ai-config

Use the Xero MCP server — obtain/refresh OAuth2 bearer tokens, troubleshoot authentication, and pick up other operational notes for working with Xero MCP tools. Use when Xero MCP tools fail with authentication errors, when the bearer token has expired (tokens last ~30 min), before starting any Xero workflow, or for general guidance on Xero MCP usage.

General Xero browser automation notes. Use when automating any Xero page with agent-browser — covers non-standard UI patterns, waiting, and dropdown menus.

Size the agent-browser Chromium window to fill its current screen, leaving a configurable bottom margin for the desktop panel. Use before any agent-browser automation that needs the full screen visible without elements overlapping or scrolling off (e.g. Xero, dense web apps).

Review all unreviewed documents in Hubdoc. Use when reviewing, processing or publishing Hubdoc receipts and bills.

Convert XLSX spreadsheets (single or multi-sheet) to CSV files you can read and grep. Use whenever you need to process an .xlsx report from Xero, Cryptio, bank exports, or any tool that delivers spreadsheet output.

Create Claude Code slash commands, OpenCode command files, and Pi prompt templates that delegate to the right subagent or skill. Use when creating new commands or refactoring existing ones to follow platform conventions.

Generate a PR description for the current branch. Writes Markdown to .git/magit/posts/new-pullreq for use with magit-forge.

Find and address all unresolved GitHub PR review comments on the current branch's pull request. Use when the user asks to resolve, address, respond to, or reply to PR review feedback — whether from humans, CodeRabbit, Copilot, Claude Code reviewer, or any other source. Triggers on "/rr", "resolve review comments", "address PR feedback", "reply to review threads", "deal with CodeRabbit", etc.

Find Linear issues ready for an AI agent to pick up. Equivalent of `bd ready` for Linear workflows. Use when starting a session to find claimable work, or when asked "what's next" or "find work".

Decompose an approved implementation plan into self-contained Linear issues with zero guesswork. Use when breaking down a plan into actionable Linear tasks via the MCP server.

Decompose an approved implementation plan into self-contained beads issues with zero guesswork. Use when breaking down a plan file into actionable beads tasks.

Update documentation based on lessons learned. Use after completing work to capture learnings and prevent future issues.

Remove code duplication by extracting shared logic into reusable components. Use when the same logic appears in multiple places.

Add or change allowed commands in AI agent permission configs (OpenCode, Claude Code)

Run linters according to repository guidelines. Use immediately after creating or modifying code, or before committing changes.

Refactor overly large code units into smaller, more focused components. Use when code has grown too large or complex.

Review code for quality, security, and maintainability. Use after code changes are completed and ready for review.

Generate a .editorconfig file for a repository

Create well-formatted commits following conventional commits style with proper atomic commits and descriptive messages

Stage files, hunks, or specific lines in git non-interactively.

Implement sub-tasks iteratively with user approval between each one. Use when working through a task list with user collaboration.

Manage Open Build Service (OBS) projects. Use when working with OBS packages for home:aspiers.

Initialize a project with AI agent rules and documentation. Use when setting up a new repository for AI agent collaboration.

Generate a Product Requirements Prompt (PRP) from a feature description. Use when starting work on a new feature.

Safely delete files / directories without asking for permission

Create and maintain Claude Code skills following Anthropic best practices. Use when building new skills, refactoring existing ones, or ensuring skills follow official guidelines for structure, naming, progressive disclosure, and testing.

Pipe long running commands through tee(1) to allow watching output and repeated analyses without rerunning

Create subagent definitions for Claude Code and OpenCode that delegate to skills. Use when creating new subagents or refactoring existing ones to follow the delegation pattern.

Generate a detailed task list from a PRP. Use after a PRP is created and ready for implementation planning.

Implement a single sub-task from a task list. Use when working on feature development with existing task lists.

Orchestrate the complete development workflow for implementing sub-tasks from a task list. Use for end-to-end feature implementation with quality controls.

Run tests according to repository guidelines. Use after linting passes, before staging changes.