Desenvolvimento

Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/PRD asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to

Defines context handover format when workers hit turn limit. Posts structured handover to GitHub issue comments enabling replacement workers to continue seamlessly.

Subjects every non-trivial decision to a fresh-context adversarial review before it stands. Use when correctness matters more than speed, when working in unfamiliar code, when stakes are high (production, security-sensitive logic, irreversible operations), or any time a confident output would be cheaper to verify now than to debug later.

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

Generates a structured brief identifying the types of experts needed for a story, where to find them, and how to approach them credibly.

TDD: enforce RED-GREEN-REFACTOR, tests before code.

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback

Produces a structured framework for reviewing how a topic has been covered by other media outlets — identifying the dominant narrative frames, the sources quoted, the angles explored, and the gaps in coverage — so a journalist can find the untold story and avoid repeating what has already been reported.

Use for any development work - the master 13-step coding process that orchestrates all other skills, ensuring GitHub issue tracking, proper branching, TDD, code review, and CI verification

Use local Codex/Claude JSONL logs as evidence, then produce a human-written daily diary summary and write it into Obsidian. Keep directory filtering (for example rag-flow/rag-recall) and avoid mechanical script-style output.

Discovery stage — multi-AI codebase and running app exploration

Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, mentions "red-green-refactor", wants integration tests, or asks for test-first development.