Loading...
Loading...
Found 4 Skills
Invoke a Rubber Duck Reviewer subagent to independently critique plans and implementations before proceeding. Use when the agent is about to implement a non-trivial plan (multi-file changes, architectural decisions, security-sensitive logic, database schema changes), after completing a self-contained unit of work (module, endpoint, feature), when stuck or facing repeated failures (same test fails 2+ times, unexpected results), or when the agent wants independent validation of assumptions and design decisions. Triggers on any non-trivial implementation task where independent critique would catch blind spots before they become costly mistakes.
Systematically identify what's missing in non-fiction writing—both blind spots (inherent limitations) and blank spots (gaps that could be addressed). Use before finalizing non-fiction or when feedback feels incomplete.
User-invoked read-only pass for checking whether the current direction is tunnel-visioned: strip the session's bait, fan out 2 to 5 same-model fresh reads, and report divergence first without treating convergence as proof.
Closing ritual — surface doubts, blind spots, and unverified claims before work is accepted. Use when the user signals acceptance or session end ("wrap up", "closing ritual", "before I accept this").