yeaight7

Use when confronted with an unknown failure in CI or production to rapidly categorize the issue before deep debugging.

Use to audit and remove unused or redundant third-party dependencies from package manifests.

Deterministic checks first, agent review second, regression test for every real bug fixed or document why not. Targets the blind spot where an agent writes and reviews its own code.

Use when connecting to a managed codebase-context MCP/session service, checking stale maps, or safely using MCP-provided repository context.

Audit whether a dbt incremental model uses the right incremental strategy for the repo, the data shape, and the operational constraints.

Use when the task is to understand an unfamiliar codebase, locate key entry points, or summarize architecture before editing.

Use when conversation context is bloated, constraints are being forgotten, or a compact handoff is needed before continuing work.

any input (code, docs, papers, images) → knowledge graph → clustered communities → HTML + JSON + audit report. Use when the user wants to build, inspect, or query a cross-file knowledge graph from code, docs, papers, images, or videos with upstream graphify.

Utilize ao iniciar um trabalho em um repositório com Agent Powerups instalados, caso a tarefa possa corresponder a uma skill local reutilizável, comando, fluxo de trabalho, receita de hook, modelo AGENTS.md ou recurso MCP.

Um loop determinístico de 3 ciclos para coletar o contexto da base de código antes de agir. Ele envolve uma busca ampla, seguida pela fonte exata e testes, e então documentação e configuração específicas do alvo. O processo para quando há contexto suficiente ou relata o que ainda está faltando.

Relay questions and tasks to a local Claude CLI using one-shot subprocesses per ask.

Use when validating rendered web pages, local dev servers, browser automation, screenshots, forms, auth sessions, or UI evidence with strict browser safety boundaries.