GITHUB AGENT SKILLS / 技能收录
给你的 AI 助手
装上专业技能
我们从 GitHub 持续收录、审核并分类优质的 Agent Skills，按职业与使用场景整理，复制一行命令即可安装到 Claude Code、Cursor 等智能体。
按职业浏览 Agent Skills
为不同岗位挑选的高频技能
按使用场景浏览 Agent Skills
从你要完成的任务出发
按创作者浏览 Agent Skills
按 GitHub Stars 排序的优秀创作者
Microsoft
@microsoft
openclaw
@openclaw
OpenAI
@openai
The Apache Software Foundation
@apache
GitHub
@github
Anthropic
@anthropics
AutoGPT
@Significant-Gravitas
Garry Tan
@garrytan全部 Skills 196921
dup-name
Use when doing a-things.
tooluniverse-precision-oncology
Provide actionable treatment recommendations for cancer patients based on molecular profile. Interprets tumor mutations, identifies FDA-approved therapies, finds resistance mechanisms, matches clinical trials. Use when oncologist asks about treatment options for specific mutations (EGFR, KRAS, BRAF, etc.), therapy resistance, or clinical trial eligibility.
broken-superskill
Use when exercising superskill audit checks against fixtures.
Broken_Skill
TODO fill this in later
tooluniverse-precision-medicine-stratification
Comprehensive patient stratification for precision medicine by integrating genomic, clinical, and therapeutic data. Given a disease/condition, genomic data (germline variants, somatic mutations, expression), and optional clinical parameters, performs multi-phase analysis covering disease disambiguation, genetic risk assessment, disease-specific molecular stratification, pharmacogenomic profiling, comorbidity/DDI risk, pathway analysis, clinical evidence and guideline mapping, clinical trial matching, and integrated outcome prediction. Generates a quantitative Precision Medicine Risk Score (0-100) with risk tier assignment, treatment algorithm, pharmacogenomic guidance, clinical trial matches, and monitoring plan.
skill-standards
Use when creating, updating, reviewing, or auditing a skill or superskill and you need a concrete quality bar for triggers, project grounding, metadata, authorship, routing, context efficiency, scripts, and validation.
tooluniverse-population-genetics-1000genomes
Population genetics research using the 1000 Genomes Project (IGSR) -- search populations by superpopulation ancestry (AFR, AMR, EAS, EUR, SAS), retrieve samples by population code, list available data collections, and integrate with GWAS tools for population stratification analysis. Use when users ask about 1000 Genomes populations, sample ancestry, allele frequency variation across continental groups, population-specific GWAS interpretation, or IGSR data collections like the 30x high-coverage resequencing or HGSVC.
tooluniverse-polygenic-risk-score
Build and interpret polygenic risk scores (PRS) for complex diseases using GWAS summary statistics. Calculates genetic risk profiles, interprets PRS percentiles, and assesses disease predisposition across conditions including type 2 diabetes, coronary artery disease, and Alzheimer's disease. Use when asked to calculate polygenic risk scores, interpret genetic risk for complex diseases, build custom PRS from GWAS data, or answer questions like "What is my genetic predisposition to breast cancer?"
tooluniverse-plant-genomics
Research plant genes, pathways, and species using PlantReactome, Ensembl Plants, POWO, UniProt, KEGG, and literature tools. Covers plant pathway analysis, gene function annotation, species identification, crop genomics, and comparative plant biology. Use when asked about plant genes, Arabidopsis, crop improvement, plant pathways, plant metabolism, photosynthesis, plant development, or plant species identification.
greenfield-parity
Use when judging whether a codebase (or a change) carries more complexity than its current spec needs — "would we build it this way from scratch?", "is this over-engineered for what it does", "this reads vibe-coded", "reconcile the existing complexity against the goal" — and when an audit that files beads must be re-runnable without duplicating findings already in the backlog. Pre-production codebases where rewrite is on the table are the primary case.
tooluniverse-phylogenetics
Production-ready phylogenetics and sequence analysis skill for alignment processing, tree analysis, and evolutionary metrics. Computes treeness, RCV, treeness/RCV, parsimony informative sites, evolutionary rate, DVMC, tree length, alignment gap statistics, GC content, and bootstrap support using PhyKIT, Biopython, and DendroPy. Performs NJ/UPGMA/parsimony tree construction, Robinson-Foulds distance, Mann-Whitney U tests, and batch analysis across gene families. Integrates with ToolUniverse for sequence retrieval (NCBI, UniProt, Ensembl) and tree annotation. Use when processing FASTA/PHYLIP/Nexus/Newick files, computing phylogenetic metrics, comparing taxa groups, or answering questions about alignments, trees, parsimony, or molecular evolution.
tooluniverse-pharmacovigilance
Analyze drug safety signals from FDA adverse event reports, label warnings, and pharmacogenomic data. Calculates disproportionality measures (PRR, ROR), identifies serious adverse events, assesses pharmacogenomic risk variants. Use when asked about drug safety, adverse events, post-market surveillance, or risk-benefit assessment.
excalidraw-diagram
Use when the user wants a workflow, architecture, protocol, concept, or Mermaid diagram converted into or out of Excalidraw, especially when the result should teach through structure, flow, and concrete evidence.
engineering-bar
Use when implementing or reviewing any non-trivial change and you need the canonical engineering quality bar — default biases, definition of done, and reviewable expectations — or when authoring a project's about/craft-and-care pillar that should reference this bar instead of restating it.
tooluniverse-pharmacogenomics
Guide pharmacogenomics (PGx) research -- drug-gene interaction lookup, CPIC guideline retrieval, variant-drug annotation, allele function status, FDA biomarker labeling, and clinical dosing recommendations. Covers the full CPIC-to-PharmGKB-to-clinical-recommendation workflow. Use when users ask about pharmacogenomics, drug-gene interactions, CPIC guidelines, genotype-guided dosing, PGx biomarkers, CYP enzyme phenotypes, or star allele interpretation.
tooluniverse-pathway-disease-genetics
Connect GWAS variants to biological pathways for drug target discovery. Maps disease-associated SNPs to causal genes via eQTL colocalization (GTEx), links genes to enriched pathways (Reactome, KEGG, MetaCyc), and identifies druggable targets within disease-relevant pathways. Use when asked to translate GWAS findings into mechanistic insights, find pathways enriched for disease genes, discover drug targets from genetic evidence, or answer questions like "What pathways are disrupted in type 2 diabetes based on GWAS data?"
documentation
Use when creating, reviewing, or auditing a codebase's documentation — README and docs/ trees, architecture/workflow diagrams, API references, formal doc sites (OpenAPI, MkDocs, Sphinx, ReadTheDocs) — and you need the bar for accessibility (concise synthesis, diagrams where structure beats prose) and accuracy over time (code-cited facts under an explicit maintenance contract).
diagnosis
Use when diagnosing a hard bug, intermittent/flaky failure, or performance regression and you need the evidence bar for the diagnosis itself — a repeatable feedback loop, ranked falsifiable hypotheses before instrumentation, tagged debug logging that gets cleaned up, and a regression test at the correct seam. Complements process skills like systematic-debugging: this is the bar for what counts as a verified root cause, not a debugging walkthrough.