Business & Operations

Evaluates a unified vision-language model's ability to ground natural language instructions to 3D objects and 2D regions, as well as answer 3D visual questions. It probes spatial reasoning, cross-modal alignment, and robustness to different 3D input representations (mesh-sampled vs. sensor RGB-D point clouds). Use when the user wants to benchmark on SR3D, NR3D, ScanRefer, RefCOCO, RefCOCO+, RefCOCOg, ScanQA, SQA3D, or asks about evaluating this task. Reports top-1 accuracy (Acc@25/50/75).

IBM quantum computing framework. Use when targeting IBM Quantum hardware, working with Qiskit Runtime for production workloads, or needing IBM optimization tools. Best for IBM hardware execution, quantum error mitigation, and enterprise quantum computing. For Google hardware use cirq; for gradient-based quantum ML use pennylane; for open quantum system simulations use qutip.

Google quantum computing framework. Use when targeting Google Quantum AI hardware, designing noise-aware circuits, or running quantum characterization experiments. Best for Google hardware, noise modeling, and low-level circuit design. For IBM hardware use qiskit; for quantum ML with autodiff use pennylane; for physics simulations use qutip.

Package agent-generated scientific code, figures, tables, data, logs, and conclusions into a navigable workspace result with stable paths and a concise manifest. Use near the end of computational tasks.

Comprehensive toolkit for preparing ISO 13485 certification documentation for medical device Quality Management Systems. Use when users need help with ISO 13485 QMS documentation, including (1) conducting gap analysis of existing documentation, (2) creating Quality Manuals, (3) developing required procedures and work instructions, (4) preparing Medical Device Files, (5) understanding ISO 13485 requirements, or (6) identifying missing documentation for medical device certification. Also use wh...

RNN+Transformer hybrid with O(n) inference. Linear time, infinite context, no KV cache. Train like GPT (parallel), infer like RNN (sequential). Linux Foundation AI project. Production at Windows, Office, NeMo. RWKV-7 (March 2025). Models up to 14B parameters.

High-level PyTorch framework with Trainer class, automatic distributed training (DDP/FSDP/DeepSpeed), callbacks system, and minimal boilerplate. Scales from laptop to supercomputer with same code. Use when you want clean training loops with built-in best practices.

Cost modeling and ROI analysis for specialized LLM development. Use when deciding whether to train a custom model, estimating total cost, or calculating break-even vs frontier APIs. Covers training costs, inference costs, and time-to-ROI projections.

Process-based discrete-event simulation framework in Python. Use this skill when building simulations of systems with processes, queues, resources, and time-based events such as manufacturing systems, service operations, network traffic, logistics, or any system where entities interact with shared resources over time.

Medicinal chemistry filters. Apply drug-likeness rules (Lipinski, Veber), PAINS filters, structural alerts, complexity metrics, for compound prioritization and library filtering.

Spectral similarity and compound identification for metabolomics. Use for comparing mass spectra, computing similarity scores (cosine, modified cosine), and identifying unknown compounds from spectral libraries. Best for metabolite identification, spectral matching, library searching. For full LC-MS/MS proteomics pipelines use pyopenms.

Analyzes chemical libraries by scaffold using Bemis-Murcko scaffolds, generic frameworks, cyclic skeletons, matched molecular pair (MMP) analysis via mmpdb, R-group decomposition, Free-Wilson analysis, scaffold hopping, and chemotype-aware ML train/test splits. Use when identifying chemotype clusters in a library, deriving SAR transformation rules, decomposing series into R-groups, performing scaffold-balanced QSAR splits, or planning analog campaigns.

Interpretable ADMET analysis with mechanistic reasoning. Maps liabilities to structural causes and biological pathways. Based on CoTox (Park 2025) and DrugR (Liu 2026).

Constraint-based metabolic modeling (COBRA). FBA, FVA, gene knockouts, flux sampling, SBML models, for systems biology and metabolic engineering analysis.

Infer integer allele-specific copy number, tumor purity, and ploidy from tumor sequencing by jointly modeling read depth (logR) and B-allele frequency (BAF) with ASCAT, Sequenza, FACETS, PURPLE, and PureCN (tumor-only). Covers the purity-ploidy identifiability problem, the diploid-baseline (dipLogR) anchor, major/minor copy number, loss of heterozygosity, sunrise/contour fit diagnostics, and reconciliation of conflicting fits. Use when tumor analysis needs absolute copy number rather than rel...

Mark and remove PCR/optical duplicates using samtools fixmate and markdup. Use when preparing alignments for variant calling or when duplicate reads would bias analysis.

Render a Parallax full stock research report (the get_stock_report output) under a client's brand as a white-labeled HTML and PDF. Takes a ticker (RIC), pulls the report, and re-renders all sections (cover, factor scores, thesis, company + peers, technical, financial analysis, statements, ratios, analyst ratings, disclosures) with the client's logo, colors, and fonts from the active white-label config. Visual skin only: keeps Chicago Global / MAS regulatory disclosures verbatim and a \"Powere...

Ingest a CIO house view (PDF / text / URL / wizard) into the Parallax workflow system. Extracts structured tilts and excludes, presents a confirmation gate, then saves the view to ~/.parallax/active-house-view/ where every portfolio skill auto-loads it. Use to set, update, re-pair, extend, or clear the active house view. NOT for portfolio construction (use /parallax-portfolio-builder), not for one-off scenario exploration (just describe inline to the relevant skill).

Friendly concierge that opens a four-branch menu (Stock / Portfolio / Discovery / Investor profiles) for users who arrive without a specific /parallax-* command in mind. Triggers on greetings addressed to Parallax — 'Hi Parallax', 'Hello Parallax', 'Hey Parallax', 'Good morning Parallax', 'Yo Parallax', 'Parallax!' — case- and punctuation-insensitive. Also triggers on 'what can Parallax do', 'help me get started with Parallax', 'show me Parallax workflows', or any open-ended request to explor...

Monthly CIO letter prep pack for fund managers: period attribution via daily contribution analysis, top contributors / detractors with evidence-backed drivers, macro snapshot, news themes, and a conditional forward-outlook. Output is Word .docx for the CIO to edit and send. Provide current_portfolio, prior_portfolio, trade_log, period_start, period_end. Symbols in RIC format. NOT for individual stock analysis (use /parallax-deep-dive), not for daily fund-manager check-ins (use /parallax-morni...

Translate financial content (stock reports, CIO reports, macro reports) to Thai with correct code-switching, terminology, and natural phrasing. Use when translating text to Thai for institutional finance audiences.

Translate financial content (stock reports, CIO reports, macro reports) to Chinese — Simplified (zh-CN) or Traditional (zh-TW/zh-HK) — with correct code-switching, terminology, and natural phrasing. Use when translating text to Chinese for institutional finance audiences.

Render a Parallax full stock research report (the get_stock_report output) under a client's brand as a white-labeled HTML and PDF. Takes a ticker (RIC), pulls the report, and re-renders all sections (cover, factor scores, thesis, company + peers, technical, financial analysis, statements, ratios, analyst ratings, disclosures) with the client's logo, colors, and fonts from the active white-label config. Visual skin only: keeps Chicago Global / MAS regulatory disclosures verbatim and a \"Powere...

Configure white-label client branding for Parallax report output. Extracts colors, logos, fonts AND writing voice from a folder of client collateral (PowerPoint, Word docs), a website URL, a PDF brand guide, or guided wizard intake. Multi-source ingestion supported: when more than one source is provided, mismatches between sources are flagged at the confirmation gate rather than silently resolved. Validates visual assets against WCAG accessibility standards and voice section against corpus-si...