Menu
Explain a code location, component, command, or user-facing system flow. Use when the user asks what code does, why it exists, how a feature works, or wants a trace of entry points, branches, dependencies, and side effects.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Pressure-test an assumption, architecture decision, estimate, or inherited constraint. Use when the user asks to challenge a belief, play devil's advocate, test reasoning, or find a simpler alternative.
Prepare difficult technical or delivery news for a client, stakeholder, or team. Use for delays, incidents, security findings, cost changes, failed approaches, or other conversations where clarity and trust matter.
Plan and work through project, client, vendor, or team offboarding. Use for handovers, access removal, ownership transfer, documentation, credential rotation, data cleanup, and knowledge-transfer checklists.
Discover how a codebase already handles a concern before extending it. Use when asked how the repository does something, where a pattern lives, whether implementations are consistent, or what convention new work should follow.
Help the user think through a confusing problem or decision by asking focused questions and reflecting their reasoning. Use when they want to think out loud, untangle a problem, or find the question beneath the question.
Project-aware router for Ruby and Rails development. Use for gems, Rails, RSpec, Minitest, Cucumber, SimpleCov, RuboCop, RubyCritic, PostgreSQL, Active Record, debugging, reviews, performance, security, i18n, Sorbet, RBS, Ruby LSP, or Ruby runtime and tooling work.
| name | explain |
| description | Explain a code location, component, command, or user-facing system flow. Use when the user asks what code does, why it exists, how a feature works, or wants a trace of entry points, branches, dependencies, and side effects. |
Build a working mental model and explain it in one pass. This is explanation, not code review; identify surprising behavior without turning preferences into findings.
Start from the named file, symbol, command, feature, or user action. Inspect the implementation, relevant callers, configuration, tests, and generated or framework entry points. Consult local Git history when it materially explains why surprising code exists. Do not fetch remotes merely to add history.
Cover, in the order that best fits the target:
Skip line-by-line narration of obvious syntax. Include precise file and line references using the host application's supported format.
Find every relevant route, event, scheduled task, command, or integration entry point. Trace success and failure paths through authorization, application logic, persistence, jobs, notifications, storage, and external systems. Summarize:
Use a compact diagram only when it makes the lifecycle easier to understand than prose.
Adapted from Thoughtbot's rails-consultant explain skill at
revision f2cb97d. Distributed under the accompanying MIT license.
