A product-management agent that organizes work across the product lifecycle, from an initial idea or problem through later stages. The description says it routes work to stages P0 through P14 and uses 80 executable skills.
A practical method for designing AI products made of agents and skills. It takes a task situation and maps the needed task breakdown, agent roles, skills, tools, limits, and fallback behavior.
A practical method for auditing an AI product or system before release. It examines design evidence, evaluation evidence, and shadow evidence, then defines release limits and a go/no-go decision.
A workflow for designing how an AI system receives and manages information for a task. It covers choosing context, controlling the amount of information, and checking the result.
A workflow for designing a knowledge system that lets an AI find answers in company documents. RAG means retrieving relevant source material before generating an answer.
A method for planning marketing and growth around AI as a core part of the product. It focuses on connecting data, models, and feedback into a repeating growth process.
A practical method for designing memory in an AI product. It covers what the product should remember, how memories are classified, who can access them, how long they last, and how they are stored and corrected.
A product-management workflow for AI products that guides an idea through seven stages, from discovering needs to launch auditing. It includes direction, user experience, system design, business model, and growth planning.
A method for operating an AI product after launch or during preparation for launch. It covers monitoring, metrics, failure handling, human corrections, feedback, and business or customer feedback loops.
A method for designing AI-native products during the system-building stage. It turns experiment findings into a plan covering system boundaries, capabilities, governance, and monitoring.
A business-planning tool that connects a company's pricing model with its growth strategy. An AI-native growth flywheel is a repeating cycle in which artificial-intelligence-based work supports further growth.
A product-discovery tool that turns user problems into a defined direction for development. It checks small needs, validates whether a need is real, and breaks it down through four layers.
A UX design and audit tool that connects risk assessment, trust levels, progressive disclosure, and release approval. UX means how people experience and use a product; an audit checks whether it meets defined standards.
A requirements-discovery workflow that coordinates eight checks, from spotting a small request to defining agent boundaries and rewriting recommendations.
A product-discovery process for finding needs that are well suited to AI agents. The description does not provide enough detail about its specific steps or outputs.
A five-question skill for detecting small but important needs. It is based on the idea that a problem that looks minor may still be deeply affecting a person or team.
A five-question skill for checking whether a request reflects a real need. It is based on separating genuine problems from requests that only look useful.
A four-layer skill for breaking down user requests. It separates what a person says from the problem that is actually blocking them before suggesting features.
A skill for investigating the history behind a request, including earlier decisions, team structures, and changes in the business.
★not rated 46▲
+1
changed 4d agoA73 tokens
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: