rosneri

Trace the second-, third-, and nth-order consequences of a decision, change, or plan — the effects of the effects — so thinking doesn't stop at the obvious first-order outcome. Use when the user asks "what are the consequences of X", "think this through", "second-order effects", "n order consequences", "what could this cause downstream", or before committing to a significant decision (technical, product, organizational, personal).

Quiz the user on whether they actually understand a code change before it ships. Generates a short literate explainer of a diff, then administers five comprehension questions that test how the change works — not requirements, not trivia. Use before opening a PR, before merging, when reviewing someone else's PR, or when the user says "quiz me on this", "do I understand this change", "code quiz", "gate this PR", or wants to check comprehension of AI-written code.

Bruno API client skill — .bru file format, JavaScript API reference, authentication patterns, testing with Chai.js, and Git-first collection management.

Review feature code against DDD and hexagonal architecture principles. Validates domain entities, value objects, use cases, adapters, folder structure, file naming, and test placement.

Create Phase 0 documentation for a new feature. Generates docs folder structure with plan.md, glossary.md, business-logic.md, architecture.md, errors.md, questions.md, and adr/ folder. Use before any code is written.

Git operations enforcer - manages branches, commits, and pull requests with strict naming conventions and quality gates

Teaches Helix editor by analyzing the user's existing configuration, explaining keybindings and LSP setup, and answering questions. Use when the user asks about Helix, their helix config, keybindings, LSP setup, themes, or wants help setting up or learning Helix. Also triggers on "helix keybindings", "explain my helix config", "helix setup", "learn helix", or "hx config".

Teaches Neovim by analyzing the user's existing configuration, explaining installed plugins and keymaps, and answering questions. Use when the user asks about Neovim, Vim, their nvim config, plugins, keymaps, LSP setup, or wants help setting up or learning Neovim. Also triggers on "what plugins do I have", "explain my neovim", "neovim setup", or "learn vim".

Run a manual test of the ralph CLI to verify it works end-to-end. Use when you need to smoke test ralph after making changes.

End-to-end ship a feature in this repo — fresh branch from main, local CI gates, commit + push, PR with body, wait for CI, squash-merge, tag at main HEAD, wait for npm publish, verify. Use when the user says "ship this", "release a new version", "create a PR and publish", or describes a code change that should land on npm.

Run CI targets locally, push, and watch remote CI checks. Surfaces issues concisely. All output saved to /tmp.

Enforce test-first workflow for bug fixes. Use whenever the user asks to fix a bug, defect, regression, or issue. Write a failing test that captures the bug AND a passing test for the correct behavior BEFORE touching production code, then fix and flip.

End-to-end ship a feature in this repo — fresh branch from main, local CI gates, commit + push, PR with body, wait for CI, squash-merge, tag at main HEAD, wait for npm publish, verify. Use when the user says "ship this", "release a new version", "create a PR and publish", or describes a code change that should land on npm.

Run a manual test of the ralph CLI to verify it works end-to-end. Use when you need to smoke test ralph after making changes.

Access and search Apple Contacts on macOS using AppleScript. Use when the user asks to look up a contact, find a phone number or email, search contacts by name, or get details about someone in their address book. macOS only.

Debug a running Node.js process via CDP (Chrome DevTools Protocol). Set breakpoints, step through code, inspect variables, and evaluate expressions — all headless, no GUI needed.