Skill UI

This skill formalizes successful, recurring patterns discovered in auto-memory (MEMORY.md) and graduates them into permanent, enforced rules within the project's core instruction set (CLAUDE.md or scoped rules). It ensures that learned best practices become mandatory project conventions, significantly improving adherence and consistency across all future AI interactions and development cycles. Use this when a temporary note proves to be a vital, repeatable guideline.

Summarizes any requested week, month, quarter or year into a factual financial narrative, comparing current results to prior and year-ago periods while flagging anomalies and recurring bills.

This skill initializes an autonomous, scheduled loop for running complex research or engineering experiments. Users specify the target experiment and select a recurring interval (e.g., 10 minutes, daily, weekly). It utilizes cron scheduling to ensure continuous research, guiding iterative changes, evaluating metrics, and committing results automatically until manually stopped.

This skill systematically audits a given project by analyzing its historical memory, rollout summaries, and local skill definitions. It identifies repeated complex workflows, recurring operational patterns, or areas where existing skills are stale. The audit process guides the user to recommend the highest-value skills to either add (if a new pattern emerges) or update (if current skills are outdated or incomplete), ensuring the AI agent operates with the most accurate and context-specific knowledge base for optimal project execution.

Guides aspiring entrepreneurs to discover communities they already belong to, evaluate recurring pains, and focus on problems they can solve with minimalist businesses inspired by Sahil Lavingia’s philosophy.

This harness transforms standard code environments into fully persistent, autonomous agent systems. It leverages native features like scheduled tasks (Crons), remote dispatching, and structured memory storage (MCP) to enable continuous, self-directing automation. Ideal for building AI assistants that require long-term context, recurring workflows, and complex, multi-step operations, eliminating the need for external agent frameworks like AutoGPT.

This guide provides a systematic, structured approach for debugging complex technical issues, such as failing tests, broken builds, or unexpected runtime errors. It teaches the 'Stop-the-Line' rule and utilizes a comprehensive triage checklist (Reproduce, Localize, Reduce, Fix, Guard, Verify) to ensure root causes are found and prevented from recurring.

Creates recurring focus time blocks on Google Calendar to reserve deep work hours across weekdays and surface them as busy blocks so meetings aren't scheduled during protected slots.

Reads sales data from Google Sheets, formats it into a Google Docs report, and shares it via Drive permissions, simplifying recurring reporting workflows for stakeholders.

Automates applying Gmail labels to matching messages and archiving them via gws commands so recurring notifications stay organized without manual inbox cleanup.

Automate creation of recurring Google Calendar meetings with attendees via the gws calendar CLI, then review upcoming slots using the agenda view.

Use the cron tool to schedule reminders, recurring tasks, or one-time events with simple expressions for intervals, cron syntax, or ISO timestamps; supports listing and removing jobs.