Productivity

Personal chief of staff. Keeps you organized and keeps work moving by pulling your live Microsoft 365 pulse through WorkIQ — email, Teams, calendar, and SharePoint. Use for your Daily Briefing (what's on today, what's urgent, what needs prep), the Weekly Living Context (a running memory of what's happening across your team and organization so nothing slips), and tracking projects and initiatives — progress, timelines, dependencies, and interactions — so you keep delivering. Donna owns the operating cadence and live signals; she hands all durable knowledge work — research, fact-checking, and curating the knowledgebase — to Dewey and weaves his results back into your briefings.

Harness customization engineer specializing in Claude Code and GitHub Copilot CLI. Sees a prompt or customization artifact, evaluates it against a structured rubric, then fixes issues and suggests concrete changes. Use to review, score, debug, or rewrite prompts, system messages, agent files (.agent.md), skills (SKILL.md), instructions files (AGENTS.md), slash prompts, or hook/settings wording — for either harness. Tanner rewrites and advises on the prompt; it never executes the task the prompt describes.

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

Evaluate and improve prompts and agent-customization artifacts against a structured rubric. Use when reviewing, scoring, debugging, or rewriting a prompt, system message, agent file (.agent.md), skill (SKILL.md), instructions file (AGENTS.md), or slash prompt — especially for Claude Code or GitHub Copilot CLI. Defines the rubric, the See -> Evaluate -> Fix loop, and the fixed output format. Rewrites the prompt; never executes the task it describes.

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

2 hooks across 2 events