thisisryanswift

Explore requirements and approaches through collaborative dialogue before writing a right-sized requirements document and planning implementation. Use for feature ideas, problem framing, when the user says 'let's brainstorm', or when they want to think through options before deciding what to build. Also use when a user describes a vague or ambitious feature request, asks 'what should we build', 'help me think through X', presents a problem with multiple valid solutions, or seems unsure about scope or direction — even if they don't explicitly ask to brainstorm.

Structured code review using tiered persona agents, confidence-gated findings, and a merge/dedup pipeline. Use when reviewing code changes before creating a PR.

Commit, push, and open a PR with an adaptive, value-first description. Use when the user says "commit and PR", "push and open a PR", "ship this", "create a PR", "open a pull request", "commit push PR", or wants to go from working changes to an open pull request in one step. Also use when the user says "update the PR description", "refresh the PR description", "freshen the PR", or wants to rewrite an existing PR description. Produces PR descriptions that scale in depth with the complexity of the change, avoiding cookie-cutter templates.

Create a git commit with a clear, value-communicating message. Use when the user says "commit", "commit this", "save my changes", "create a commit", or wants to commit staged or unstaged work. Produces well-structured commit messages that follow repo conventions when they exist, and defaults to conventional commit format otherwise.

Refresh stale learning docs and pattern docs under docs/solutions/ by reviewing them against the current codebase, then updating, consolidating, replacing, or deleting the drifted ones. Trigger this skill when the user asks to refresh, audit, sweep, clean up, or consolidate stale docs in docs/solutions/ (phrases like "refresh my learnings", "audit docs/solutions/", "clean up stale learnings", "consolidate overlapping docs", "compound refresh", "/ce-compound-refresh"), or when ce-compound has just captured a new learning and flagged a specific older doc in docs/solutions/ as now inaccurate or superseded — invoke with the narrow scope hint ce-compound provides. Also trigger when the user points at a specific learning or pattern doc under docs/solutions/ and calls it stale, outdated, overlapping, or drifted. Do not trigger for general refactor, migration, debugging, or code-review work unless the user has explicitly directed attention to docs/solutions/ itself.

Document a recently solved problem to compound your team's knowledge

Systematically find root causes and fix bugs. Use when debugging errors, investigating test failures, reproducing bugs from issue trackers (GitHub, Linear, Jira), or when stuck on a problem after failed fix attempts. Also use when the user says 'debug this', 'why is this failing', 'fix this bug', 'trace this error', or pastes stack traces, error messages, or issue references.

Capture a visual demo reel (GIF, terminal recording, screenshots) for PR descriptions. Use when shipping UI changes, CLI features, or any work with observable behavior that benefits from visual proof. Also use when asked to add a demo, record a GIF, screenshot a feature, show what changed visually, create a demo reel, capture evidence, add proof to a PR, or create a before/after comparison.

Use this skill when moving or re-attaching OpenCode agent sessions to a different project/workspace, especially when a session was accidentally started from $HOME or the wrong directory.

Draft and edit Ryan-style developer blog posts from long technical sessions, especially for DEV.to. Use when turning coding sessions, tool explorations, or messy implementation notes into concise public posts.

Use this skill when configuring ToolHive itself: installing MCP servers, registering clients, managing groups, adding skills, handling auth/secrets, and debugging ToolHive workflows across local AI clients.

Delegates tasks to Google Jules, an autonomous AI coding agent. Suggest Jules for time-consuming, well-defined, or parallelizable work. Always ask before sending.

Diagnose and fix generic Wayland taskbar or dock icons caused by desktop-file and runtime app-ID mismatches on Linux, especially Electron or Chromium apps on KDE Plasma.

Delegates tasks to Google Jules, an autonomous AI coding agent. Suggest Jules for time-consuming, well-defined, or parallelizable work. Always ask before sending.

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.

Reviews AI-generated code for correctness, security, performance, and slop. Use this when you are asked to review a diff or recent changes.

Identifies missing test coverage in changed code. Use this when asked to check what tests need to be written for recent changes.

Expert guidance for developing PyQt6 applications. Use when implementing UI components, managing background workers with QThread, handling signals/slots, or troubleshooting high-DPI sizing and layout issues.

Design and UX resource for auditing screenshots and evaluating UI for aesthetic "taste," usability heuristics, and information hierarchy. Use when you need a critique of a UI screenshot or guidance on making an interface feel more modern and polished.

Use this skill when building applications with Gemini models, Gemini API, working with multimodal content (text, images, audio, video), implementing function calling, using structured outputs, or needing current model specifications. Covers SDK usage (google-genai for Python, @google/genai for JavaScript/TypeScript, com.google.genai:google-genai for Java, google.golang.org/genai for Go), model selection, and API capabilities.

Use this skill when writing code that calls the Gemini API for text generation, multi-turn chat, multimodal understanding, image generation, streaming responses, background research tasks, function calling, structured output, or migrating from the old generateContent API. This skill covers the Interactions API, the recommended way to use Gemini models and agents in Python and TypeScript.

Use this skill when building applications with Gemini models, Gemini API, working with multimodal content (text, images, audio, video), implementing function calling, using structured outputs, or needing current model specifications. Covers SDK usage (google-genai for Python, @google/genai for JavaScript/TypeScript, com.google.genai:google-genai for Java, google.golang.org/genai for Go), model selection, and API capabilities.

Use this to generate UI screens, mockups, and frontend code using the Stitch SDK. Can create projects, generate screens from text, edit existing screens, and generate design variants.