scaryrawr

Automate browser interactions, test web pages and work with Playwright tests.

Use this skill to create, generate, draw, or edit images/photos into saved PNG files with OMLX image models. Covers text-to-image and image-to-image edits. Do not use for text-only image explanations, screenshot summaries, or non-generative image processing scripts.

Coordinate durable coding-job handoffs between Microsoft Scout and GitHub Copilot through a shared SQLite queue. Use when asked to enqueue work for Copilot, claim or pick up queued work, identify the repository for a claimed job, mark or safely unblock blocked work, release a claimed job for retry, record a pushed branch and draft pull request, or discover blocked and finished jobs. Do not use for ordinary coding work that was not queued or for generic process scheduling.

Use for performing Azure DevOps work — create, inspect, review, comment on, vote on, or manage pull requests; find, query, create, update, and link Azure Boards work items (including building WIQL queries); parse and route dev.azure.com or *.visualstudio.com URLs; and upload PNG/image/file attachments to pull requests. Triggers on Azure DevOps / ADO / Azure Boards links or action requests such as "make an ADO PR", "review this Azure DevOps PR", or "find work items assigned to me". Not for general conceptual explanations that do not act on a specific Azure DevOps resource, and not for GitHub, Jira, or other non-Azure-DevOps tools.

Use this skill to turn a video or audio recording (a talk, meeting, or demo) into written content: documentation, a blog post, tutorial, changelog, or notes. Handles transcription, takeaway synthesis, screenshot/frame selection, and grounded drafting from local OpenAI-compatible media models. Not for real-time transcription, generic video editing, or non-generative media processing.

Use this skill to create, revise, package, evaluate, or optimize GitHub Copilot skills and reusable SKILL.md-based agent instructions. Use it whenever the user wants a new Copilot skill, edits to an existing skill, eval/test prompts, skill benchmarking, skill packaging, trigger-description optimization, or reusable agent instructions.

Create or improve AGENTS.md and project agent-skill guidance for a repository. Use when the user asks to initialize, bootstrap, or set up agent instructions, repo guidelines, AGENTS.md, or reusable skills. Discovers repo structure, commands, existing instruction files, and .agents/skills, then writes concise, high-signal guidance.

Code review an Azure DevOps pull request

When users share links (such as visualstudio.com or dev.azure.com) and/or mention Azure DevOps, use the Azure DevOps CLI to interact with work items, pull requests (PRs), repositories, and more.

Remote control tmux sessions for interactive CLIs (python, gdb, etc.) by sending keystrokes and scraping pane output.

Use this skill for end-of-task digivolution/reflection requests that ask whether durable repo-specific guidance, AGENTS.md/Copilot instructions, or in-repo SKILL.md instructions are stale, missing, or should be updated.

Use the local smahties MCP server when users ask for semantic code search, conceptual codebase discovery, keyword or hybrid code search, indexing files/directories, checking index status, or listing indexed code units.

Use this skill when smahtiepants MCP tools are available and a task depends on current documentation for a library, framework, language, runtime, API, or CLI tool (for example React, Express, Node, Python, Rust, CSS, Docker, Git, or Bun). Prefer the MCP tools `list_docsets`, `search_docs`, and `get_page_content` before answering from memory whenever API details, option names, defaults, examples, or "is this still current" questions could be stale. This is the MCP-tool version of the smahtiepants documentation workflow; use it instead of shelling out to the CLI when the MCP server is connected.

Use this skill before answering questions or writing code that depends on a specific library, framework, language, runtime, or CLI tool (e.g. React, Express, Node, Python, Rust, CSS, Docker, Git, Bun). Your training data has a cutoff and APIs change, get deprecated, or gain new features after it. smahtiepants searches a local, up-to-date mirror of DevDocs so you can ground answers in current documentation instead of relying on potentially stale memory. Use it whenever you are unsure about an API signature, default, option name, version-specific behavior, or "is this still the right way to do X", and whenever the user asks how to use a library or what a function/flag does.

Update fish shell completions for the GitHub Copilot CLI based on its current help output. Use when asked to update, sync, or refresh completions, or when the CLI has been updated and completions need to match the latest flags, subcommands, and help topics.

Run fish syntax and completion validation for this repository.

Review fish wrapper changes for token injection consistency and safe argument passthrough.

Validate fish wrapper and completion changes with syntax and smoke checks.

Audit or prepare this GNOME Shell extension for extensions.gnome.org review. Use after changing extension lifecycle, asynchronous work, signals, GLib sources, preferences, GSettings, supported Shell versions, packaging, or before a release or EGO submission.

Update the Zsh completion function (_copilot) to match the current copilot CLI interface. Use this skill when the user asks to update, refresh, or sync completions, or when new copilot CLI options, commands, or models need to be added to the completion file.

Use this skill for end-of-task pi-digivolve reflection when deciding whether durable repo-specific guidance, AGENTS.md, pi skills, or in-repo SKILL.md files are stale, missing, or should be updated.

Update PowerShell tab completions for the GitHub Copilot CLI based on its current help output. Use when asked to update, sync, or refresh completions, or when the CLI has been updated and completions need to match the latest flags, subcommands, and help topics.

Update Fish shell completions for Claude Code CLI by running help commands and comparing output against the current completion script. Use when the user asks to update, refresh, or sync completions, or when a new Claude Code version is released.