Skill UI

This skill formalizes the process of logging a founder's decision, turning in-session deliberation into durable company memory. It utilizes a two-layer memory model to store both approved, structured decisions (which feed into future planning) and raw, verbatim transcripts (for historical reference and preserving dissent). It supports structured decision records, success criteria, kill criteria, and follow-up scheduling.

A comprehensive 12-agent pipeline designed to guide users through the entire academic writing lifecycle. It covers literature search, structural planning, full-text drafting, bilingual abstract generation, simulated peer review, and professional formatting (LaTeX/DOCX/PDF). Features include Style Calibration and Writing Quality Checks to ensure publication-ready quality.

This skill is designed to capture and organize unstructured 'brain dumps'—messy streams of thoughts, ideas, and tasks—with zero information loss. It immediately structures the input into distinct, actionable sections (Projects/Ideas, Tasks, Connections, etc.), providing a clean, next-step guide. Use it whenever you are unloading a large, mixed block of thoughts and need them turned into coherent, executable plans.

Performs comprehensive, recurring email triage by classifying messages, researching new senders, generating decision recommendations, and drafting replies. It consumes a structured knowledge base (KB) and delivers a report and updated knowledge base without sending any emails. Designed for automated, periodic execution.

This skill provides a structured 'launching pad' for conducting academic literature reviews. It guides the user through a comprehensive intake process, requiring specificity on the research question and selecting appropriate frameworks (PICO, SPIDER, Decomposition). It then conducts strategic searches using Consensus, synthesizing findings into a professionally formatted research guide in DOCX format. It is designed not to produce a finished review, but an organized orientation document that allows researchers to dive into unfamiliar fields with confidence. Use cases include initiating res...

This skill automatically generates a comprehensive, professionally formatted reading list from any course syllabus. It parses learning outcomes and core topics, searches Consensus for the most recent peer-reviewed academic papers, and compiles them into a DOCX file. The generated content includes plain-language summaries and Bloom-higher-order discussion questions, calibrated specifically to the target audience (e.g., undergraduate, graduate) for maximum academic utility.

This cheatsheet serves as a comprehensive lookup reference for the Mercury MCP tools. It guides AI agents on which specific `mercury_*` tools to call for various team interactions, including messaging teammates, managing threads and tasks, scheduling automations, and performing organizational admin edits. Use it when connecting to the Mercury MCP server to ensure the agent selects the correct function without guessing.