AI & ML

stanfish06 Bundle

Expert-thinking profile for Spintronics Physicist (thin-film fab / magneto-transport / spin dynamics (ST-FMR, MTJ/SOT) / micromagnetics): Reasons from spin-orbit coupling, spin diffusion length, exchange and DMI, and spin-dependent transport through MTJ/TMR characterization, ST-FMR and harmonic-Hall torque measurement, nonlocal spin valves, and Valet-Fert and MuMax3/OOMMF modeling, while treating barrier pinholes and shunt paths...

stanfish06 Bundle

Expert-thinking profile for Mathematical Modeler (mechanistic modeling / ODE-PDE & agent-based / identifiability & UQ / calibration & inverse problems): Reasons from nondimensionalization, conservation/positivity laws, and minimal-viable model structure through mechanistic ODE/PDE, stochastic, and agent-based formulations, profile-likelihood and Fisher-information identifiability, and Sobol/Morris sensitivity analysis, while treating sloppy unidentifiable parameters...

stanfish06 Bundle

Expert-thinking profile for Carbon Cycle Scientist (flux towers / atmospheric inversions / GHG inventories / isotopic constraints / Earth-system model evaluation): Reasons from carbon mass balance across reservoirs and timescales, sign conventions, and budget closure through the Global Carbon Budget protocol, ONEFlux/REddyProc eddy- covariance processing, atmospheric inversions (CarbonTracker, CAMS, GEOS-Chem), Δ¹⁴C/δ¹³C isotopic partitioning, and ILAMB model evaluation while...

stanfish06 Bundle

Eval-driven skill tuning. Given a task and an LLM-judge rubric, iteratively rewrites a SKILL.md until a downstream executor agent performs well against the judge. Low-code: all evaluation is LLM-as-judge, not deterministic Python.

stanfish06 Bundle

Expert-thinking profile for Deep Learning Scientist (computational / architecture & large-scale training): Reasons from CNN/Transformer inductive bias, Li et al. loss landscapes, grokking/mode connectivity, and Kaplan/Chinchilla scaling (~20 tokens/param); designs ResNet/ViT/DiT/MoE/FlashAttention stacks with FLOPs-matched ablations; trains AdamW+cosine/WSD via Megatron-FSDP/DeepSpeed; evaluates FID/MMLU- Pro/MMLU-CF with...

stanfish06 Bundle

Expert-thinking profile for Environmental Scientist (fate & transport / exposure-risk assessment / groundwater & remediation / environmental chemistry / regulatory (CERCLA, SW-846)): Reasons from source-pathway-receptor linkages, multimedia partitioning, and dose-as-exposure through conceptual site models, fate models (MODFLOW/MT3DMS, AERMOD), SW-846 QA/QC chains, and ProUCL/Mann-Kendall statistics while treating censoring bias, conceptual-model error, well-construction artifacts, and seasonal...

stanfish06 Bundle

Compute pairwise r² between a lead variant and every variant in a window using the 1000 Genomes Phase 3 GRCh38 reference panel, ancestry-stratified. Use when an agent needs LD coloring for a regional plot or LD pruning around a candidate causal variant. Single client (on-demand region fetch from EBI 1000G FTP); no multi-GB cold-start.

stanfish06 Bundle

Expert-thinking profile for Translational Researcher (preclinical / IND-IDE-enabling / early clinical PoC & biomarker translation): Reasons from T0–T4 stage gates, murine vs NHP translatability, PK/PD allometric bridging, MRSD/MABEL FIH dose selection, BEST/CLIA/CAP biomarker tiers, and CONSORT/SPIRIT/STROBE reporting while treating target-wrong, model-wrong, non-predictive biomarker, and preclinical irreproducibility as first-class failure modes.

stanfish06 Bundle

Zoom Meeting SDK for Android native apps. Use when embedding Zoom meetings in Android with default/custom UI, PKCE + SDK auth, join/start flows, and Meeting SDK API integration.

stanfish06 Bundle

Zoom Meeting SDK for Windows - Native C++ SDK for embedding Zoom meetings into Windows desktop applications. Supports custom UI architecture with raw video/audio data, headless bots, and deep integration with meeting features. Includes SDK architecture patterns and Windows message loop handling.

stanfish06 Skill

LLM and agent observability, tracing, and evaluation workflows with langfuse, phoenix-cli, and phoenix-evals. Use when instrumenting Langfuse, Phoenix, OpenTelemetry GenAI traces, eval datasets, prompt experiments, latency/cost debugging, trace scoring, or regression testing agent behavior.

stanfish06 Skill

Migrate a .NET Framework (4.x) project or solution to modern .NET (10), the large cross-runtime jump — not a version bump. USE FOR: ".NET Framework migration", "netfx to net", porting net48/net472 to net10.0 (or net8.0/net9.0), assessment with the .NET Upgrade Assistant / GitHub Copilot app modernization ("modernize .NET") / apiport, converting old-style .csproj to SDK-style, "packages.config" → <PackageReference>, replacing System.Configuration, "WCF migration" to CoreWCF or gRPC, porting System.Web/ASP.NET to ASP.NET Core, multi-targeting during transition, and Framework→Core breaking changes (BinaryFormatter, ICU globalization, config model). DO NOT USE FOR: bumping between modern .NET versions (net8→net9→net10 — use the migrate-dotnetN-to-dotnetN+1 skills), greenfield .NET projects, or trimming/AOT concerns (use dotnet-aot-compat).

stanfish06 Bundle

Expert-thinking profile for Edge / Embedded AI Engineer (embedded firmware / on-device inference): Reasons from tensor-arena budgets, full-int8 PTQ with representative calibration, and TFLM/CMSIS-NN or Vela/Ethos-U compile paths through ONNX Runtime QNN HTP and mobile delegates—treating train–serve preprocessing skew, float thresholds on quantized outputs, and NPU operator fallback as first-class failure modes.

stanfish06 Bundle

Expert-thinking profile for Electromagnetics Engineer (RF/microwave / full-wave simulation / VNA measurement / EMC-SAR): Reasons from Maxwell scaling and S-parameters through HFSS/CST/ADS workflows, SOLT/TRL calibration, mesh ΔS convergence, Smith-chart matching, anechoic OTA, and CISPR/FCC Part 15 / IEC-IEEE 62209-1528 SAR compliance while treating PML reflections, probe de-embedding, and chamber ripple as first-class failure modes.

stanfish06 Skill

Expert guidance for LlamaIndex development including RAG applications, vector stores, document processing, query engines, and building production AI applications.

stanfish06 Bundle

Perform language and framework specific security best-practice reviews and suggest improvements. Use when the user explicitly requests security best practices guidance, a security review or report, or secure-by-default coding help. Supports Python, JavaScript/TypeScript, and Go. Do NOT use for general code review, debugging, threat modeling (use threat-model), or non-security tasks.

stanfish06 Bundle

Expert-thinking profile for Formal Methods Researcher (theoretical / verification / interactive proof & model checking): Reasons from operational semantics and temporal logics through SPIN/TLA+/PRISM, Coq/Lean/Isabelle, Z3/CVC5, refinement and separation logic, vacuity and false-positive diagnosis, and Dafny/F* versus property-based testing boundaries.

stanfish06 Bundle

Fetch a region of GWAS summary statistics from the NHGRI-EBI GWAS Catalog harmonised collection via tabix-on-FTP. Use when an agent needs GWAS beta / SE / p-value for every variant in a window for one specific study (GCST accession). Input: accession, chromosome, start, end. Output: harmonised TSV slice in canonical format.

stanfish06 Bundle

Expert-thinking profile for Machine Learning Engineer (production ML / MLOps / feature stores & serving): Reasons from feature-store point-in-time joins (Feast/Tecton), Airflow/Kubeflow training pipelines, MLflow registry, Triton/TorchServe/BentoML serving, Evidently/WhyLabs drift and PSI, shadow/canary/A/B rollouts, inference SLAs, and reproducible training hashes while treating train–serve skew, label leakage, and...

stanfish06 Bundle

Expert-thinking profile for Neuroimaging Scientist (clinical / research): Reasons from k-space acquisition physics, BOLD hemodynamics, and per-voxel statistical models through fMRIPrep/QSIPrep BIDS pipelines, FSL/SPM/nilearn analysis, neuroCombat harmonization, and TFCE/permutation inference while treating head motion, partial- volume and reference-region errors in PET, global-signal...

stanfish06 Bundle

Expert-thinking profile for Physical Oceanographer (observational / field / computational ocean physics): Reasons from geostrophy, thermal wind, PV, and Ekman/Sverdrup balances; integrates GO-SHIP/CCHDO sections, Argo DMQC, DUACS/CMEMS altimetry, and ROMS/MITgcm/NEMO validation while treating reference-level transport ambiguity, Argo conductivity drift, and MDT/alias artifacts as first-class failure modes.

stanfish06 Bundle

Expert-thinking profile for Quantitative Biologist (computational / live-imaging / dynamical systems biology): Reasons from SBML/PEtab ODE models, structural and profile-likelihood identifiability, Bayesian inference (Stan/PyMC/AMICI), and live- cell pipelines (Cellpose/TrackMate/PhotoFiTT, REMBI); treats sloppiness, phototoxicity, and segmentation-tracking artifacts as first-class failure modes.

stanfish06 Bundle

Expert-thinking profile for Stellar Astrophysicist (stellar evolution modeling / spectroscopy + photometry / asteroseismology / multi-messenger observation / MESA simulation): Reasons from stellar structure, nucleosynthesis, radiative transfer, and the distance ladder through MESA evolution models, spectroscopic and asteroseismic fitting, Gaia astrometry, and MCMC/nested-sampling inference while treating PSF and flat-field artifacts, telluric contamination, Malmquist and Eddington selection...

stanfish06 Bundle

Runs 16S/ITS amplicon (microbiome) analysis with the QIIME 2 amplicon distribution (2026.1; renamed to "qiime2" in 2026.4) in the correct order: manifest import, cutadapt trim-paired primer removal BEFORE dada2 denoise-paired (trunc-len chosen from the demux quality .qzv), feature-classifier classify-sklearn against a version-matched SILVA 138 or Greengenes2 classifier, and diversity core-metrics-phylogenetic — teaching the .qza/.qzv artifact-and-provenance model and the 2026.1 feature-table summarize change (the former summarize_plus). Use when the request mentions QIIME2, QIIME 2, qiime, 16S, 18S, ITS, amplicon, microbiome, ASV, DADA2 denoising, feature table, taxonomic classification, or core-metrics diversity. For downstream alpha/beta diversity, PCoA, and PERMANOVA on the exported feature table prefer alterlab-scikit-bio; this is conda-only (no pip install). Part of the AlterLab Academic Skills suite.

stanfish06 Bundle

Zoom Virtual Agent iOS integration via WKWebView. Use for Swift/Objective-C script injection, message handlers, support_handoff relay, and URL routing policies.

stanfish06 Bundle

Zoom Meeting SDK for Electron desktop applications. Use when embedding Zoom meetings in an Electron app with the Node addon wrapper, JWT auth, join/start flows, settings controllers, and raw data integration.

stanfish06 Bundle

Expert-thinking profile for Causal Inference Scientist (DAGs / potential outcomes / quasi-experiments (DiD, RD, IV) / doubly-robust estimation / sensitivity analysis): Reasons from structural causal models, potential outcomes, and identification logic through DAGs and do-calculus, doubly-robust estimators (AIPW/TMLE, IPTW, g-formula), and design-based methods (IV, RD, Callaway-Sant'Anna DiD, synthetic control) while treating colliders and M-bias, positivity/overlap failure, and...

stanfish06 Bundle

Expert-thinking profile for Cognitive Neuroscientist (human experimental / fMRI–EEG–MEG / behavioral cognitive neuroscience): Reasons from latent constructs through converging behavior, fMRI/M/EEG, TMS, and lesion evidence; designs factorial and dissociation contrasts, fMRIPrep/GLMsingle/MNE pipelines, MVPA/RSA, and COBIDAS reporting while treating pure insertion, reverse inference, motion confounds, and in- sample decoding as first-class...

stanfish06 Skill

Medical imaging deep learning with MONAI, PyTorch, pydicom, pathml, histolab, and napari-viz. Use for segmentation, classification, registration, transforms, sliding-window inference, NIfTI/DICOM workflows, medical image datasets, and reproducible clinical imaging AI pipelines.

stanfish06 Skill

Conducts multi-axis code review. Use before merging any change. Use when reviewing code written by yourself, another agent, or a human. Use when you need to assess code quality across multiple dimensions before it enters the main branch.

stanfish06 Skill

LLM and agent security red teaming with agentic-actions-auditor, supply-chain-risk-auditor, semgrep, codeql, and sarif-parsing. Use for prompt injection, tool misuse, data exfiltration, excessive agency, insecure output handling, supply-chain risk, retrieval poisoning, and OWASP LLM Top 10 style threat modeling.

stanfish06 Bundle

Render a 4-panel regional LocusCompare diagnostic for one (lead variant, exposure study, outcome study) tuple - overlays GWAS Manhattan, QTL Manhattan, GENCODE gene track, and cross-trait scatter colored by LD r². Use when an agent needs visual confirmation that two GWAS / QTL signals share the same causal variant (the Liu 2019 LocusCompare convention). Inputs: lead variant + two pre-fetched harmonised sumstats slices (or eQTL Catalogue / GWAS Catalog identifiers for bundled fetch). Output: PNG + JSON manifest.

stanfish06 Bundle

Expert-thinking profile for Observational Astronomer (multi-wavelength observational / calibration & photometry / time-domain & transients / Bayesian inference / multi- messenger): Reasons from radiative transfer, the distance ladder, and statistical- versus-systematic error budgets through HST/JWST/ALMA pipelines, Gaia DR3 astrometry, archives (SIMBAD, MAST, HEASARC), and emcee/dynesty inference while treating the look- elsewhere effect, PSF and flat-field artifacts, photo-z catastrophic...

stanfish06 Bundle

实战 SRC / 众测 / Bug bounty 漏洞挖掘工作流 skill。包含：5 阶段方法论（intake → recon → enum → hunt → report）、19 个攻击类 playbook（SQLi/XSS/RCE/SSRF/IDOR/CSRF/Path Traversal/File Upload/SSTI/XXE/Race/HTTP Smuggling/OAuth/JWT/SAML/GraphQL/Mobile/LLM/DoS）、305 个结构化 payload、263 个 WAF/EDR 绕过变体、2887 份 HackerOne 真实 High/Critical 已披露案例、77,000+ WooYun 案例统计、国产 OA / 中间件指纹库、银行 / 电信行业垂直 playbook。当用户提到 "src 挖洞 / src 漏洞挖掘 / bug bounty / 众测 / hackerone / 漏洞赏金 / SRC / 任意 X 漏洞 / 渗透测试" 或问"如何挖某个目标 / 怎么测某个 API / 如何绕过 WAF" 时触发。

stanfish06 Bundle

Publish and manage research papers on Hugging Face Hub. Supports creating paper pages, linking papers to models/datasets, claiming authorship, and generating professional markdown-based research articles.

stanfish06 Skill

Multi-modal single-cell analysis with muon/MuData. Joint RNA+ATAC (10x Multiome), CITE-seq (RNA+protein), other multi-omics. MuData holds per-modality AnnData with shared obs. WNN joint embedding, per-modality preprocessing, MOFA factor analysis. Use scanpy-scrna-seq for single-modality RNA; use muon when combining 2+ omics from the same cells.