Desenvolvimento

Use when reviewing AI-generated code for architectural quality, design patterns, and engineering practices

Run coding agent benchmarks and verify results with nasde. Use this skill when the user wants to: - Run a benchmark (all tasks, single task, specific variant) - Re-run assessment evaluation on existing trial results - Check or verify results in Opik (traces, feedback scores, experiments) - Troubleshoot a failed benchmark run - View or compare trial results Even if the user doesn't say "benchmark"

Produz um resumo estruturado de como outras mídias já cobriram um determinado tópico, permitindo que você aborde qualquer história com uma visão clara do cenário midiático existente.

Scan the repo for scattered documentation files, analyze organization issues, and output cleanup recommendations. Analysis only — no changes made.

Runs a structured checklist over every statistic in your draft — flagging figures that look wrong, comparisons that may mislead, and numbers that need a primary source before they are safe to publish.

Test coverage analysis: detect test framework, run test suite, capture failures and coverage metrics, identify coverage gaps in recent changes, and create a structured GitHub issue.

Delegate coding to OpenAI Codex CLI (features, PRs).

When the user wants to optimize signup, registration, account creation, or trial activation flows. Also use when the user mentions "signup conversions," "registration friction," "signup form optimization," "free trial signup," "reduce signup dropoff," or "account creation flow." For post-signup onboarding, see onboarding-cro.

Deep code review via Claude subagent — reviews uncommitted changes by default, loops until no critical issues remain. Use after /qq:test passes, before /qq:commit-push.

PK Stage — multi-AI competitive debate with iterative consensus. Sends a topic to all configured AI participants simultaneously, synthesizes the best approach, then iterates until consensus or max rounds.

Writes a structured dramatic character profile — covering psychology, backstory, want, need, flaw, wound, and voice — that a screenwriter can use throughout a full draft.

This skill should be used when the user wants to "create a skill", "add a skill to plugin", "write a new skill", "improve skill description", "organize skill content", or needs guidance on skill structure, progressive disclosure, or skill development best practices for Claude Code plugins.