ralph-ban

This skill should be used when the user asks to "QA browser changes", "verify a web UI", "test the browser flow", "check the page works", "validate the dev server", or wants end-to-end behavioral verification of web pages or web apps. Drives a real browser to navigate, snapshot, interact, and capture evidence — supports both agent-browser (preferred) and playwright-cli, picking whichever is installed.

This skill should be used when the user asks to "QA a CLI tool", "verify a command-line program", "check the binary's output", "validate exit codes", "compare against a golden file", or wants end-to-end behavioural verification of command-line tools. Drives a binary with representative inputs, captures stdout / stderr / exit code as separate evidence channels, asserts via golden-file comparison with volatile-field redaction.

This skill should be used when the user asks to "verify database state", "check what's in the database", "assert DB rows after the action", "validate the migration", or wants behavioural verification of database side effects. Snapshots database state before the action, exercises the system, snapshots after, and diffs structurally — ignoring volatile fields the spec does not assert. Used by primary-surface oracles (http-qa, cli-qa, library-qa) when a card asserts side-effect behaviour.

This skill should be used when the user asks to "QA an HTTP endpoint", "verify an API", "check the API behaves", "drive the API", "validate a route", or wants end-to-end behavioural verification of HTTP/JSON services. Drives a real running service with curl + jq, asserts on status / shape / headers / timing, captures the full request-response transcript as evidence, and distinguishes spec violations from flake.

This skill should be used when the user asks to "QA a library", "verify the package", "check the API behaves", "exercise the module", or wants end-to-end behavioural verification of an importable library or package (Go, Ruby, TypeScript, etc.). Writes a one-shot consumer program in scratch space, runs it against the library under test, observes structured output, and judges whether the behaviour matches the card's spec.

This skill should be used when the user asks to "verify a log line appears", "wait for the log message", "check the audit log", "assert async behaviour from the log", or wants behavioural verification of asynchronous side effects observable only through a log file or stream. Tails a log file with bounded waiting, asserts pattern presence with history-vs-tail semantics and occurrence counts, fails fast when the log stops growing. Used by primary-surface oracles (http-qa, cli-qa, library-qa) when a card asserts log-emission behaviour.

Break down work into board cards for ralph-ban orchestration. This skill should be used when the user has a plan, design doc, or clear requirement to decompose into epics and tasks with EARS specs. Triggers on "plan this", "create cards", "break this down", "decompose into tasks", "rb-planning", "put this on the board", or when a design doc from /rb-brainstorm needs to become actionable work. Creates cards via bl CLI with specs, priorities, dependencies, and epic grouping.

This skill should be used when the user asks to "QA changes", "verify this works", "test the build", "check if this runs", "validate changes in tmux", or wants end-to-end verification of code changes by running builds, tests, and applications in tmux.

Interactive brainstorming for ralph-ban projects. This skill should be used when the user has a fuzzy idea, vague goal, or problem statement that needs exploration before it becomes board cards. Triggers on "brainstorm", "explore an idea", "I want to build", "let's think about", "what should we build", "I have an idea", or any request that needs design exploration before planning. Produces a design doc in .agent-history/ that feeds into /rb-planning.