kai

Technical co-pilot for non-engineering teams — health checks, stack review, UX audits, brainstorming, documentation, debugging, and weekly coaching. Examples: "/kai" (what can I help with?), "/kai doctor" (check before sharing), "/kai brainstorm" (help me plan), "/kai 5x" (quick coaching), "/kai 10x" (deep coaching).

Idea companion that turns vague "I want to build X" into a structured 1-page spec through conversation. Senior product advisor personality — curious, encouraging, one question at a time. Challenges assumptions gently. Examples: "help me plan a feature", "brainstorm", "I want to build something"

Quick coaching report that preprocesses session transcripts with shell commands and uses Sonnet for fast, token-efficient analysis. Produces the same HTML coaching report as 10x but skips deep prompt style analysis. Examples: "5x", "quick coaching", "quick insights"

Deep coaching report that dispatches Sonnet subagents to analyze session transcripts in parallel, then synthesizes findings with Opus into a rich HTML coaching report. Includes prompt style personality analysis. Examples: "10x", "deep coaching", "full coaching report"

Structured 6-step debugging workflow for any error in the approved stack. Classifies errors, forms hypotheses, investigates systematically, and documents the trail for future reference. Examples: "help me fix a bug", "debug", "something is broken", "I'm getting an error"

Thorough health audit for internal tools. Runs 80+ checks across reliability, safety, code health, and user experience. Produces a narrative report with billboard status, tiered findings, and actionable fixes. Examples: "check before sharing", "health check", "is this ready to deploy?"

Core knowledge for using admin-mcp tools: brand codes, URL-to-identifier resolution, identifier format rules, staging-only guardrail, and critical gotchas. Auto-activates whenever admin-mcp MCP tools are being used or when the user asks about page configs, PDPs, widget pages, experiments, or brand settings for Mosaic Wellness brands.

Rules and patterns for internal tools that call Claude API or build MCP servers. Covers model selection, cost management, security, prompt engineering, and MCP server conventions. Auto-activates when a project imports @anthropic-ai/sdk, uses Claude API, builds an MCP server, or when the user asks about AI features, prompt design, or token costs.

Strategies for handling bulk page operations (auditing, comparing, batch-editing) without bloating context. Teaches when to use summary tools, bulk-fetch script, or direct MCP calls based on the volume and nature of the task. Auto-activates when the user's request involves more than 3 pages or uses words like "all", "every", "across", "audit", "bulk", or "batch".

Foundation skill for all Mosaic internal tools. Defines the approved tech stack, project structure, security baseline, deployment requirements, and communication standards. Auto-activates for every agent in the plugin — this is the single source of truth for what "good" looks like when non-engineering teams build internal tools with Claude Code.

Templates and rules for creating project documentation: PRDs, tech specs, and Architecture Decision Records (ADRs). Includes mermaid diagram patterns, folder structure conventions, and document lifecycle rules (create, update, refresh). Auto-activates when the user asks to document, create a PRD, write a spec, record a decision, update docs, compare docs to code, or uses the document command.

7 hooks across 5 events