meridian

Handle CodeRabbit AI review cycles after creating a PR

You have been asked to think through a problem before acting.

Start a work-until loop that keeps you working on a task until completion

Reviews architecture — either existing code or proposed plans. Use during planning to validate approach, or after changes to check structural health.

Finds dead code, pattern drift, over-engineering, and refactoring opportunities. Use after completing large tasks, at the end of feature work, or when code has gone through many iterations.

Deep code review that finds real bugs — logic errors, data flow issues, pattern inconsistencies. Returns structured findings to the calling agent.

Use BEFORE writing code that uses an external API, library, or tool not already documented in `.meridian/api-docs/`. Researches via web scraping and builds comprehensive knowledge docs with current versions, API operations, limits, and gotchas.

Use for broad codebase research when you don't know where to look, need to understand "how does X work?", or want comprehensive findings across many files. Returns file paths, line numbers, code snippets, and negative results. Read-only — cannot modify files.

Use when you have a detailed, unambiguous implementation spec (e.g., "add export for function X in file Y"). Executes the spec, runs typecheck/tests, reports results. Spawn multiple in parallel for independent tasks. Does NOT ask questions — reports ambiguity and stops.

Documents planned work in Pebble before implementation. Creates appropriate structure (epic, task, or bug fix) based on scope.

Validate a plan before implementation. Use before exiting Plan mode. Pass the plan file path and any additional context files. Returns JSON with findings and score (must reach 9+ to proceed).

Scan all .md files in the project and add or fix YAML frontmatter (summary + read_when) so they can be discovered by context routers like Reflex.

Create or update .meridian/docs/ knowledge files for a module or directory. Produces reference docs with frontmatter for context routing.

Audit code for silent error swallowing, fallbacks to degraded alternatives, backwards compatibility shims, and UI that fails to show errors to the user. Finds and fixes all occurrences in the specified scope.

Audit code for observability gaps — debug logs left in, errors caught without being logged, missing context on log entries, untracked slow operations. Uses the app's existing observability tooling exclusively.

Interview-driven planning methodology that produces implementation-ready plans. Always use this skill INSTEAD of EnterPlanMode — it provides structured interviewing (20-40 clarifying questions), exhaustive parallel codebase exploration (5-15 Explore agents), verbatim requirements capture, and automated plan validation via plan-reviewer (must score 9+). Use for new features, refactoring, architecture changes, migrations, or any non-trivial implementation work.

Audit UI code for missing loading states, empty states, and error states. Every async operation and data-driven UI must handle all three. Finds gaps and implements the missing states using the app's existing patterns.

15 hooks across 7 events