Pesquisa e Web

Detects shared stack membership and iterates a command across all PRs in base-to-tip order. Use when a command supports --stack flag for multi-PR iteration.

Audits Makefiles for build correctness, portability, and recipe duplication. Use when reviewing a Makefile or before committing Makefile changes.

Detects codebase bloat via dead code, duplication, complexity, and doc bloat scans. Use when codebase feels large or before a release.

Searches and navigates stored knowledge in memory palaces. Use when looking for previously stored information or cross-referencing concepts across palaces.

Selects optimal sources for tool calls, balancing accuracy with token cost. Use before research tasks or when deciding whether a claim needs verification.

Guide creating Claude Code skills with TDD and persuasion principles. Use for new skill development.

Scores backlog items with RICE/WSJF/Kano and files GitHub issues for top candidates. Use when triaging a roadmap or prioritizing features for a sprint.

Applies client-server architecture for web/mobile apps. Use when designing systems with centralized backend services, trust boundaries, or offline-first sync.

Records browser sessions via Playwright and converts video to GIF. Use when creating web UI tutorials or demos showing browser interactions.

Standardizes release approvals with GitHub-aware checklists and deployment gates. Use before releasing to production to verify all gates pass.

Generates a compressed project context map to avoid expensive Read/Grep calls. Use at session start or before implementing features in an unfamiliar codebase.

Assesses decision reversibility and risk at critical checkpoints. Use when a workflow reaches a high-stakes branch needing escalation check.