[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75K13D1APRKXBXZG4MQVGJB":3,"skill-same:01M75K13D1APRKXBXZG4MQVGJB":137},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":92,"commitSha":93,"skillDirectory":94,"forksCount":95,"repositoryHtmlUrl":96,"repositoryHomepageUrl":6,"ownerHtmlUrl":97,"ownerBlogUrl":98,"ownerDescription":6,"updatedAt":99,"install":100,"resources":113},"01M75K13D1APRKXBXZG4MQVGJB","gi-splice",null,"Detect splice donor and acceptor sites in DNA sequences using the Genomic Intelligence G0 BigBird transformer, via the hosted \u002Fv1\u002Ftasks\u002Fsplice\u002Fpredict API. Returns per-position site probabilities and called sites.","stanfish06\u002Fskillquarium","stanfish06","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F93099613?v=4","01M75F1CK4ZW109ZK3T26VN52F","Zhiyuan","01M75F1CM53VH6F79DZ8GXKKES",12,"MIT","https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fgi-splice\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: gi-splice\ndescription: Detect splice donor and acceptor sites in DNA sequences using the Genomic Intelligence G0 BigBird transformer, via the hosted \u002Fv1\u002Ftasks\u002Fsplice\u002Fpredict API. Returns per-position site probabilities\n  and called sites.\nlicense: MIT\nmetadata:\n  openclaw:\n    requires:\n      bins:\n      - python3\n      env: null\n      config: null\n    always: false\n    emoji: ✂️\n    homepage: https:\u002F\u002Fdocs.genomicintelligence.ai\n    os:\n    - darwin\n    - linux\n    install:\n    - kind: pip\n      package: requests\n      bins: null\n    trigger_keywords:\n    - splice\n    - splice site\n    - splice donor\n    - splice acceptor\n    - splicing prediction\n    - intron exon boundary\n    - cryptic splice site\n    - GT-AG site\n    - gi splice\n    - G0 splice\n    - genomic intelligence splice\n  author: ClawBio + Genomic Intelligence\n  demo_data:\n  - path: example_data\u002Fsplice_hbb.fa\n    description: HBB gene body (chr11, GRCh38; reverse-complemented to gene-sense) — bundled real reference sequence.\n  dependencies:\n    python: '>=3.10'\n    packages:\n    - requests>=2.31\n  domain: genomics\n  endpoints:\n    cli: python skills\u002Fgi-splice\u002Fgi_splice.py --input {input_file} --output {output_dir}\n  inputs:\n  - name: input_file\n    type: file\n    format:\n    - fa\n    - fasta\n    - fna\n    description: Single-record FASTA, typically a gene body (5'UTR → 3'UTR including introns).\n    required: false\n  outputs:\n  - name: report\n    type: file\n    format: md\n    description: Markdown report — sequence + model metadata, called splice sites (position, kind, strand, probability).\n  - name: result\n    type: file\n    format: json\n    description: Full `{data, meta}` response from the GI API plus a flattened summary.\n  - name: reproducibility\n    type: directory\n    description: command.sh + environment.json for exact-rerun reproducibility.\n  tags:\n  - genomics\n  - splice\n  - splice-site\n  - splicing\n  - intron-exon\n  - dna-lm\n  - transformer\n  - gi-api\n  version: 0.1.0\n---\n\n# ✂️ gi-splice\n\nYou are **gi-splice**, a ClawBio agent that calls the **Genomic Intelligence** splice-site model. Given a gene-body sequence, it returns called donor\u002Facceptor sites and per-position probabilities via the hosted API.\n\n> ⚠️ **Remote inference — opt-in required.** Unlike most ClawBio skills, this skill uploads your FASTA sequence to the hosted Genomic Intelligence API at `https:\u002F\u002Fapi.genomicintelligence.ai`. Prefer a browser? The same models run interactively at \u003Chttps:\u002F\u002Fgenomicintelligence.ai>. **Do not submit identifiable patient data** without an appropriate data-use agreement. Key setup: see [Authentication](#authentication) below.\n\n## Trigger\n\n**Fire this skill when the user says any of:**\n- \"predict splice sites in this gene\"\n- \"find splice donors\u002Facceptors\"\n- \"score this for cryptic splice sites\"\n- \"splice site prediction\"\n- \"gi-splice\", \"G0 splice\"\n- \"where does this transcript splice?\"\n\n**Do NOT fire when:**\n- The user asks for full transcript structure (multi-exon annotation) → `gi-annotation`\n- The user asks about variant effect on splicing → use `variant-annotation` (VEP) or chain `gi-splice` ref\u002Falt comparisons\n\n## Why This Exists\n\n- **Without it**: SpliceAI \u002F similar require local GPU + weights + careful preprocessing.\n- **With it**: One CLI call → ranked site list with positions and probabilities, in ~1 s.\n- **Why ClawBio**: Hosted G0 BigBird inference plus ClawBio's reproducibility bundle and chaining (`gi-splice` → `gi-annotation` → variant interpretation).\n\n## API Backed\n\n`POST https:\u002F\u002Fapi.genomicintelligence.ai\u002Fv1\u002Ftasks\u002Fsplice\u002Fpredict` — default model `g0-splice-bigbird` (G0 BigBird transformer; long-context handling for full gene bodies).\n\n## Workflow\n\n1. **Parse**: single-record FASTA via `clawbio.gi.gi_client.read_fasta`.\n2. **POST** the full gene body to `\u002Fv1\u002Ftasks\u002Fsplice\u002Fpredict`.\n3. **Render**: `report.md` + `result.json` + `reproducibility\u002F`.\n\n## CLI Reference\n\n```bash\n# Demo — bundled HBB gene body\npython skills\u002Fgi-splice\u002Fgi_splice.py --demo --output \u002Ftmp\u002Fgi-splice-demo\n\n# Your own FASTA\npython skills\u002Fgi-splice\u002Fgi_splice.py --input my_gene.fa --output report_dir\n\n# Via ClawBio runner\npython clawbio.py run gi-splice --demo\n```\n\n## Demo\n\n```bash\npython clawbio.py run gi-splice --demo\n```\n\nBundled fixture is HBB (β-globin) gene body, reverse-complemented to gene-sense. HBB has 3 exons \u002F 2 introns; on the coding strand the model calls ~8 sites (≈4 donor + 4 acceptor, including lower-confidence alternates).\n\n## Authentication\n\nThe skill requires a Genomic Intelligence partner key in `GI_API_KEY`. Resolution order:\n\n1. `--api-key \u003Cvalue>` CLI flag (explicit override).\n2. `GI_API_KEY` environment variable.\n3. Otherwise: the skill raises a `RuntimeError` pointing here.\n\n### Quick start — ClawBio hackathon key\n\nA shared hackathon-tier key ships in `.env.example` at the repo root (50 concurrent \u002F 120 rpm, opt-in only). From wherever the ClawBio files live on your machine:\n\n```bash\n# Repo root (git clone) — or ~\u002F.claude\u002Fplugins\u002Fcache\u002Fclawbio\u002Fclawbio\u002F\u003Cversion>\u002F for plugin installs\ncp .env.example .env\nset -a && source .env && set +a\n```\n\n### Production \u002F heavier use\n\nRequest an individual key at **contact@genomicintelligence.ai**, then:\n\n```bash\nexport GI_API_KEY=gi_yourkeyhere\n```\n\n## Gotchas\n\n- **Submit gene-sense, not genomic-sense.** Minus-strand genes need RC'd input. The bundled HBB fixture demonstrates this — its FASTA header notes `strand:-1` (gene-sense for the minus-strand HBB gene).\n- **Full gene body, not just an exon.** The model uses long context to disambiguate; truncated input degrades accuracy.\n- **Donor\u002Facceptor pairs.** The model emits independent site calls. Pair them downstream by ordering + strand consistency if you need intron boundaries.\n- **Hackathon key is shared** — `GI_API_KEY` for serious work.\n\n## Output Structure\n\n```\noutput_dir\u002F\n├── report.md              # Site table (position, kind, strand, probability)\n├── result.json            # Full {data, meta} envelope\n└── reproducibility\u002F\n    ├── command.sh\n    └── environment.json\n```\n\n## Integration with Bio Orchestrator\n\nRoutes here on: \"splice site\", \"splice donor\", \"splice acceptor\", \"predict splicing\".\n\nChains with: `variant-annotation` (intersect calls with VEP splice consequences), `gi-annotation` (cross-check against predicted exon boundaries).\n\n## Safety\n\nResearch tool. Not a clinical assay.\n","# ✂️ gi-splice\n\nYou are **gi-splice**, a ClawBio agent that calls the **Genomic Intelligence** splice-site model. Given a gene-body sequence, it returns called donor\u002Facceptor sites and per-position probabilities via the hosted API.\n\n> ⚠️ **Remote inference — opt-in required.** Unlike most ClawBio skills, this skill uploads your FASTA sequence to the hosted Genomic Intelligence API at `https:\u002F\u002Fapi.genomicintelligence.ai`. Prefer a browser? The same models run interactively at \u003Chttps:\u002F\u002Fgenomicintelligence.ai>. **Do not submit identifiable patient data** without an appropriate data-use agreement. Key setup: see [Authentication](#authentication) below.\n\n## Trigger\n\n**Fire this skill when the user says any of:**\n- \"predict splice sites in this gene\"\n- \"find splice donors\u002Facceptors\"\n- \"score this for cryptic splice sites\"\n- \"splice site prediction\"\n- \"gi-splice\", \"G0 splice\"\n- \"where does this transcript splice?\"\n\n**Do NOT fire when:**\n- The user asks for full transcript structure (multi-exon annotation) → `gi-annotation`\n- The user asks about variant effect on splicing → use `variant-annotation` (VEP) or chain `gi-splice` ref\u002Falt comparisons\n\n## Why This Exists\n\n- **Without it**: SpliceAI \u002F similar require local GPU + weights + careful preprocessing.\n- **With it**: One CLI call → ranked site list with positions and probabilities, in ~1 s.\n- **Why ClawBio**: Hosted G0 BigBird inference plus ClawBio's reproducibility bundle and chaining (`gi-splice` → `gi-annotation` → variant interpretation).\n\n## API Backed\n\n`POST https:\u002F\u002Fapi.genomicintelligence.ai\u002Fv1\u002Ftasks\u002Fsplice\u002Fpredict` — default model `g0-splice-bigbird` (G0 BigBird transformer; long-context handling for full gene bodies).\n\n## Workflow\n\n1. **Parse**: single-record FASTA via `clawbio.gi.gi_client.read_fasta`.\n2. **POST** the full gene body to `\u002Fv1\u002Ftasks\u002Fsplice\u002Fpredict`.\n3. **Render**: `report.md` + `result.json` + `reproducibility\u002F`.\n\n## CLI Reference\n\n```bash\n# Demo — bundled HBB gene body\npython skills\u002Fgi-splice\u002Fgi_splice.py --demo --output \u002Ftmp\u002Fgi-splice-demo\n\n# Your own FASTA\npython skills\u002Fgi-splice\u002Fgi_splice.py --input my_gene.fa --output report_dir\n\n# Via ClawBio runner\npython clawbio.py run gi-splice --demo\n```\n\n## Demo\n\n```bash\npython clawbio.py run gi-splice --demo\n```\n\nBundled fixture is HBB (β-globin) gene body, reverse-complemented to gene-sense. HBB has 3 exons \u002F 2 introns; on the coding strand the model calls ~8 sites (≈4 donor + 4 acceptor, including lower-confidence alternates).\n\n## Authentication\n\nThe skill requires a Genomic Intelligence partner key in `GI_API_KEY`. Resolution order:\n\n1. `--api-key \u003Cvalue>` CLI flag (explicit override).\n2. `GI_API_KEY` environment variable.\n3. Otherwise: the skill raises a `RuntimeError` pointing here.\n\n### Quick start — ClawBio hackathon key\n\nA shared hackathon-tier key ships in `.env.example` at the repo root (50 concurrent \u002F 120 rpm, opt-in only). From wherever the ClawBio files live on your machine:\n\n```bash\n# Repo root (git clone) — or ~\u002F.claude\u002Fplugins\u002Fcache\u002Fclawbio\u002Fclawbio\u002F\u003Cversion>\u002F for plugin installs\ncp .env.example .env\nset -a && source .env && set +a\n```\n\n### Production \u002F heavier use\n\nRequest an individual key at **contact@genomicintelligence.ai**, then:\n\n```bash\nexport GI_API_KEY=gi_yourkeyhere\n```\n\n## Gotchas\n\n- **Submit gene-sense, not genomic-sense.** Minus-strand genes need RC'd input. The bundled HBB fixture demonstrates this — its FASTA header notes `strand:-1` (gene-sense for the minus-strand HBB gene).\n- **Full gene body, not just an exon.** The model uses long context to disambiguate; truncated input degrades accuracy.\n- **Donor\u002Facceptor pairs.** The model emits independent site calls. Pair them downstream by ordering + strand consistency if you need intron boundaries.\n- **Hackathon key is shared** — `GI_API_KEY` for serious work.\n\n## Output Structure\n\n```\noutput_dir\u002F\n├── report.md              # Site table (position, kind, strand, probability)\n├── result.json            # Full {data, meta} envelope\n└── reproducibility\u002F\n    ├── command.sh\n    └── environment.json\n```\n\n## Integration with Bio Orchestrator\n\nRoutes here on: \"splice site\", \"splice donor\", \"splice acceptor\", \"predict splicing\".\n\nChains with: `variant-annotation` (intersect calls with VEP splice consequences), `gi-annotation` (cross-check against predicted exon boundaries).\n\n## Safety\n\nResearch tool. Not a clinical assay.\n",{"name":5,"license":15,"metadata":24,"description":7},{"tags":25,"author":34,"domain":26,"inputs":35,"outputs":44,"version":57,"openclaw":58,"demo_data":82,"endpoints":86,"dependencies":88},[26,27,28,29,30,31,32,33],"genomics","splice","splice-site","splicing","intron-exon","dna-lm","transformer","gi-api","ClawBio + Genomic Intelligence",[36],{"name":37,"type":38,"format":39,"required":20,"description":43},"input_file","file",[40,41,42],"fa","fasta","fna","Single-record FASTA, typically a gene body (5'UTR → 3'UTR including introns).",[45,49,53],{"name":46,"type":38,"format":47,"description":48},"report","md","Markdown report — sequence + model metadata, called splice sites (position, kind, strand, probability).",{"name":50,"type":38,"format":51,"description":52},"result","json","Full `{data, meta}` response from the GI API plus a flattened summary.",{"name":54,"type":55,"description":56},"reproducibility","directory","command.sh + environment.json for exact-rerun reproducibility.","0.1.0",{"os":59,"emoji":62,"always":20,"install":63,"homepage":67,"requires":68,"trigger_keywords":71},[60,61],"darwin","linux","✂️",[64],{"bins":6,"kind":65,"package":66},"pip","requests","https:\u002F\u002Fdocs.genomicintelligence.ai",{"env":6,"bins":69,"config":6},[70],"python3",[27,72,73,74,75,76,77,78,79,80,81],"splice site","splice donor","splice acceptor","splicing prediction","intron exon boundary","cryptic splice site","GT-AG site","gi splice","G0 splice","genomic intelligence splice",[83],{"path":84,"description":85},"example_data\u002Fsplice_hbb.fa","HBB gene body (chr11, GRCh38; reverse-complemented to gene-sense) — bundled real reference sequence.",{"cli":87},"python skills\u002Fgi-splice\u002Fgi_splice.py --input {input_file} --output {output_dir}",{"python":89,"packages":90},">=3.10",[91],"requests>=2.31","master","49e49abf2f670d429e0b7e2c0349739c3fdd5cbe","skills\u002Fgi-splice",5,"https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium","https:\u002F\u002Fgithub.com\u002Fstanfish06","https:\u002F\u002Fwww.stanfish.dev\u002F","2026-11-14 21:31:37",{"source":8,"skillName":5,"commands":101,"prompt":111,"zipAvailable":112},[102,105,108],{"tool":103,"command":104},"npx","npx skills add stanfish06\u002Fskillquarium --skill gi-splice",{"tool":106,"command":107},"bunx","bunx skills add stanfish06\u002Fskillquarium --skill gi-splice",{"tool":109,"command":110},"pnpm","pnpm dlx skills add stanfish06\u002Fskillquarium --skill gi-splice","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fgi-splice\u002FSKILL.md",true,[114,120,125,129,133],{"path":115,"resourceType":116,"resourceTypeDesc":117,"sizeBytes":118,"sourceHtmlUrl":119},"api.py","SCRIPT","脚本",1116,"https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fgi-splice\u002Fapi.py",{"path":84,"resourceType":121,"resourceTypeDesc":122,"sizeBytes":123,"sourceHtmlUrl":124},"OTHER","其他",4048,"https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fgi-splice\u002Fexample_data\u002Fsplice_hbb.fa",{"path":126,"resourceType":116,"resourceTypeDesc":117,"sizeBytes":127,"sourceHtmlUrl":128},"gi_splice.py",511,"https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fgi-splice\u002Fgi_splice.py",{"path":130,"resourceType":116,"resourceTypeDesc":117,"sizeBytes":131,"sourceHtmlUrl":132},"tests\u002F__init__.py",0,"https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fgi-splice\u002Ftests\u002F__init__.py",{"path":134,"resourceType":116,"resourceTypeDesc":117,"sizeBytes":135,"sourceHtmlUrl":136},"tests\u002Ftest_gi_splice.py",1636,"https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fgi-splice\u002Ftests\u002Ftest_gi_splice.py",[138,145,154,161,168,175],{"skillNo":139,"name":140,"nameZh":6,"description":141,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":142,"categories":143,"keywords":144,"publishedAt":19},"01M76ZJTRVA456GD7K8Y3EP82H","zarr-python","Stores and queries chunked N-D scientific arrays with Zarr-Python 3, including codecs, sharding, S3\u002FGCS storage, and NumPy\u002FDask\u002FXarray integration. Use for array layout, bounded I\u002FO, format migration, or scientific metadata preservation.","https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fzarr-python\u002FSKILL.md",[],[],{"skillNo":146,"name":147,"nameZh":6,"description":148,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":149,"licenseFileUrl":150,"sourceHtmlUrl":151,"categories":152,"keywords":153,"publishedAt":19},"01M76ZJQZ15Q1HKC5V85NHE325","yeet","Publish local changes to GitHub by confirming scope, committing intentionally, pushing the branch, and opening a draft PR through the GitHub app from this plugin, with `gh` used only as a fallback where connector coverage is insufficient.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fyeet\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fyeet\u002FSKILL.md",[],[],{"skillNo":155,"name":156,"nameZh":6,"description":157,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":149,"licenseFileUrl":6,"sourceHtmlUrl":158,"categories":159,"keywords":160,"publishedAt":19},"01M76ZJ8ASZ4QYQ70Y6SBA4Z4S","xarray","N-dimensional labeled arrays and datasets in Python. Built on top of NumPy and Dask. It introduces labels in the form of dimensions, coordinates, and attributes on top of raw NumPy-like arrays, making data analysis in physical sciences more intuitive and less error-prone. Use for working with multi-dimensional scientific data, NetCDF\u002FGRIB\u002FZarr files, climate\u002Fweather\u002Foceanographic datasets, remote sensing, geospatial imaging, large out-of-memory datasets with Dask, and labeled array operations.","https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fxarray\u002FSKILL.md",[],[],{"skillNo":162,"name":163,"nameZh":6,"description":164,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":165,"categories":166,"keywords":167,"publishedAt":19},"01M76ZHFBXD6VXPQ02VCEG202B","writing-mstest-tests","Use when asked to fix, rewrite, update, improve, modernize, show corrected code for, or explain existing MSTest tests or MSTest-specific configuration. Use for \"review\" when corrected code or edits are wanted, even for one pasted assertion or passing tests with bad failure output. Covers expected\u002Factual labels; generic Boolean, collection, string, numeric, null, identity, exception, hard-cast, and object[] checks; TestContext\u002Flifecycle; timeout\u002Fcancellation; OS\u002FCI conditions, retry, cleanup, parallelization, MSTest.Sdk project setup, and MSTESTxxxx. Honor the installed MSTest version. DO NOT USE to design new test cases (code-testing), perform report-only audits, create project files rather than explain MSTest setup, run tests, migrate frameworks, or handle non-MSTest\u002Fnon-.NET code.","https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fwriting-mstest-tests\u002FSKILL.md",[],[],{"skillNo":169,"name":170,"nameZh":6,"description":171,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":172,"categories":173,"keywords":174,"publishedAt":19},"01M76ZDFDF4N88RH6HSYGS7GP2","wgs-prs","End-to-end WGS to polygenic risk score pipeline. Takes paired-end FASTQ files (or a pre-existing VCF) through nf-core\u002Fsarek for variant calling, applies VCF QC (normalisation, hard filtering, Ti\u002FTv and Het\u002FHom checks), then computes polygenic risk scores via the PGS Catalog. Fills the FASTQ to VCF gap upstream of the gwas-prs skill.","https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fwgs-prs\u002FSKILL.md",[],[],{"skillNo":176,"name":177,"nameZh":6,"description":178,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":149,"licenseFileUrl":179,"sourceHtmlUrl":180,"categories":181,"keywords":182,"publishedAt":19},"01M76ZCC1SC68J42QK4MDC8RCG","webapp-testing","Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.","https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fwebapp-testing\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fwebapp-testing\u002FSKILL.md",[],[]]