Skill UI

Provides CEO-level strategic leadership frameworks for company strategy, fundraising, board and investor management, organizational culture, and stakeholder alignment, with Python tools for strategy and financial scenario analysis.

A comprehensive guide for treating project context as a managed, first-class artifact alongside code. It establishes systematic documentation (e.g., product vision, tech stack, workflow) to ensure consistent requirements, maintain team alignment, and optimize AI interactions throughout the entire development lifecycle. Essential for greenfield and brownfield projects.

Provides expert guidance for GRPO training with TRL, covering dataset prep, reward engineering, structured outputs, and multi-objective alignment when preference pairs are scarce.

High-performance Rust-backed tokenization toolkit with Python bindings, offering BPE/WordPiece/Unigram, custom vocabulary training, alignment tracking, and production-ready integrations for NLP pipelines.

Guides production-grade miles RL training for massive MoE models, covering FP8/INT4 low precision, train-inference alignment, and speculative rollout workflows to maximize throughput in enterprise deployments.

A comprehensive toolkit designed for Product Heads to define, cascade, and align Objectives and Key Results (OKRs) across the entire organization. This tool supports quarterly strategic planning, allowing users to define company-wide goals, decompose them into product objectives, and further cascade them to specific team goals. It measures critical alignment scores (vertical, horizontal) and generates structured roadmaps for maximizing organizational excellence and strategic focus.

SimPO (Simple Preference Optimization) is a state-of-the-art, reference-free method designed for aligning Large Language Models (LLMs) using human preference data. It is an efficient alternative to DPO and PPO, notably outperforming DPO without requiring a separate reference model. It is ideal for practitioners who need faster, simpler, and more resource-efficient fine-tuning for preference alignment.

Pysam offers Python bindings to htslib for reading and writing SAM/BAM/CRAM alignments, VCF/BCF variants, and FASTA/FASTQ sequences, enabling coverage stats, pileup analysis, variant queries, and seamless integration into NGS pipelines.

scikit-bio provides a Python-native biological data toolkit for reading/writing FASTA/Newick files, manipulating sequences, building alignments and phylogenies, and calculating diversity metrics for microbiome and ecology workflows.

A comprehensive guide for creating a consistent, credible, and highly defensible suite of investor-facing materials. This tool ensures alignment across pitch decks, financial models, one-pagers, and memos by enforcing a single source of truth for all metrics, assumptions, and use of funds, significantly boosting fundraising credibility.

A comprehensive toolkit for reconstructing and analyzing the evolutionary history of biological sequences (genes, proteins, genomes). The standard workflow includes multiple sequence alignment using MAFFT, robust maximum likelihood tree inference with IQ-TREE 2 and FastTree, and advanced visualization/manipulation using ETE3. This skill is essential for studies in viral phylodynamics, microbial genomics, protein family evolution, and molecular clock dating.

Guides product managers through strategic roadmap planning by orchestrating prioritization, epic definition, stakeholder alignment, and release sequencing into a structured workflow that turns strategy into executable outcomes and keeps stakeholders aligned.