dotfiles

Thorough, critical code review focused on correctness, business logic, implementation, tests, and documentation. Use when reviewing code changes, pull requests, or implementations. Only invoke when user explicitly asks for code review.

Use when the user asks to create or render a Mermaid or Merman chart, mentions merman-cli, or wants an ASCII terminal diagram. Render it with `merman-cli`.

Defensive security review and hardening of application code, configuration, dependencies, and tests using current OWASP guidance. Use only when the user explicitly asks for a security review, security audit, vulnerability review, or security hardening. Do not use for general code review.

Expert guidance for using the GitLab CLI (glab) to manage GitLab issues, merge requests, CI/CD pipelines, repositories, and other GitLab operations from the command line. Use this skill when the user needs to interact with GitLab resources or perform GitLab workflows. Assumes the user is already authenticated.

Use when editing, modifying, or transforming existing image files with AI using the local Gemini image-edit CLI. Trigger this for style changes, object removal, background edits, text/layout fixes, color tweaks, or when the user says to use image-edit from the terminal. This skill runs the global `image-edit` executable from any repo.

Use when generating image files from text prompts with the local Gemini image CLI. Trigger this when the user asks to create, generate, or render an AI image, artwork, ad image, book cover, mockup, visual asset, or says to use image-gen from the terminal. This skill runs the global `image-gen` executable from any repo.

Use when the user asks for a "1-3-1", wants decision options, or needs a concise recommendation to forward. Produces one problem, three options, one recommendation, success criteria, and an action plan.

Use when implementing any feature or bugfix, before writing implementation code

Use when creating, editing, or modifying opencode.jsonc configuration files OR opencode plugins. Triggers on permission changes, tool configuration, model settings, MCP servers, agent preferences, custom tools, event hooks, notifications, or modifying default opencode behavior. Make sure to use this skill whenever the user mentions opencode settings, opencode.jsonc, opencode plugins, custom opencode tools, opencode hooks, or opencode configuration of any kind.

Only use this skill when the user explicitly invokes or asks for it. This is an interactive skill that requires the user to be in the loop at all times.

Use when creating, listing, or viewing GitHub issues via CLI - triggers on issue management tasks, bug reporting, or feature requests

Use when analyzing server performance, diagnosing resource issues, investigating alerts, or making optimization recommendations using Netdata API

Process ATODO (Agent TODO) comments from code review. Finds comments like `// ATODO: refactor this` or `# ATODO: add error handling`, executes the instructions, and removes the comments.