Development & Agent Automation Skills

Automates Apple-platform apps (iOS, tvOS, macOS) and Android devices. Use when navigating apps, taking snapshots/screenshots, tapping, typing, scrolling, extracting UI info, collecting logs/network/perf evidence, or planning agent-device CLI commands.

Create or update durable agent goals by turning user intent into a polished, outcome-first closed feedback loop prompt. Use when the user asks to create, update, write, refine, or install a goal, or mentions goal prompts, closed feedback loops, goal tool usage, or goal instructions.

Creates pull requests with generated descriptions. Triggered when: PR creation, pull request, merge request, code review preparation.

Use when pair programming with humans - enforces XP values (communication, simplicity, feedback, courage, respect) to deliver high-quality software; push back on YAGNI violations regardless of seniority or sunk…

Read this skill before making git commits; use this skill when the user asks you to commit the code, or before pushing or making a new github pull…

Interactive model selection workflow with paginated navigation. Use when users want to select a model interactively - guides them through provider selection then model selection using the question tool with pagination support for large lists.

Framework for building AI agents that work effectively across multiple context windows on complex, long-running tasks. Use when building agents for multi-hour/multi-day projects, implementing persistent coding workflows, creating systems that need state management across sessions, or when an agent needs to make incremental progress on large codebases. Provides initializer and coding agent patterns, progress tracking, feature management, and session handoff strategies.

Generate beautiful, self-contained HTML visualizations themed with Plannotator's design system. Wraps the visual-explainer skill by nicobailon with Plannotator theme token integration. Use for architecture diagrams, diff reviews, plan reviews, data tables, slide decks, project recaps, or any visual explanation of technical concepts — whenever you want output styled consistently with Plannotator's UI and compatible with --render-html annotation. Triggers on the same prompts as visual-explainer (diagrams, architecture overviews, visual plans, diff reviews) but produces output that uses Plannotator CSS custom properties instead of custom palettes.

Run an extremely strict maintainability review for abstraction quality, giant files, and spaghetti-condition growth.

Upgrade this agent wrapper to a newly released upstream earendil-works/pi version, including package versions, lockfile, release manifest, patch-package patches, verification, commit, and push. Use when user asks to upgrade Pi, update to a new Pi release/tag/version, regenerate Pi patches, or handle repeated upstream Pi release bumps.

Run the gemini CLI in headless mode for one-off prompts, model-directed Gemini tasks, structured output capture, and follow-up messages against prior Gemini sessions. Use when the user asks to use Gemini CLI, mentions gemini -p, wants Gemini in non-interactive mode, wants a flash or pro Gemini run, needs project-scoped session discovery, or wants to continue an older Gemini session from the terminal instead of the interactive TUI.

Verify a claim with fresh local evidence. restate it falsifiably, capture baseline and treatment, compare artifacts, and return VERIFIED, NOT VERIFIED, or INCONCLUSIVE. Use this skill when the user asks to verify a claim or say verify this, prove it works, or did this fix it.

Fetch web pages and convert them to clean Markdown using markdown.new. Use when user wants to fetch a URL as markdown, convert HTML to markdown, or extract clean text from websites.