --skill onekgpd",{"tool":46,"command":47},"pnpm","pnpm dlx skills add beanspowt\u002Fbeancode --skill onekgpd","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fbeanspowt\u002Fbeancode\u002Fblob\u002Fmain\u002Fhermes\u002Fprofiles\u002Fworker-research\u002Fskills\u002Fonekgpd\u002FSKILL.md",true,[51,57,63,67,73],{"path":52,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":55,"sourceHtmlUrl":56},"assets\u002Fkgpe.json","ASSET","资产文件",1037258,"https:\u002F\u002Fgithub.com\u002Fbeanspowt\u002Fbeancode\u002Fblob\u002Fmain\u002Fhermes\u002Fprofiles\u002Fworker-research\u002Fskills\u002Fonekgpd\u002Fassets\u002Fkgpe.json",{"path":58,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":61,"sourceHtmlUrl":62},"references\u002Fannotation_vocabularies.md","REFERENCE","参考文档",4777,"https:\u002F\u002Fgithub.com\u002Fbeanspowt\u002Fbeancode\u002Fblob\u002Fmain\u002Fhermes\u002Fprofiles\u002Fworker-research\u002Fskills\u002Fonekgpd\u002Freferences\u002Fannotation_vocabularies.md",{"path":64,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":65,"sourceHtmlUrl":66},"references\u002Fonekgpd_commands.md",18164,"https:\u002F\u002Fgithub.com\u002Fbeanspowt\u002Fbeancode\u002Fblob\u002Fmain\u002Fhermes\u002Fprofiles\u002Fworker-research\u002Fskills\u002Fonekgpd\u002Freferences\u002Fonekgpd_commands.md",{"path":68,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":71,"sourceHtmlUrl":72},"scripts\u002Fonekgpd_api.py","SCRIPT","脚本",32584,"https:\u002F\u002Fgithub.com\u002Fbeanspowt\u002Fbeancode\u002Fblob\u002Fmain\u002Fhermes\u002Fprofiles\u002Fworker-research\u002Fskills\u002Fonekgpd\u002Fscripts\u002Fonekgpd_api.py",{"path":74,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":75,"sourceHtmlUrl":76},"scripts\u002Fonekgpd_meta.py",19389,"https:\u002F\u002Fgithub.com\u002Fbeanspowt\u002Fbeancode\u002Fblob\u002Fmain\u002Fhermes\u002Fprofiles\u002Fworker-research\u002Fskills\u002Fonekgpd\u002Fscripts\u002Fonekgpd_meta.py",[78,85,92,99,106,113],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":18},"01M7F6BB3VS43C65P23JR4ZN5G","venue-templates","Prepares journal manuscripts, conference papers, research posters, and grant documents using venue-specific formatting guidance and bundled LaTeX scaffolds. Supports selecting an official template, checking current page or anonymity rules, adapting academic writing to a venue, or inspecting a submission PDF.","https:\u002F\u002Fgithub.com\u002Fbeanspowt\u002Fbeancode\u002Fblob\u002Fmain\u002Fhermes\u002Fprofiles\u002Fworker-writer\u002Fskills\u002Fvenue-templates\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":18},"01M7F6B4CBVEHY1RKVW55X8484","scientific-writing","Drafts, revises, and audits scientific manuscripts or reports with explicit evidence provenance, reporting-guideline coverage, authorship accountability, confidentiality controls, and local consistency checks. Use for manuscript sections, references, declarations, tables, figures, or submission preparation when scientific accuracy and traceability matter.","https:\u002F\u002Fgithub.com\u002Fbeanspowt\u002Fbeancode\u002Fblob\u002Fmain\u002Fhermes\u002Fprofiles\u002Fworker-writer\u002Fskills\u002Fscientific-writing\u002FSKILL.md",[],[],{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":18},"01M7F6AXKSP5AXE8B7RCE1KP0C","scientific-visualization","Creates and audits truthful, accessible, publication-ready scientific figures with Matplotlib, Seaborn, or Plotly. Use it for figure design, multi-panel layouts, uncertainty and missing-data displays, color\u002Fcontrast review, image metadata validation, and journal export planning.","https:\u002F\u002Fgithub.com\u002Fbeanspowt\u002Fbeancode\u002Fblob\u002Fmain\u002Fhermes\u002Fprofiles\u002Fworker-writer\u002Fskills\u002Fscientific-visualization\u002FSKILL.md",[],[],{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"publishedAt":18},"01M7F6AMRHS0QH64CMKE8TP9Y7","scientific-slides","Builds slide decks and presentations for research talks. Used for making PowerPoint slides, conference presentations, seminar talks, research presentations, thesis defense slides, or any scientific talk. Provides slide structure, design templates, timing guidance, and visual validation. Works with PowerPoint and LaTeX Beamer.","https:\u002F\u002Fgithub.com\u002Fbeanspowt\u002Fbeancode\u002Fblob\u002Fmain\u002Fhermes\u002Fprofiles\u002Fworker-writer\u002Fskills\u002Fscientific-slides\u002FSKILL.md",[],[],{"skillNo":107,"name":108,"nameZh":6,"description":109,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":110,"categories":111,"keywords":112,"publishedAt":18},"01M7F6ACZ7GQJNNW0682235MC3","scientific-schematics","Generates scientific diagram drafts using Nano Banana 2 AI with smart iterative refinement. Uses Gemini 3.7 Flash for quality review. Refines when the review requests improvement, with at most two generations. Specialized in neural network architectures, system diagrams, flowcharts, biological pathways, and complex scientific visualizations.","https:\u002F\u002Fgithub.com\u002Fbeanspowt\u002Fbeancode\u002Fblob\u002Fmain\u002Fhermes\u002Fprofiles\u002Fworker-writer\u002Fskills\u002Fscientific-schematics\u002FSKILL.md",[],[],{"skillNo":114,"name":115,"nameZh":6,"description":116,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":117,"categories":118,"keywords":119,"publishedAt":18},"01M7F6A2JDHTYABYSA4NCE82VG","research-grants","Supports research proposal preparation and review for NSF, NIH, DOE, DARPA, and Taiwan NSTC, including opportunity-specific requirements, aims, review criteria, budgets, broader impacts, forms, and resubmissions. Use for investigator-authored grant development, compliance matrices, and proposal critiques.","https:\u002F\u002Fgithub.com\u002Fbeanspowt\u002Fbeancode\u002Fblob\u002Fmain\u002Fhermes\u002Fprofiles\u002Fworker-writer\u002Fskills\u002Fresearch-grants\u002FSKILL.md",[],[]]