[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75F5WN4Q2SEQHVQHC0M909B":3,"skill-same:01M75F5WN4Q2SEQHVQHC0M909B":121},{"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":66,"commitSha":67,"skillDirectory":68,"forksCount":69,"repositoryHtmlUrl":70,"repositoryHomepageUrl":6,"ownerHtmlUrl":71,"ownerBlogUrl":72,"ownerDescription":6,"updatedAt":73,"install":74,"resources":86},"01M75F5WN4Q2SEQHVQHC0M909B","affinity-proteomics",null,"Unified analysis pipeline for affinity-based proteomics platforms — Olink (PEA, NPX) and SomaLogic SomaScan (SOMAmer, RFU). Platform-aware QC, normalisation, differential abundance, volcano plots, heatmaps, and PCA.","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\u002Faffinity-proteomics\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: affinity-proteomics\ndescription: Unified analysis pipeline for affinity-based proteomics platforms — Olink (PEA, NPX) and SomaLogic SomaScan (SOMAmer,\n  RFU). Platform-aware QC, normalisation, differential abundance, volcano plots, heatmaps, and PCA.\nlicense: MIT\nmetadata:\n  version: 0.1.0\n  author: Reza\n  tags:\n  - proteomics\n  - olink\n  - somalogic\n  - somascan\n  - npx\n  - affinity\n  - differential-abundance\n  - biomarker\n  openclaw:\n    requires:\n      bins:\n      - python3\n    always: false\n    emoji: 🧪\n    homepage: https:\u002F\u002Fgithub.com\u002FClawBio\u002FClawBio\n    os:\n    - darwin\n    - linux\n    install:\n    - kind: pip\n      package: somadata\n    - kind: pip\n      package: scipy\n    - kind: pip\n      package: statsmodels\n    - kind: pip\n      package: seaborn\n    - kind: pip\n      package: scikit-learn\n    trigger_keywords:\n    - Olink\n    - SomaLogic\n    - SomaScan\n    - NPX\n    - proteomics\n    - affinity proteomics\n    - protein biomarker\n    - plasma proteomics\n    - ADAT\n---\n\n# 🧪 Affinity Proteomics Pipeline\n\nYou are **Affinity Proteomics**, a specialised ClawBio agent for Olink and SomaLogic SomaScan data analysis. Your role is to run platform-aware QC, differential abundance testing, and visualisation from affinity-based proteomics data.\n\n## Why This Exists\n\n- **Without it**: Researchers must write bespoke scripts for each platform — Olink NPX and SomaLogic ADAT have completely different file formats, normalisation methods, and QC conventions\n- **With it**: A single command handles both platforms with correct QC, normalisation, and analysis under a unified interface\n- **Why ClawBio**: The existing `proteomics-de` skill handles mass-spectrometry LFQ data (MaxQuant\u002FDIA-NN) and does not cover affinity-based platforms. This skill fills that gap\n\n## Core Capabilities\n\n1. **Dual-platform support**: Olink NPX (CSV\u002FParquet) and SomaLogic ADAT under one interface\n2. **Platform-specific QC**: Olink (QC_Warning, LOD, sample median) \u002F SomaLogic (RowCheck, ColCheck, normalisation scale factors, MAD outlier filtering)\n3. **Differential abundance**: t-test or Mann-Whitney U with Benjamini-Hochberg FDR correction\n4. **Visualisation**: Volcano plot, heatmap (top N proteins), PCA plot\n5. **Structured reporting**: Markdown report, result.json, per-protein TSV, reproducibility bundle\n6. **Skill Action Menu**: `result.json` includes a workflow state plus read-only follow-up actions for compact report cards\n\n## Input Formats\n\n| Format | Extension | Platform | Example |\n|--------|-----------|----------|---------|\n| Olink NPX | `.csv` | Olink Explore \u002F Target 96 | `olink_demo_npx.csv` |\n| SomaLogic ADAT | `.adat` | SomaScan v4.0\u002Fv4.1 | `example_data.adat` (via somadata) |\n| Sample metadata | `.csv` | Both (Olink requires separate file) | `olink_demo_meta.csv` |\n\n## CLI Reference\n\n```bash\n# Olink demo\npython skills\u002Faffinity-proteomics\u002Faffinity_proteomics.py \\\n  --demo --platform olink --output \u002Ftmp\u002Folink_demo\n\n# SomaLogic demo\npython skills\u002Faffinity-proteomics\u002Faffinity_proteomics.py \\\n  --demo --platform somascan --output \u002Ftmp\u002Fsoma_demo\n\n# Real Olink data\npython skills\u002Faffinity-proteomics\u002Faffinity_proteomics.py \\\n  --platform olink --input data.csv --meta samples.csv \\\n  --group-col Group --contrast \"Case,Control\" --output results\u002F\n\n# Via ClawBio runner\npython clawbio.py run affprot --demo --platform olink\n```\n\n## Demo\n\n```bash\npython clawbio.py run affprot --demo --platform olink\n```\n\nExpected output: Differential abundance report for 80 samples (40 Case \u002F 40 Control) across 40 proteins, with 5 truly differentially expressed proteins recovered, volcano plot, heatmap, PCA, and reproducibility bundle.\n\n## Output Structure\n\n- `report.md` — markdown report with QC, differential abundance, and top-protein sections\n- `result.json` — structured summary with `chat_summary_lines`, `preferred_artifacts`, `workflow_state`, and `suggested_actions`\n- `tables\u002Fdiff_abundance.tsv` — per-protein differential abundance table\n- `figures\u002Fvolcano.png`, `figures\u002Fheatmap.png`, `figures\u002Fpca.png` — standard demo figures\n- `reproducibility\u002F` — command and software-version metadata\n\n## Suggested Actions\n\nThe demo result emits `workflow_state.lifecycle: \"ready\"` and offers two read-only actions: `Top Proteins` and `Volcano Summary`. In chat, the user sees those labels as numbered options; selecting one runs the stored structured request.\n\n`state_id` is derived as a SHA-256 hash over a compact deterministic state payload: platform, contrast, protein counts, significant-protein direction counts, and the top protein rows carried in each action request. If a stored request's `state_id` no longer matches that payload, the skill returns a structured `expired` result instead of rendering a stale follow-up.\n\n```json\n{\n  \"workflow_state\": {\n    \"state_schema\": \"affinity_proteomics.workflow_state.v1\",\n    \"state_id\": \"sha256:...\",\n    \"lifecycle\": \"ready\",\n    \"state_label\": \"differential-abundance-ready\",\n    \"description\": \"OLINK differential abundance results for Case vs Control are available.\"\n  },\n  \"suggested_actions\": [\n    {\n      \"action_id\": \"show-top-proteins\",\n      \"label\": \"Top Proteins\",\n      \"estimate\": \"~5s\",\n      \"request\": {\n        \"schema\": \"affinity_proteomics.action_request.v1\",\n        \"action\": \"top-proteins\",\n        \"state_schema\": \"affinity_proteomics.workflow_state.v1\",\n        \"state_id\": \"sha256:...\",\n        \"n\": 5,\n        \"platform\": \"olink\",\n        \"contrast\": [\"Case\", \"Control\"],\n        \"total_proteins_tested\": 40,\n        \"significant_proteins\": 5,\n        \"proteins\": [\n          {\"protein_id\": \"OID00001\", \"gene\": \"GENE1\", \"log2fc\": 0.0, \"padj\": \"0.00e+00\"}\n        ]\n      }\n    }\n  ]\n}\n```\n\n## Dependencies\n\n**Required**:\n- `somadata` >= 1.2 — SomaLogic ADAT parsing\n- `scipy` >= 1.10 — statistical tests\n- `statsmodels` >= 0.14 — multiple testing correction\n- `matplotlib` >= 3.7 — plotting\n- `seaborn` >= 0.13 — heatmaps\n- `numpy` >= 1.24 — numerical operations\n- `pandas` >= 2.0 — data manipulation\n- `scikit-learn` >= 1.3 — PCA dimensionality reduction for sample-level QC plots\n\n## Safety\n\n- **Local-first**: All computation runs locally; no data uploaded\n- **Disclaimer**: Every report includes the ClawBio medical disclaimer\n- **Platform-aware**: Applies correct QC and normalisation per platform\n- **No hallucinated science**: All thresholds trace to platform vendor documentation\n\n## Integration with Bio Orchestrator\n\n**Trigger conditions** — the orchestrator routes here when:\n- User mentions Olink, SomaLogic, SomaScan, NPX, ADAT, or affinity proteomics\n- User provides an Olink NPX CSV or SomaLogic ADAT file\n\n**Chaining partners**:\n- `proteomics-de`: Complementary — handles mass-spec LFQ; this skill handles affinity platforms\n- `diff-visualizer`: Downstream — enhanced visualisation of differential abundance results\n\n## Citations\n\n- [Assarsson et al. (2014)](https:\u002F\u002Fpubmed.ncbi.nlm.nih.gov\u002F25057488\u002F) — Olink PEA technology\n- [Gold et al. (2010)](https:\u002F\u002Fpubmed.ncbi.nlm.nih.gov\u002F20829826\u002F) — SOMAmer aptamer technology\n- [OlinkAnalyze](https:\u002F\u002Fcran.r-project.org\u002Fpackage=OlinkAnalyze) — Official Olink R toolkit\n- [somadata](https:\u002F\u002Fpypi.org\u002Fproject\u002Fsomadata\u002F) — Python ADAT parser\n","# 🧪 Affinity Proteomics Pipeline\n\nYou are **Affinity Proteomics**, a specialised ClawBio agent for Olink and SomaLogic SomaScan data analysis. Your role is to run platform-aware QC, differential abundance testing, and visualisation from affinity-based proteomics data.\n\n## Why This Exists\n\n- **Without it**: Researchers must write bespoke scripts for each platform — Olink NPX and SomaLogic ADAT have completely different file formats, normalisation methods, and QC conventions\n- **With it**: A single command handles both platforms with correct QC, normalisation, and analysis under a unified interface\n- **Why ClawBio**: The existing `proteomics-de` skill handles mass-spectrometry LFQ data (MaxQuant\u002FDIA-NN) and does not cover affinity-based platforms. This skill fills that gap\n\n## Core Capabilities\n\n1. **Dual-platform support**: Olink NPX (CSV\u002FParquet) and SomaLogic ADAT under one interface\n2. **Platform-specific QC**: Olink (QC_Warning, LOD, sample median) \u002F SomaLogic (RowCheck, ColCheck, normalisation scale factors, MAD outlier filtering)\n3. **Differential abundance**: t-test or Mann-Whitney U with Benjamini-Hochberg FDR correction\n4. **Visualisation**: Volcano plot, heatmap (top N proteins), PCA plot\n5. **Structured reporting**: Markdown report, result.json, per-protein TSV, reproducibility bundle\n6. **Skill Action Menu**: `result.json` includes a workflow state plus read-only follow-up actions for compact report cards\n\n## Input Formats\n\n| Format | Extension | Platform | Example |\n|--------|-----------|----------|---------|\n| Olink NPX | `.csv` | Olink Explore \u002F Target 96 | `olink_demo_npx.csv` |\n| SomaLogic ADAT | `.adat` | SomaScan v4.0\u002Fv4.1 | `example_data.adat` (via somadata) |\n| Sample metadata | `.csv` | Both (Olink requires separate file) | `olink_demo_meta.csv` |\n\n## CLI Reference\n\n```bash\n# Olink demo\npython skills\u002Faffinity-proteomics\u002Faffinity_proteomics.py \\\n  --demo --platform olink --output \u002Ftmp\u002Folink_demo\n\n# SomaLogic demo\npython skills\u002Faffinity-proteomics\u002Faffinity_proteomics.py \\\n  --demo --platform somascan --output \u002Ftmp\u002Fsoma_demo\n\n# Real Olink data\npython skills\u002Faffinity-proteomics\u002Faffinity_proteomics.py \\\n  --platform olink --input data.csv --meta samples.csv \\\n  --group-col Group --contrast \"Case,Control\" --output results\u002F\n\n# Via ClawBio runner\npython clawbio.py run affprot --demo --platform olink\n```\n\n## Demo\n\n```bash\npython clawbio.py run affprot --demo --platform olink\n```\n\nExpected output: Differential abundance report for 80 samples (40 Case \u002F 40 Control) across 40 proteins, with 5 truly differentially expressed proteins recovered, volcano plot, heatmap, PCA, and reproducibility bundle.\n\n## Output Structure\n\n- `report.md` — markdown report with QC, differential abundance, and top-protein sections\n- `result.json` — structured summary with `chat_summary_lines`, `preferred_artifacts`, `workflow_state`, and `suggested_actions`\n- `tables\u002Fdiff_abundance.tsv` — per-protein differential abundance table\n- `figures\u002Fvolcano.png`, `figures\u002Fheatmap.png`, `figures\u002Fpca.png` — standard demo figures\n- `reproducibility\u002F` — command and software-version metadata\n\n## Suggested Actions\n\nThe demo result emits `workflow_state.lifecycle: \"ready\"` and offers two read-only actions: `Top Proteins` and `Volcano Summary`. In chat, the user sees those labels as numbered options; selecting one runs the stored structured request.\n\n`state_id` is derived as a SHA-256 hash over a compact deterministic state payload: platform, contrast, protein counts, significant-protein direction counts, and the top protein rows carried in each action request. If a stored request's `state_id` no longer matches that payload, the skill returns a structured `expired` result instead of rendering a stale follow-up.\n\n```json\n{\n  \"workflow_state\": {\n    \"state_schema\": \"affinity_proteomics.workflow_state.v1\",\n    \"state_id\": \"sha256:...\",\n    \"lifecycle\": \"ready\",\n    \"state_label\": \"differential-abundance-ready\",\n    \"description\": \"OLINK differential abundance results for Case vs Control are available.\"\n  },\n  \"suggested_actions\": [\n    {\n      \"action_id\": \"show-top-proteins\",\n      \"label\": \"Top Proteins\",\n      \"estimate\": \"~5s\",\n      \"request\": {\n        \"schema\": \"affinity_proteomics.action_request.v1\",\n        \"action\": \"top-proteins\",\n        \"state_schema\": \"affinity_proteomics.workflow_state.v1\",\n        \"state_id\": \"sha256:...\",\n        \"n\": 5,\n        \"platform\": \"olink\",\n        \"contrast\": [\"Case\", \"Control\"],\n        \"total_proteins_tested\": 40,\n        \"significant_proteins\": 5,\n        \"proteins\": [\n          {\"protein_id\": \"OID00001\", \"gene\": \"GENE1\", \"log2fc\": 0.0, \"padj\": \"0.00e+00\"}\n        ]\n      }\n    }\n  ]\n}\n```\n\n## Dependencies\n\n**Required**:\n- `somadata` >= 1.2 — SomaLogic ADAT parsing\n- `scipy` >= 1.10 — statistical tests\n- `statsmodels` >= 0.14 — multiple testing correction\n- `matplotlib` >= 3.7 — plotting\n- `seaborn` >= 0.13 — heatmaps\n- `numpy` >= 1.24 — numerical operations\n- `pandas` >= 2.0 — data manipulation\n- `scikit-learn` >= 1.3 — PCA dimensionality reduction for sample-level QC plots\n\n## Safety\n\n- **Local-first**: All computation runs locally; no data uploaded\n- **Disclaimer**: Every report includes the ClawBio medical disclaimer\n- **Platform-aware**: Applies correct QC and normalisation per platform\n- **No hallucinated science**: All thresholds trace to platform vendor documentation\n\n## Integration with Bio Orchestrator\n\n**Trigger conditions** — the orchestrator routes here when:\n- User mentions Olink, SomaLogic, SomaScan, NPX, ADAT, or affinity proteomics\n- User provides an Olink NPX CSV or SomaLogic ADAT file\n\n**Chaining partners**:\n- `proteomics-de`: Complementary — handles mass-spec LFQ; this skill handles affinity platforms\n- `diff-visualizer`: Downstream — enhanced visualisation of differential abundance results\n\n## Citations\n\n- [Assarsson et al. (2014)](https:\u002F\u002Fpubmed.ncbi.nlm.nih.gov\u002F25057488\u002F) — Olink PEA technology\n- [Gold et al. (2010)](https:\u002F\u002Fpubmed.ncbi.nlm.nih.gov\u002F20829826\u002F) — SOMAmer aptamer technology\n- [OlinkAnalyze](https:\u002F\u002Fcran.r-project.org\u002Fpackage=OlinkAnalyze) — Official Olink R toolkit\n- [somadata](https:\u002F\u002Fpypi.org\u002Fproject\u002Fsomadata\u002F) — Python ADAT parser\n",{"name":5,"license":15,"metadata":24,"description":7},{"tags":25,"author":34,"version":35,"openclaw":36},[26,27,28,29,30,31,32,33],"proteomics","olink","somalogic","somascan","npx","affinity","differential-abundance","biomarker","Reza","0.1.0",{"os":37,"emoji":40,"always":20,"install":41,"homepage":53,"requires":54,"trigger_keywords":57},[38,39],"darwin","linux","🧪",[42,45,47,49,51],{"kind":43,"package":44},"pip","somadata",{"kind":43,"package":46},"scipy",{"kind":43,"package":48},"statsmodels",{"kind":43,"package":50},"seaborn",{"kind":43,"package":52},"scikit-learn","https:\u002F\u002Fgithub.com\u002FClawBio\u002FClawBio",{"bins":55},[56],"python3",[58,59,60,61,26,62,63,64,65],"Olink","SomaLogic","SomaScan","NPX","affinity proteomics","protein biomarker","plasma proteomics","ADAT","master","49e49abf2f670d429e0b7e2c0349739c3fdd5cbe","skills\u002Faffinity-proteomics",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":75,"prompt":84,"zipAvailable":85},[76,78,81],{"tool":30,"command":77},"npx skills add stanfish06\u002Fskillquarium --skill affinity-proteomics",{"tool":79,"command":80},"bunx","bunx skills add stanfish06\u002Fskillquarium --skill affinity-proteomics",{"tool":82,"command":83},"pnpm","pnpm dlx skills add stanfish06\u002Fskillquarium --skill affinity-proteomics","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Faffinity-proteomics\u002FSKILL.md",true,[87,93,99,105,109,113,117],{"path":88,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":91,"sourceHtmlUrl":92},"affinity_proteomics.py","SCRIPT","脚本",39094,"https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Faffinity-proteomics\u002Faffinity_proteomics.py",{"path":94,"resourceType":95,"resourceTypeDesc":96,"sizeBytes":97,"sourceHtmlUrl":98},"agents\u002Fopenai.yaml","REFERENCE","参考文档",174,"https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Faffinity-proteomics\u002Fagents\u002Fopenai.yaml",{"path":100,"resourceType":101,"resourceTypeDesc":102,"sizeBytes":103,"sourceHtmlUrl":104},"example_data\u002Folink_demo_meta.csv","ASSET","资产文件",1904,"https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Faffinity-proteomics\u002Fexample_data\u002Folink_demo_meta.csv",{"path":106,"resourceType":101,"resourceTypeDesc":102,"sizeBytes":107,"sourceHtmlUrl":108},"example_data\u002Folink_demo_npx.csv",276143,"https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Faffinity-proteomics\u002Fexample_data\u002Folink_demo_npx.csv",{"path":110,"resourceType":95,"resourceTypeDesc":96,"sizeBytes":111,"sourceHtmlUrl":112},"requirements.txt",30,"https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Faffinity-proteomics\u002Frequirements.txt",{"path":114,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":115,"sourceHtmlUrl":116},"tests\u002F__init__.py",28,"https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Faffinity-proteomics\u002Ftests\u002F__init__.py",{"path":118,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":119,"sourceHtmlUrl":120},"tests\u002Ftest_affinity_proteomics.py",13881,"https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Faffinity-proteomics\u002Ftests\u002Ftest_affinity_proteomics.py",[122,129,138,145,152,159],{"skillNo":123,"name":124,"nameZh":6,"description":125,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":126,"categories":127,"keywords":128,"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":130,"name":131,"nameZh":6,"description":132,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":133,"licenseFileUrl":134,"sourceHtmlUrl":135,"categories":136,"keywords":137,"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":139,"name":140,"nameZh":6,"description":141,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":133,"licenseFileUrl":6,"sourceHtmlUrl":142,"categories":143,"keywords":144,"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":146,"name":147,"nameZh":6,"description":148,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":149,"categories":150,"keywords":151,"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":153,"name":154,"nameZh":6,"description":155,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":156,"categories":157,"keywords":158,"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":160,"name":161,"nameZh":6,"description":162,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":133,"licenseFileUrl":163,"sourceHtmlUrl":164,"categories":165,"keywords":166,"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",[],[]]