Agent Building skills
Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Copilot instruction layering
instruction layering with reusable, conditional instruction files
development workflow
workflow patterns for planning, subagents, self-improvement, and verification
google-workspace-auth
Re-authenticate Google Workspace MCP in-flight - refresh tokens, setup OAuth, check status
pm-delegation-patterns
Common delegation patterns for PM agent
arbiteros-instruction-metadata-dsl-writer
Guides users through creating, validating, and registering a new ArbiterOS instruction-metadata DSL YAML file. Use this skill whenever a user wants to add a new instruction metadata parser for ArbiterOS, write a DSL for a new agent type, classify instruction calls for a new agent integration, add support for a new agent's instructions to ArbiterOS, or validate an existing DSL file against the instruction_parsers schema. Also trigger for phrases like "add new agent parser", "create DSL for X agent", "register instruction parsers", "write instruction_parsers yaml", or when the user describes instructions from an agent that ArbiterOS doesn't know about yet.
build-protocol-server
Model Context Protocol (MCP) server build and evaluation guide, including local conventions for tool surfaces, config, and testing
codebase-index
Generate a pre-computed component index from a design system codebase — YAML infrastructure files containing a component inventory, relationship graph, and summary statistics that AI agents and MCP servers consume. This produces machine-readable index files in .ai/index/, NOT a health report or quality assessment. Trigger when someone says: index my codebase, build a relationship graph, create a component map, codebase index, what depends on what, dependency graph, map component relationships, or anything about producing queryable infrastructure files for AI agents or developer tooling. Do NOT trigger for component health assessments, quality scores, or audit reports — use component-audit for those.
component-decision-tree
Build queryable decision trees that help agents and teams choose between components — structured YAML files mapping user intents to the correct component through a sequence of narrowing questions. This produces selection logic for choosing BETWEEN components, NOT usage guidelines for a single component. Trigger when someone says: component decision tree, which component should I use, help me choose between, selection guide, decision framework, modal vs dialog, intent-to-component mapping, or anything about creating structured logic for picking the right component from alternatives. Do NOT trigger for usage guidance on a specific component — use usage-guidelines for that.