skills

This skill should be used when the user asks to "autofix pr", "fix pr locally", "fix ci failures", "fix review comments", "iterate on pr", "fix failing checks", "fix pr comments", "make ci green", "fix the build", "address reviewer feedback", or wants to iteratively fix CI failures and review comments on a GitHub PR from the local CLI.

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

Extract the design system (fonts, logos, colors, CSS tokens, favicons, OG assets) from a public website URL into a fresh local git repo with a fact-only README. Use when the user wants to "extract a design system", "steal a design", "pull fonts and colors from a site", "scrape design tokens", "build a design-system repo from a URL", or prepare assets to upload to claude.ai/design.

This skill should be used when the user asks to "investigate issue", "investigate

Upscale raster images with a local OpenCV EDSR super-resolution model, then produce an exact target pixel size. Use when the user asks to upscale, enlarge, super-resolve, make a higher-resolution version, or create a wallpaper/print-size raster from an existing image while preserving the original artwork.

This skill should be used when the user asks to "plan this", "make a plan", "create an implementation plan", "how should I implement", "design the implementation", "plan the refactor", "plan the migration", "plan the feature", "break this down into steps", "implementation strategy", "deep plan", "thorough plan", or wants a thorough, multi-phase implementation plan with codebase exploration before writing any code.

This skill should be used when the user asks to "get a second opinion", "ask codex", "what does GPT think", "compare with codex", "run codex", "2nd opinion", "second opinion on this code", or wants an independent analysis from OpenAI Codex CLI. Also triggered by the /codex-2nd-opinion command.

This skill should be used when the user asks "is this a skill", "can we extract a skill", "skill extraction", "is there a reusable pattern here", "should this be a skill", "extract skill", or wants to analyze the current session for reusable patterns that could become a Claude Code skill. Also triggered by the /is-skill command.

This skill should be used when the user asks to "compare code", "compare worktrees", "compare solutions", "which solution is better", "compare branches", "best of", "diff worktrees", "evaluate solutions", "pick the better implementation", "compare implementations", "review both solutions", or wants a structured, criteria-driven comparison of code across two git worktrees. Also triggered by the /best-of command.

This skill should be used when the user asks to "fork", "race claude and codex", "dual implement", "run both models", "compare implementations", "implement with both", "fork it", or wants the same task implemented by both Claude Code and OpenAI Codex in parallel to pick the best result. Also triggered by the /fork command.

This skill should be used when the user asks "what's going on", "wigo", "status", "where was I", "what were we doing", "catch me up", "tree status", "branch status", or wants a comprehensive situational briefing on the current git tree, session history, and associated PR. Also triggered by the /wigo command.

This skill should be used when the user asks to "merge dependabot PRs", "review dependabot", "auto-merge dependencies", "handle dependabot", "merge dependency updates", "check dependabot PRs", or wants to automatically review and merge open Dependabot pull requests. Also triggered by the /auto-merge-dependabot command.

This skill should be used when the user asks to "commit and push", "cp", "commit push", "ship it", "push my changes", or wants to commit and push while respecting the project's CLAUDE.md (or AGENTS.md) commit requirements. Also triggered by the /cp command.