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
@microsoftopenclaw
@openclawAnthropic
@anthropicsOpenAI
@openaiThe Apache Software Foundation
@apacheGitHub
@githubAutoGPT
@Significant-GravitasGarry Tan
@garrytan全部 Skills 482556
network-scientist
Think and work like an expert Network Scientist. Use when a task calls for Network Scientist judgment. Reasons from adjacency structure, generative models, and null hypotheses through configuration-model and SBM/ERGM nulls, CSN power-law fitting with log-normal Vuong tests, and multi-algorithm community detection (Louvain, Leiden, Infomap, graph-tool) while treating artifactual scale-free tails from correlation thresholding, modularity's resolution bias, force-directed hairball over-interpretation, and test-edge leakage in link prediction as first-class failure modes.
network-engineer
Think and work like an expert Network Engineer. Use when a task calls for Network Engineer judgment. Reasons from OSI layering, control vs. data plane, and path symmetry through BGP policy (TCP/179, communities, RR), OSPF areas/LSA adjacency, 802.1Q VLAN/trunk design, spine-leaf Clos/VXLAN-EVPN fabrics, and L1→L7 troubleshooting while treating asymmetric routing, MTU black holes, native-VLAN mismatch, and BGP OutQ/hold-time flaps as first-class failure modes.
naval-architect
Think and work like an expert Naval Architect. Use when a task calls for Naval Architect judgment. Reasons from displacement, Bonjean/KN–GZ stability, ITTC-78 resistance extrapolation, Wageningen B-series propulsion, WAMIT/NEMOH seakeeping, and IACS CSR scantlings while treating Froude/Re scale mismatch, free-surface GM error, Holtrop range violations, and trial CA bias as first-class failure modes.
natural-products-chemist
Think and work like an expert Natural Products Chemist. Use when a task calls for Natural Products Chemist judgment. Reasons from dereplication (GNPS FBMN, NPAtlas, SNAP-MS, COCONUT), bioassay-guided and MS-triggered isolation, NMR/HRMS structure tiers (DP4+/DU8+), antiSMASH/MIBiG BGC linkage, and PAINS/IMP assay interference while treating HMBC ambiguity, stereochemical misassignment, and aggregator false positives as first-class failure modes.
natural-language-processing-scientist
Think and work like an expert Natural Language Processing Scientist. Use when a task calls for Natural Language Processing Scientist judgment. Reasons from tokenization, data curation (datatrove/NeMo), and evaluation protocols (SacreBLEU/COMET, IFEval, HELM); enforces contamination audits (ConTAM, perplexity separation), paired bootstrap significance, SFT→DPO/RLHF with alignment-tax checks, and ARR/Dodge reproducibility while treating exposure bias, benchmark leakage, prompt-template confounds, and metric gaming as first-class failure modes.
nanotechnologist
Think and work like an expert Nanotechnologist. Use when a task calls for Nanotechnologist judgment. Reasons from length-scale manufacturing limits, EUV/NIL/EBL patterning, DSA defectivity, and interface-controlled integration through CD-SEM/AFM/TEM metrology, SEMI E10 yield discipline, and ISO 80004/FDA nanomaterial reporting while treating SEM shrinkage, NIL residual-layer non-uniformity, overlay error, and cherry-picked die yield as first-class failure modes.
nanophysicist
Think and work like an expert Nanophysicist. Use when a task calls for Nanophysicist judgment. Reasons from quantum confinement dimensionality, Coulomb diamonds and SET conditions, Kondo vs Luttinger-liquid power laws, and lock-in cryostat transport through STM/STS, AFM/KPFM, and STEM/EELS while treating charging artifacts, tip convolution, contact resistance, and beam-damage plasmon shifts as first-class failure modes.
nanomaterials-scientist
Think and work like an expert Nanomaterials Scientist. Use when a task calls for Nanomaterials Scientist judgment. Reasons from size-dependent thermodynamics, surface-to-volume ratio, and DLVO colloidal stability through TEM/STEM statistics, DLS/NTA, XRD Scherrer, XPS, ICP-MS, and PL quantum-yield methods while treating aggregation, beam damage, intensity-weighted DLS sizing bias, and Ostwald ripening as first-class failure modes.
mycologist
Think and work like an expert Mycologist. Use when a task calls for Mycologist judgment. Reasons from fungal life cycles, voucher-first taxonomy, and integrated sporocarp–culture–ITS/multilocus workflows; uses MycoBank/UNITE/MaarjAM, FUSARIUM-ID, EPPO Q-bank, and MycoCosm while treating rich-media non-sporulation, ITS saturation in Fusarium/Penicillium, AMF SSU vs ITS misuse, environmental-DNA-only names, and BSL-3 dimorphic mould handling as first-class failure modes.
mycobacteriologist
Think and work like an expert Mycobacteriologist. Use when a task calls for Mycobacteriologist judgment. Reasons from slow-growing acid-fast bacilli, knife-edge NALC-NaOH decontamination, and BSL-3 aerosol risk through MGIT culture, Xpert MTB/RIF and line-probe assays, MALDI-TOF and WGS resistance calls against the WHO mutation catalog while treating over-decontamination false negatives, laboratory cross-contamination pseudo-outbreaks, and NTM colonizer-versus-disease misclassification as first-class failure modes.
molecular-virologist
Think and work like an expert Molecular Virologist. Use when a task calls for Molecular Virologist judgment. Reasons from Baltimore mRNA pathways, RNP/polymerase biochemistry, cap-snatching and expression strategy, CPER/BAC/trVLP rescue, protease cis/trans mapping, viral-factory LLPS, and CRISPR host-factor screens (Brunello/MAGeCK/replicon/TRPPC) with iCLIP/ChIP-seq—while treating CPER PCR errors, DIP packaging competition, minigenome structural-protein signal, and uninfected CRISPR dropout as first-class failure modes.
molecular-pathologist
Think and work like an expert Molecular Pathologist. Use when a task calls for Molecular Pathologist judgment. Reasons from tumor cellularity, assay-specific LOD, and AMP/ASCO/CAP Tier I–IV classification; validates IHC (CAP ≥90% concordance), FISH (HER2/ALK break-apart), and NGS oncology panels under CAP/CLIA MM09 while treating FFPE deamination, HER2-low/ultralow scoring, PD-L1 TPS vs CPS, and ctDNA CHIP as first-class failure modes.
molecular-neuroscientist
Think and work like an expert Molecular Neuroscientist. Use when a task calls for Molecular Neuroscientist judgment. Reasons from NPQ transmission, AMPAR/NMDAR trafficking, monoamine receptor/transporter systems, optogenetics (ChR2/Chrimson/ACR) with retinal-artifact controls, AAV/rabies circuit tracing, and region RNA-seq with DESeq2/SynGO—integrating synaptic biochemistry, perturbation, and omics while treating mini-detection bias, TVA leak, and batch/composition confounds as first-class failure modes.
molecular-geneticist
Think and work like an expert Molecular Geneticist. Use when a task calls for Molecular Geneticist judgment. Reasons from sequence-as-hypothesis, reference context (genome build, MANE/RefSeq transcript, HGVS), and allele-level molecular consequence through ACMG/AMP-ClinGen criteria, IGV/VEP/SpliceAI/gnomAD/ClinVar review, MIQE-compliant qPCR/ddPCR, and Sanger/NGS validation while treating allele dropout, pseudogene/paralog misalignment, FFPE deamination, contamination and barcode bleed, and transcript/build mismatch as first-class failure modes.
molecular-ecologist
Think and work like an expert Molecular Ecologist. Use when a task calls for Molecular Ecologist judgment. Reasons from population genetics, eDNA/metabarcoding, and marker choice (microsatellites, SNPs, mtDNA); analyzes with STRUCTURE/ADMIXTURE, hierfstat FST, DADA2 pipelines, and ddPCR; treats null alleles, Wahlund effect, batch effects, and eDNA allelic dropout as first-class failure modes.
molecular-biologist
Think and work like an expert Molecular Biologist. Use when a task calls for Molecular Biologist judgment. Reasons from central-dogma sequence flow, binding affinity (Kd/Km/kcat), gene regulation, and biological-versus-technical replicate structure through MIQE-compliant RT-qPCR, ddPCR, Western/flow/microscopy, CRISPR editing with rescue, and IWGAV antibody validation while treating off-target reagent effects, batch effects, mycoplasma and cell-line misidentification, and toxicity-driven artifacts as first-class failure modes.
mlops-engineer
Think and work like an expert MLOps Engineer. Use when a task calls for MLOps Engineer judgment. Reasons from data contracts, feature parity, evaluation gates, and rollback-readiness through MLflow/W&B registries, Feast feature stores, KServe/Triton serving, Great Expectations/TFDV validation, and Evidently PSI/KS drift monitors while treating train-serve skew, data leakage, silent degradation, and schema/concept drift as first-class failure modes.
mining-geologist
Think and work like an expert Mining Geologist. Use when a task calls for Mining Geologist judgment. Reasons from deposit-type models (porphyry, VMS, SEDEX, orogenic Au, IOCG, skarn) through oriented core logging, domaining, variography, OK/MIK/LUC estimation, and Chain-of-Mining reconciliation to JORC Table 1, NI 43-101 Item 14, and CIM MRMR reporting; uses Leapfrog, GIM Suite/MX Deposit, and Parker F-series factors while treating support/compositing errors, batch QA/QC failures, OK smoothing bias, and Inferred-overclaim as first-class failure modes.