Claude Skills by thedixitjain

> Query the 1000 Genomes Project dataset (3,202 whole-genome-sequenced individuals, GRCh38) at the level of individual participants. Use when a question is about individuals or variants in the 1000 Genomes Project cohort: which individuals carry variants matching specific criteria in a gene or region, which individuals are homozygous-reference at a position, which variants exist in the dataset or carried by specified individuals in a gene or region, the relatedness between two specified indiv...

Use when packaging an artifact for an accepted OOPSLA paper under the SPLASH artifact-evaluation track — surviving the kick-the-tires phase, earning the Functional and Reusable badges, depositing a Zenodo snapshot with a DOI for Available, and aligning artifact claims with the paper's Data-Availability Statement.

Use when planning an OOPSLA campaign on the two-round clock — choosing October vs March entry, budgeting for Minor or Major Revision paths, mapping acceptance to the OOPSLA1 or OOPSLA2 PACMPL issue, scheduling artifact evaluation, and landing the SPLASH talk, with dates re-anchored to the live cycle.

Self-hosted, open-source alternative to Google NotebookLM for AI-powered research and document analysis. Use when organizing research materials into notebooks, ingesting diverse content sources (PDFs, videos, audio, web pages, Office documents), generating AI-powered notes and summaries, creating multi-speaker podcasts from research, chatting with documents using context-aware AI, searching across materials with full-text and vector search, or running custom content transformations. Supports ...

Particle Image Velocimetry (PIV) analysis with OpenPIV. Use when extracting velocity fields from PIV image pairs, analyzing fluid dynamics or flow visualization experiments, cross-correlating interrogation windows, validating and replacing spurious PIV vectors, or computing vorticity, strain rate, and turbulence statistics from measured velocity fields.

Manage OpenWork inference model aliases, openwork model overlays, discounts, validation, and automated base model refreshes from models.dev. Use when adding, removing, discounting, auditing, or updating OpenWork models, including requests like \"update the models\" that should trigger the GitHub update-models workflow and report when its PR merges.

GPU-accelerate Python code using CuPy, Numba CUDA, Warp, cuDF, cuML, cuGraph, KvikIO, cuCIM, cuxfilter, cuVS, cuSpatial, and RAFT. Use whenever the user mentions GPU/CUDA/NVIDIA acceleration, or wants to speed up NumPy, pandas, scikit-learn, scikit-image, NetworkX, GeoPandas, or Faiss workloads. Covers physics simulation, differentiable rendering, mesh ray casting, particle systems (DEM/SPH/fluids), vector/similarity search, GPUDirect Storage file IO, interactive dashboards, geospatial analys...

Speed up long-sequence transformer training and inference.

'Optimize deep learning models using Adam, SGD, and learning rate scheduling to improve accuracy and reduce training time. Use when asked to \"optimize deep learning model\" or \"improve model performance\". Trigger with phrases like ''optimize'', ''performance'', or ''speed up''. '

'Create optuna study creator operations. Auto-activating skill for ML Training. Triggers on: optuna study creator, optuna study creator Part of the ML Training skill category. Use when working with optuna study creator functionality. Trigger with phrases like \"optuna study creator\", \"optuna creator\", \"optuna\". '

Use when building the exhibits for an Organization Studies (OS) manuscript — data structures, process-model figures, evidence tables, and (for quantitative work) results tables. Designs exhibits that make the inference auditable; it does not run the analysis (see orgstud-data-analysis).

Use when preparing an OSDI artifact for sysartifacts-run evaluation — the post-acceptance timeline, the 2026 narrowing to a single Artifacts Available badge, Zenodo-grade permanent archiving, the AE-committee runbook, and the two-page Artifact Appendix that documents the result.

Use when designing or auditing the evaluation of an OSDI submission — choosing mature baselines and realistic workloads, structuring the section around research questions, measuring scalability and tail behavior, quantifying the design's costs, and fitting the evidence into the 12-page reviewed body.

Outlines: structured JSON/regex/Pydantic LLM generation.

Use PathML for local, research-only computational pathology workflows: load and tile slides, build preprocessing and QC pipelines, manage h5path data, quantify multiplex images, construct spatial graphs, and plan bounded model inference.

Fine-tune large LLMs with LoRA on limited GPU memory.

Hardware-agnostic quantum ML framework with automatic differentiation. Use when training quantum circuits via gradients, building hybrid quantum-classical models, or needing device portability across IBM/Google/Rigetti/IonQ. Best for variational algorithms (VQE, QAOA), quantum neural networks, and integration with PyTorch or JAX. For hardware-specific optimizations use qiskit (IBM) or cirq (Google); for open quantum systems use qutip.

Use when packaging an IEEE PerCom sensing artifact and dataset for reproducibility and any badging (IEEE Open Research Objects / Results Reproduced, IEEE DataPort or Zenodo deposit), covering what a ubicomp evaluator checks first for human-subjects sensing data, cross-subject reproduction, de-identification, and honest degrees of reproducibility.

Use when preparing an accepted IEEE PerCom paper for its IEEE Xplore camera-ready, covering de-anonymization, the IEEEtran compsocconf template and page budget, IEEE Xplore metadata (PDF eXpress, eCopyright, ORCID, index terms), integrating reviewer-required changes without scope creep, permanentizing the dataset links, and IEEE production checks.

Use when deciding what belongs in an IEEE PerCom paper body versus its dataset/artifact and any appendix, covering the tight IEEEtran 9+1 page budget, the rule that decision-critical evidence stays inside the reviewed pages, double-blind supplementary material, and how to split a human-subjects sensing paper between body and dataset.

'Detects DNS tunneling by computing Shannon entropy of DNS query names, analyzing query length distributions, inspecting TXT record payloads, and identifying high subdomain cardinality. Uses scapy for packet capture analysis and statistical methods to distinguish legitimate DNS from covert channels. Use when hunting for data exfiltration. '

Automate network traffic analysis using tshark and pyshark for protocol statistics, suspicious flow detection, DNS anomaly identification, and IOC extraction from PCAP files

'Performs User and Entity Behavior Analytics (UEBA) to detect anomalous user activities including impossible travel, unusual access patterns, privilege abuse, and insider threats using SIEM-based behavioral baselines and statistical analysis. Use when SOC teams need to identify compromised accounts or insider threats through deviation from established behavioral norms. '

Use when packaging a PLDI artifact for the post-acceptance evaluation — earning the Functional, Reusable, and Available badges, archiving a DOI-stamped snapshot on Zenodo, containerizing toolchains and benchmark suites, and writing a README an evaluator can follow in a fresh VM.

Use when drafting a PLDI author response inside the short February window — triaging reviewer objections about soundness, baselines, and benchmark validity, correcting factual errors with pointers into the submitted PDF, and committing to feasible revisions without promising new systems work.

Use when designing or auditing a PLDI evaluation — choosing defensible benchmark suites and baseline compiler configurations, measuring runtime, compile time, and memory with warmup and variance discipline, running ablations that isolate the claimed mechanism, and scoping claims to the platforms measured.

Use when deciding what accompanies a PLDI submission beyond the 20 text pages — full proofs, extended benchmark data, anonymized code — and how to keep every extra byte double-blind, optional for reviewers, and consistent with the main PDF under summary-rejection formatting rules.

Use when deciding whether a project is PLDI-shaped — implementation insight with benchmark-grade evidence — or better routed inside the PACMPL family to POPL, OOPSLA, or ICFP, or outward to ASPLOS, CGO, CAV, ICSE/FSE, or a systems venue, based on where the claim's evidence actually lives.

Use when planning a PLDI campaign across its annual clock — backward-planning from the November deadline through winter reviewing, the February response window, March notification, post-acceptance artifact evaluation, PACMPL production, and the June conference, with owners for each deliverable.

Use to enforce PNAS's statistics and reproducibility reporting — n and replication, test choice and assumptions, effect sizes with uncertainty, multiple-comparison control, randomization/blinding, sample-size justification, pre-registration where relevant, and reproducible code.

Use as the final preflight before submitting to PNAS — a complete checklist across significance, track, Significance Statement, abstract, classification + keywords, figures, statistics, data, references, and required files. Bundles a checklist and a PNAS cover-letter template. Emits GO/NO-GO.

Use to enforce PNAS Nexus's statistics and reproducibility reporting — n and replication, test choice and assumptions, effect sizes with uncertainty, multiple-comparison control, randomization/blinding, sample-size justification, and reproducible code. Also covers whether a Registered Report (Stage 1/2) is the right route for confirmatory work.

Use as the final preflight before submitting to PNAS Nexus — a complete checklist across fit, open access/APC/license, article type & length, Significance Statement, abstract, classification, figures, statistics, data/code, references, and required files. Covers the PNAS-transfer case and bundles a checklist and cover-letter template. Emits GO/NO-GO.

Use when an author expects an artifact-evaluation or badge track at ACM PODC and needs redirecting — PODC has NO artifact track and no ACM badges. This skill converts artifact-culture instincts into what PODC actually evaluates: proof-appendix completeness, model/assumption rigor, and the honest, optional role of any simulation.

Use for the PODS analogue of artifact evaluation — there is no systems artifact track at this theory symposium, so this skill covers formal-claims verification instead: a complete at-submission proof appendix, a claim-to-proof mapping reviewers can check, the full-version-on-arXiv norm, and, only when a paper claims practicality, an honest optional code artifact.

Use when understanding or planning for Production and Operations Management (POM) review — Department Editor screening, double-blind review, the rigor-and-practice evaluation, and the strict no-resubmission-after-rejection rule. Explains the process and reads decisions; it does not draft the response (pom-rebuttal).

> Show ponytail's measured impact as a compact scoreboard: less code, less cost, more speed, from the benchmark medians. One-shot display, not a persistent mode, and not a per-repo number. Trigger: /ponytail-gain, \"ponytail gain\", \"what does ponytail save\", \"show ponytail impact\", \"ponytail scoreboard\".

Use when packaging a POPL artifact — above all a mechanized proof development in Rocq/Coq, Lean, Agda, or Isabelle — for the post-conditional-acceptance evaluation, satisfying the no-admit/no-sorry completeness rule, mapping paper theorems to proof files, pinning toolchains, and earning the Functional, Reusable, and Available badges.

Add a chart (line, bar, area, pie, or scatter) to a dataset's showcase in a PortalJS portal. Installs recharts, writes a reusable Chart component, and renders it in the showcase Views section. Use when visualizing a dataset already registered in datasets.json.

Add a dataset (CSV, TSV, JSON, or GeoJSON) to an existing PortalJS portal. Appends an entry to datasets.json so the catalog and showcase render it automatically; routes the data by source (local file vs remote URL) — R2 via Git LFS by default, remote URLs by passthrough. Use when registering a new dataset in a scaffolded portal.

Add another file (resource) to an EXISTING dataset in a PortalJS portal — a data dictionary, methodology, or an additional data file. Turns a single-file dataset into a multi-resource one; the showcase renders a section per resource. Use when a dataset needs a second file, such as a data dictionary, methodology doc, or an additional period's data.

'Implement PostHog feature flags, A/B experiments, and cohort management. Use when rolling out features with flags, running A/B tests, creating cohorts, or evaluating multivariate experiments with PostHog. Trigger: \"posthog feature flag\", \"posthog experiment\", \"posthog A/B test\", \"posthog cohort\", \"feature rollout posthog\", \"posthog multivariate\". '

Use when packaging a PPoPP artifact for the post-acceptance, CGO-shared artifact-evaluation track, covering PPoPP's specific badge policy (Functional or Reusable plus Results Reproduced, no \"Results Replicated\"; Available granted by the publisher from a deposit link), reproducible parallel measurements on evaluators' hardware, and the separate AE deadline.

在为《模式识别与人工智能》(Pattern Recognition and Artificial Intelligence, PR&AI) 处理代码与数据可用性、撰写可用性声明时调用。本刊作为中文期刊是否设立独立的制品评审徽章(artifact badge)制度目前待核实——本技能讲清现状与稳妥做法：如何写诚实的代码/数据可用性声明、如何组织可供外审核验的复现仓库、如何在不可公开时说明原因与替代验证途径、如何与审稿匿名要求(是否双盲待核实)协调。用于让模式识别/机器学习论文的制品支撑而非拖累评审，避免可用性声明与实际提供的材料不一致。

在为《模式识别与人工智能》(Pattern Recognition and Artificial Intelligence, PR&AI) 撰写相关工作/文献综述并确立创新性时调用。本刊要求成果具原创创新价值，相关工作须 delta 优先——把本文相对最接近工作的增量讲清，而非文献罗列。覆盖如何组织相关工作、如何在模式识别/机器学习/视觉/NLP 语境中定位 delta、如何用 GB/T 7714 规范引用中英文文献并给中文文献英文对照、如何避免\"综述式罗列\"与\"漏引近作\"两类退稿风险。用于把创新性写到经得起外审质疑的水准。

| Use when asked to implement a chart, select a visualization type, or build a data display component. Examples: \"implement chart for time series\", \"best visualization for comparison data\", \"chart component for analytics\"

Use when running the final pre-submission preflight for a Physical Review Letters manuscript — length check, format, files, Supplemental Material, classification, author info, and metadata. Verifies submission readiness; does not write content.

'Process images using object detection, classification, and segmentation. Use when requesting \"analyze image\", \"object detection\", \"image classification\", or \"computer vision\". Trigger with relevant phrases based on skill purpose. '

Version-aware guidance for PufferLib reinforcement-learning environments, vectorization, policies, PuffeRL training, evaluation, and safe checkpoint review. Use when adapting Gymnasium/PettingZoo environments to published PufferLib 3.0.0 or working with the redesigned native 4.0 source line.

Build clinical/healthcare deep-learning pipelines with PyHealth — loading EHR/signal/imaging datasets (MIMIC-III/IV, eICU, OMOP, SleepEDF, ChestXray14, EHRShot), defining tasks (mortality, readmission, length-of-stay, drug recommendation, sleep staging, ICD coding, EEG events), instantiating models (Transformer, RETAIN, GAMENet, SafeDrug, MICRON, StageNet, AdaCare, CNN/RNN/MLP), training with the PyHealth Trainer, computing clinical metrics, and using medical code utilities (ICD/ATC/NDC/RxNor...