All Skills

Identify what to measure, test, or track to de-risk a product or AI idea across internal and external risk dimensions.

Guide PMs through the transition to Director with adaptive coaching across preparing, interviewing, landing, and recalibrating phases.

Evaluate feature investments using revenue impact, cost structure, ROI, and strategic value to make data-driven build/don't-build decisions.

Design multi-agent AI workflows with clear boundaries, handoffs, and monitoring for complex product management tasks.

Assess whether your product work is AI-first or AI-shaped, evaluate maturity across five key competencies, and get recommendations on which capability to build next.

Diagnose whether an AI workflow suffers from context stuffing or benefits from context engineering, and apply structured techniques to improve reliability.

Structure the first 90 days of a VP or CPO transition as a diagnostic process, not an execution sprint, using a three-phase playbook to build evidence before making decisions.

Evaluate the financial impact of pricing changes using ARPU, conversion, churn risk, NRR, and payback analysis to make data-driven go/no-go decisions.

Structure spoken product-sense interview answers with assumptions, segmentation, pain-point prioritization, and MVP tradeoffs.

Evaluate SaaS unit economics and capital efficiency to determine if a business can scale efficiently or needs correction.

Provides structured guidance for building production-grade AI agent systems through context engineering, covering fundamentals, architectural patterns, operational excellence, and evaluation.

Provides a structured template for creating new Agent Skills, including sections for description, activation criteria, core concepts, practical guidance, and integration notes.

Design and build hosted agent infrastructure with sandboxed execution, warm pools, session persistence, and multiplayer collaboration.

Designs persistent memory architectures for AI agents, covering cross-session knowledge retention, entity tracking, temporal validity, graph/vector retrieval, and memory consolidation.

Shares memory between agents at the representation level by compacting the orchestrator's KV cache for efficient worker handoff, reducing token costs without summarization or retrieval.

Convert books into supervised fine-tuning datasets and train style-transfer models that replicate an author's voice.

Provides production-grade techniques for evaluating LLM outputs using LLMs as judges, covering direct scoring, pairwise comparison, bias mitigation, rubric generation, and confidence calibration.

Optimizes long-running agent sessions with structured context compression, summarization, and durable handoff summaries that preserve decisions, files, risks, and next actions.

Guides project-level decisions for LLM-powered systems: task-model fit, pipeline architecture, token and cost estimation, and agent-assisted iteration.

Explains foundational concepts of context engineering: what context is, attention mechanics, the U-shaped attention curve, and why context quality matters more than quantity.

Extends effective context capacity through strategic compression, masking, caching, and partitioning techniques.

Debug and optimize AI agents by analyzing reasoning traces, context degradation, tool confusion, instruction drift, repeated task failures, and performance regressions.

Improves multi-step research reliability with structured protocols for source validation, error recovery, and transparent reasoning.

Enables fast similarity search and clustering of dense vectors using FAISS, supporting billions of vectors, GPU acceleration, and various index types.

Build production RAG and semantic search systems with a high-performance vector database written in Rust, supporting hybrid search, filtering, and horizontal scaling.

Track ML experiments, manage model registry with versioning, deploy models to production, and reproduce experiments with MLflow.

Provides code examples and best practices for using Pinecone, a managed vector database for production RAG, recommendation, and semantic search applications.

Track ML experiments with open-source run logging, local or self-hosted dashboards, and media visualization using SwanLab.

Build, deploy, and manage continuous AI agents using a visual workflow editor or development toolkit.

Optimize AI agents through automated evolution cycles using LLM-driven mutation of prompts, skills, and memory against measurable benchmarks.

Enables zero-shot image classification, image-text matching, and cross-modal retrieval using OpenAI's CLIP model.

Fine-tune large language models by training less than 1% of parameters using LoRA, QLoRA, and 25+ adapter methods, enabling efficient adaptation on consumer GPUs.

Quantize large language models to 8/4/3/2/1-bit precision without calibration data, using multiple optimized backends for deployment with vLLM or HuggingFace Transformers.

Build LLM-powered applications with agents, chains, and RAG using a framework that supports multiple providers and 500+ integrations.

Enables visual instruction tuning and image-based conversations using open-source vision-language models. Supports multi-turn image chat, visual question answering, and image understanding tasks.

Orchestrates end-to-end autonomous AI research projects using a two-loop architecture for rapid experimentation and synthesis, producing papers and presentations.