[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-83116":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":9,"language":10,"languages":9,"totalLinesOfCode":9,"stars":11,"forks":12,"watchers":13,"openIssues":14,"contributorsCount":14,"subscribersCount":14,"size":14,"stars1d":12,"stars7d":15,"stars30d":15,"stars90d":14,"forks30d":14,"starsTrendScore":16,"compositeScore":17,"rankGlobal":9,"rankLanguage":9,"license":18,"archived":19,"fork":19,"defaultBranch":20,"hasWiki":19,"hasPages":19,"topics":21,"createdAt":9,"pushedAt":9,"updatedAt":22,"readmeContent":23,"aiSummary":24,"trendingCount":14,"starSnapshotCount":14,"syncStatus":25,"lastSyncTime":26,"discoverSource":27},83116,"biomate-bioconductor-kb","bioMate-AI\u002Fbiomate-bioconductor-kb","bioMate-AI","BioMate-KB Bioconductor Skills — top 100 packages as Claude\u002Fagent skills, vignette-grounded",null,"Python",247,27,12,0,186,132,4.34,"Other",false,"main",[],"2026-06-12 02:04:31","# BioMate-KB — Bioconductor Skills\n\n**Top 100 Bioconductor packages by official download score, formatted as Claude Code Skills.**\n\nA skill bundle in [Claude Code Skills](https:\u002F\u002Fdocs.anthropic.com\u002Fen\u002Fdocs\u002Fclaude-code\u002Fskills-overview) format, covering the most-used 100 Bioconductor packages from the BioMate-KB knowledge base. Each skill teaches Claude when to choose a package, what parameters to set, how to interpret results, and what pitfalls to avoid.\n\n## What's here\n\n```\nskills\u002F\n├── transcriptomics\u002F    (33 skills — DESeq2, edgeR, limma, fgsea, ...)\n├── genomics\u002F           (23 skills — GenomicRanges, Rsamtools, ...)\n├── general\u002F            (16 skills — utility \u002F cross-domain)\n├── proteomics\u002F         (8  skills — MSstats, MSnbase, Spectra, ...)\n├── variant-calling\u002F    (4  skills — VariantAnnotation, maftools, ...)\n├── metagenomics\u002F       (4  skills — phyloseq, ANCOMBC, dada2, ...)\n├── single-cell\u002F        (3  skills — Seurat, scran, scater, ...)\n├── epigenomics\u002F        (3  skills — ChIPseeker, DiffBind, methylKit, ...)\n├── enrichment\u002F         (2  skills — clusterProfiler, ReactomePA, ...)\n├── annotation\u002F         (2  skills — biomaRt, AnnotationHub, ...)\n└── imaging\u002F            (2  skills)\n```\n\nThis bundle is intentionally focused on the **highest-traffic packages** — the top 100 accounts for roughly 60% of all Bioconductor downloads. The full BioMate KB covers all 1,818 active Bioconductor packages and is available via [BioMate Cloud](https:\u002F\u002Fbiomate.ai).\n\nEach `SKILL.md` has:\n- **YAML frontmatter**: `name`, `description`, `when_to_use`, `user-invocable: false`\n- **Best Practices** — what to do and how to configure\n- **Key Parameters** — recommended values with context\n- **Result Interpretation** — how to read outputs\n- **Common Pitfalls** — what to warn users about\n- **Data Requirements** — expected input format\n- **Alternatives** — when to suggest a different package\n\n## Want the full collection?\n\nThis bundle covers the top 100 Bioconductor packages. **[BioMate AI](https:\u002F\u002Fwww.biomate.ai)** gives you:\n\n- **Full coverage** — all 1,818+ active Bioconductor packages plus 2,455 curated workflows across genomics, transcriptomics, proteomics, drug discovery, and more\n- **Efficient parallel computing** — workflows run in the cloud with automatic scaling, no cluster setup required\n- **Output visualization and analysis** — interactive charts, QC dashboards, and AI-generated findings built in\n- **Report generation** — one-click publication-ready methods reports and summary documents\n\n**Start using BioMate AI for free at [www.biomate.ai](https:\u002F\u002Fwww.biomate.ai)**\nQuestions or collaboration inquiries: [contact@biomate.ai](mailto:contact@biomate.ai)\n\n## How to use\n\n```bash\n# Clone\ngit clone https:\u002F\u002Fgithub.com\u002FbioMate-AI\u002Fbiomate-bioconductor-kb.git\ncd biomate-bioconductor-kb\n\n# Install all skills into Claude Code (global)\nfind skills -name \"SKILL.md\" | while read f; do\n  pkg=$(dirname \"$f\" | xargs basename)\n  cp \"$f\" ~\u002F.claude\u002Fskills\u002Fbioconductor-${pkg}.md\ndone\n```\n\nOr copy a single domain:\n\n```bash\n# Only RNA-seq DE skills\nfind skills\u002Ftranscriptomics -name \"SKILL.md\" | while read f; do\n  pkg=$(dirname \"$f\" | xargs basename)\n  cp \"$f\" ~\u002F.claude\u002Fskills\u002Fbioconductor-${pkg}.md\ndone\n```\n\nEach `SKILL.md` is a self-contained Claude Code skill file — Claude discovers it automatically once it's in `~\u002F.claude\u002Fskills\u002F` (global) or `.claude\u002Fskills\u002F` (project-level).\n\n## Ranking source\n\nPackages are ordered by Bioconductor's official monthly download score:\n- Source: \u003Chttps:\u002F\u002Fbioconductor.org\u002Fpackages\u002Fstats\u002Fbioc\u002Fbioc_pkg_scores.tab>\n- Snapshot taken: 2026-05-21\n- Top 100 of 3,058 ranked Bioconductor software packages (covers 3.3% of the catalog by count, ~60% by traffic)\n\n## What this skill bundle does NOT include\n\n- **No execution-layer details**: no Docker images, no Nextflow paths, no AWS Batch \u002F S3 hints, no Galaxy tool IDs, no BioMate-internal identifiers. The skills are knowledge artifacts, not pipeline definitions.\n- **No proprietary workflow wrappers**: the 1,818 executable `.nf` Nextflow modules that BioMate uses to run these packages on AWS Batch are not in this bundle. **For end-to-end cloud execution with managed compute, QC governance, and reproducible outputs, see [BioMate](https:\u002F\u002Fbiomate.ai)**.\n\nThis is intentional — the goal is to give the open-source community the *knowledge* layer, while BioMate Cloud provides the *execution* layer.\n\n## License\n\n- **Skill content** (`skills\u002F**\u002F*.md`, `MANIFEST.json`): **CC-BY-4.0** — share + adapt with attribution.\n- **Extraction scripts** (`extraction\u002F*.py`): **Apache-2.0** — use, modify, distribute.\n- **Underlying Bioconductor packages** retain their own (mostly Artistic-2.0 \u002F GPL) licenses.\n\n## Citation\n\nIf you use this skill bundle in research, please cite:\n\n> BioMate-KB: A Structured, Executable Knowledge Base of Bioconductor Workflows Linking 15,641 Curated Analysis Steps to Galaxy and Nextflow Execution. (2026). bioRxiv. DOI: [pending]\n\n(bioRxiv DOI will replace this stub once the preprint is published.)\n\n## Regenerating the bundle\n\n```bash\n# Re-fetch the latest Bioconductor download scores\ncurl -O https:\u002F\u002Fbioconductor.org\u002Fpackages\u002Fstats\u002Fbioc\u002Fbioc_pkg_scores.tab\n\n# Regenerate the skill bundle (top 100 by default)\npython3 extraction\u002Fgenerate_bundle.py --top 100\n\n# Single package\npython3 extraction\u002Fextract_skill.py \\\\\n    --db \u003Cpath-to-biomate-knowledge-db> \\\\\n    --pkg DESeq2 \\\\\n    --out my-deseq2-skill.md\n```\n\nThe extraction code (`extraction\u002Fextract_skill.py`) is intentionally minimal (~300 lines) and reads only from BioMate's public knowledge fields — `tool_knowledge.{use_cases, limitations, alternatives, recommended_parameters, primary_citation, benchmark_papers}` and `tools.scientific_context`. Execution-layer columns are explicitly blocked via `EXEC_FIELDS_BLOCKLIST`.\n\n## Versioning\n\nThis is **v1.0.0** of the bundle. Future versions will track:\n- New Bioconductor releases (currently pinned to 3.20)\n- Expanded coverage (top-1000 if community demand justifies)\n- Refined SKILL.md sections (Q&A, gotchas, additional examples)\n\n## Contributing\n\nOpen an issue or PR for:\n- Errors in any SKILL.md\n- Suggestions for new sections to extract\n- Packages missing from the top-100 that should be included\n\n## Acknowledgments\n\nBioconductor download statistics published by the Bioconductor Core Team. SKILL.md format from [Anthropic Claude Code](https:\u002F\u002Fdocs.anthropic.com\u002Fen\u002Fdocs\u002Fclaude-code\u002Fskills-overview).\n","BioMate-KB项目将Bioconductor中最常用的100个生物信息学软件包转换为Claude Code Skills格式，旨在帮助用户更好地理解和使用这些工具。该项目的核心功能包括对每个软件包的详细说明文档（SKILL.md），涵盖最佳实践、关键参数设置、结果解读以及常见问题等，确保用户能够高效准确地应用相关工具进行生物数据分析。特别适合于需要频繁使用Bioconductor资源的研究人员或开发者，在转录组学、基因组学、蛋白质组学等多个领域都有广泛应用。此外，通过与BioMate AI平台结合，还能获得更全面的服务支持，如云端并行计算能力及可视化报告生成等。",2,"2026-06-11 04:10:09","CREATED_QUERY"]