AGENT SKILLS · 任务装备
值得安装的 Agent Skills
汇总公开仓库中已验证的 Skills。安装前先看清它能做什么、包内包含什么、热度如何，以及来源是否可靠。
- 目录范围
- 已验证
- Skills
- 23,248
- 仓库
- 3589
- 最近同步
- 2026年11月4日
sjuneparkaddress-issues
Resolve a specified GitHub issue or a confirmed queue of issues through validated, reviewed, merged PRs. Explicit invocation only.
- 1小时安装量
- 1
- GitHub Stars
- 1
- 最近更新
- 9月10日
sjuneparkaddress-pr-feedback
Address existing GitHub PR feedback from human or bot reviewers end to end, including stacked PR chains.
- 1小时安装量
- 1
- GitHub Stars
- 1
- 最近更新
- 9月10日
sjuneparkagents-md-writer
Design or audit AGENTS.md and tool-specific instruction hierarchies for nested scope, conflicts, legacy or cross-tool migration, bloat, discovery, or precedence failures.
- 1小时安装量
- 1
- GitHub Stars
- 1
- 最近更新
- 9月10日
sjuneparkexplore-repo
Explore external GitHub or Git source from the centralized ~/.repos cache for pinned refs, upstream comparison, or delegated repository inspection.
- 1小时安装量
- 1
- GitHub Stars
- 1
- 最近更新
- 9月10日
sjuneparkmerge-branch
Integrate Git branches deliberately: plan or dry-run merges, transplant work, resolve conflicts, or audit completed or in-progress merges.
- 1小时安装量
- 1
- GitHub Stars
- 1
- 最近更新
- 9月10日
sjuneparkteach
Teach design-level mental models of existing source code and explain behavioral changes in diffs, commits, patches, or file comparisons. Use when a learner asks how a focused subsystem, feature, whole project, or change works.
- 1小时安装量
- 1
- GitHub Stars
- 1
- 最近更新
- 9月10日
gil-1codex-pr-review
Run Codex validation on an existing GitHub PR. Use when waiting for Codex status, delegating review fixes to a sub-agent, investigating repeated feedback patterns, and repeating until Codex approves, blocks with evidence, or times out.
- 1小时安装量
- 1
- GitHub Stars
- 0
- 最近更新
- 8月22日
gil-1project-architecture-report
Creates a standalone HTML report that maps a codebase: structure, flows, dependencies, data model, symbols, risks, gaps, and likely next needs. Use when the user asks for architecture analysis, dependency or flow mapping, an HTML project report, or scripts/sub-agents to list files, functions, classes, and interfaces.
- 1小时安装量
- 1
- GitHub Stars
- 0
- 最近更新
- 8月22日
gil-1project-folder-structure
Audits and improves project or workspace organization using constraint-first, project-neutral structure rules. Use when Codex needs to scan, reorganize, declutter, or decide where files belong in any app, library, service, data/ML project, infrastructure repo, docs/content project, automation repo, creative asset project, workspace folder, or mixed monorepo.
- 1小时安装量
- 1
- GitHub Stars
- 0
- 最近更新
- 8月22日
sjuneparkconsult-mytech
Consult mytech technical preferences to guide a coding task or assess a project's alignment. Explicit invocation only.
- 1小时安装量
- 1
- GitHub Stars
- 0
- 最近更新
- 9月10日
sickn33yann-lecun
Agente que simula Yann LeCun — inventor das Convolutional Neural Networks, Chief AI Scientist da Meta, Prêmio Turing 2018.
- 1小时安装量
- 1
- GitHub Stars
- 4.6万
- 最近更新
- 9月9日
google-deepmindalphagenome-atlas-website-links
- Constructs deep-links and URLs for the AlphaGenome Atlas website. Supports generating single-variant exploration links (1-based chr:pos:refalt), genomic locus views (1-based closed chr:start-end), candidate summary tables, and AlphaGenome reference vs. alternate predictions. Use whenever visualizing, exploring, charting, or linking genetic variants and genomic loci on the AlphaGenome Atlas, or when asked to inspect, view, or link predictions for a genomic variant.
- 1小时安装量
- 1
- GitHub Stars
- 2984
- 最近更新
- 9月8日
google-deepmindalphagenome-variant-impact-score
- Score, annotate, and analyze the functional impact of genetic variants using AlphaGenome Variant Impact (AVI) scores. Query variants in chr:pos:refalt format, annotate VCF/tabular callsets, perform saturation mutagenesis window scans (1-based closed chr:start-end), and extract GENCODE v46 GTF gene/exon/junction coordinates all via the AlphaGenome Atlas API.
- 1小时安装量
- 1
- GitHub Stars
- 2984
- 最近更新
- 9月8日
google-deepmindensembl-database
Query the Ensembl database to resolve gene, transcript, and protein IDs, fetch genomic or protein sequences, retrieve gene structures (exons), and get variant consequence and effect predictions (VEP). Use this skill as a primary ID translator, genomic sequence database and variant effect prediction tool.
- 1小时安装量
- 1
- GitHub Stars
- 2984
- 最近更新
- 9月8日
google-deepmindgtex-database
Use when you want to retrieve quantitative RNA expression data and variant eQTL information from the GTEx (Genotype-Tissue Expression) Project across 54 non-diseased tissue sites.
- 1小时安装量
- 1
- GitHub Stars
- 2984
- 最近更新
- 9月8日
google-deepmindjaspar-database
Query the JASPAR database for Transcription Factor (TF) binding profiles. Use when retrieving Position Frequency Matrices (PFMs) or Position Weight Matrices (PWMs) for specific TFs, resolving gene symbols to JASPAR Matrix IDs, or getting TF metadata. Supports multiple output formats (MEME, TRANSFAC, PFM, JASPAR, YAML).
- 1小时安装量
- 1
- GitHub Stars
- 2984
- 最近更新
- 9月8日
google-deepmindliterature-search-biorxiv
Browse, filter, and download life sciences, biology, and medical preprints from bioRxiv and medRxiv. Supports fetching paper metadata by DOI, and browsing by date range with category and keyword filters. Keyword filtering is local, so date ranges MUST be narrow (1-4 weeks) with a category to prevent timeouts.
- 1小时安装量
- 1
- GitHub Stars
- 2984
- 最近更新
- 9月8日
google-deepmindopentargets-database
Query Open Targets Platform for target-disease associations, drug target discovery, tractability/safety data, genetics/omics evidence, known drugs, for therapeutic target identification.
- 1小时安装量
- 1
- GitHub Stars
- 2984
- 最近更新
- 9月8日
google-deepmindprotein-sequence-msa
Performs multiple sequence alignment of proteins with EBI Clustal Omega. Use when you need to align multiple sequences to assess similarity, domain conservation, or key residue conservation. Supports up to 4000 sequences and a maximum file size of 4 MB. Do not use to search for homologous proteins in a database (use MMseqs2, BLAST), align non-protein sequences (DNA, RNA), perform structural alignment (use Foldseek, PyMOL), or if you only have a single sequence.
- 1小时安装量
- 1
- GitHub Stars
- 2984
- 最近更新
- 9月8日
google-deepmindreactome-database
Query the Reactome database (Analysis and Content Services). Use when the user asks about pathway analysis, gene list enrichment, retrieving results by token, finding unmapped or not-found identifiers, mapping identifiers, reaction participants (inputs, outputs), pathway hierarchy (including top-level pathways), diagram export, cross-reference mapping, or searching the knowledgebase.
- 1小时安装量
- 1
- GitHub Stars
- 2984
- 最近更新
- 9月8日
google-deepminduniprot-database
- Access protein metadata, function, taxonomy, and sequences across UniProtKB, UniParc, and UniRef. Use when searching for proteins, mapping identifiers, or retrieving functional annotations and publications. Don't use for sequence alignment, protein folding, or sequence similarity search (use specialized skills for those tasks).
- 1小时安装量
- 1
- GitHub Stars
- 2984
- 最近更新
- 9月8日
google-deepmindworkflow-skill-creator
Distills a completed user workflow or interaction into a reusable agent skill. Use when the user asks to turn their workflow, interaction, or multi-step process into a skill, or when they say "make this a skill", "create a skill from what we just did", "package this workflow" or similar. Do not use for creating skills from scratch without an existing workflow (use a generic skill-creator for that).
- 1小时安装量
- 1
- GitHub Stars
- 2984
- 最近更新
- 9月8日
jeremylongshoreconsul-service-discovery
'Manage consul service discovery operations. Auto-activating skill for DevOps Advanced. Triggers on: consul service discovery, consul service discovery Part of the DevOps Advanced skill category. Use when working with consul service discovery functionality. Trigger with phrases like "consul service discovery", "consul discovery", "consul". '
- 1小时安装量
- 1
- GitHub Stars
- 2714
- 最近更新
- 9月10日
borgheisales-operations
Sales operations across CRM, analytics, territory planning, and compensation. Use when building pipeline reports, designing territories, setting quotas, creating comp plans, or auditing CRM data quality.
- 1小时安装量
- 1
- GitHub Stars
- 732
- 最近更新
- 8月12日