Skill UI

Guides PMs through a full discovery cycle—from framing a hypothesis to validating solutions—by combining problem definition, customer interviews, synthesis, and experiments so teams can test assumptions before investing in build work.

Guides product managers from discovery notes to an aligned PRD by orchestrating problem framing, user context, solution definition, and success criteria so engineering and stakeholders share a clear source of truth.

Guides product teams through MITRE's Problem Framing Canvas with structured inward/outward/reframe questions so you clarify assumptions, surface stakeholders, and create an actionable HMW statement before ideating.

Guides teams through an empathy-driven problem framing that captures the persona, desired outcome, blockers, root causes, and feelings before jumping into solutions.

This mode acts as a structured thinking partner, guiding users through ambiguous problems, complex decisions, and open-ended strategy questions. Instead of providing direct answers, it focuses on challenging assumptions, asking clarifying questions, surfacing multiple perspectives (e.g., stakeholder views), and helping the user structure their thought process using advanced techniques like reframing, pre-mortem analysis, and identifying critical constraints. Ideal for product managers and leaders who need to explore ideas without a clear path forward.

This skill transforms vague, unclear, or half-formed business opportunities and brief descriptions into highly structured, actionable problem statements. It guides the user through a three-stage process: reframing the core questions, rigorously defining in-scope and out-of-scope boundaries, and designing a minimum viable research plan. It ensures that ambiguous inputs are converted into clear, executable steps, allowing the user to respond with confidence rather than asking for more clarification meetings.

A comprehensive, end-to-end playbook designed for software engineers and AI agents. It provides a structured methodology to safely introduce machine learning capabilities into existing, non-ML codebases. The process covers critical stages: problem framing, data readiness, architectural decoupling (using dedicated APIs/services), baseline model implementation, and final handoff to MLOps practices (CI/CD, monitoring).

This guide outlines the critical process of developing the short, mandatory proposal (≤5 pages) for submitting a literature review to the Academy of Management Annals. It details the required four-part structure, focusing on how to identify a core field problem, differentiate from existing work, define scope, and articulate new integrative insights to successfully gatekeep the project.

A structured guide for authors on how to frame the central findings of an Econometric Theory (ET) paper. It ensures that the contribution is clearly articulated by defining the underlying problem, stating the main theorem and its scope, identifying the generality delta, and discussing practical implications, meeting the rigorous standards of top academic journals.

This skill guides authors in transforming raw experimental data into a compelling, logically structured scientific narrative suitable for top-tier journals like JACS. It teaches how to explicitly define the 'chemical advance' by building an evidence-backed claim chain: Problem $ ightarrow$ Advance $ ightarrow$ Evidence $ ightarrow$ Significance. It ensures that every claim of novelty is rigorously supported by data and compares the work explicitly against the closest prior art.

This guide assists researchers in transforming narrowly focused, technically correct findings into broadly significant methodological contributions suitable for high-impact econometrics journals (e.g., JoE). It outlines strategies for framing the work by identifying the general problem class, stating the advance as a property (rather than a procedure), and anchoring the contribution within broader economic settings. Use this when your paper needs to be elevated from an incremental fix to a field-changing principle.

This guide teaches researchers how to structure and articulate the contribution of a mathematical finance manuscript. It advises authors to move beyond simply proving a theorem, instead focusing on framing the methodological novelty and its direct payoff to financial modeling problems like pricing, hedging, risk management, and portfolio choice. It ensures the paper is seen as relevant to practitioners, not just mathematicians.