yeaight7

Coordinate multiple subagents through dependency-aware waves, stage handoffs, monitoring, and verification loops. Use when the work is too large or too mixed for a single agent.

Analyze BigQuery usage, identify cost hotspots, repeated failures, and practical optimization opportunities.

Use when debugging complex runtime failures, distributed systems, or issues where a local debugger cannot be attached.

Use when optimizing agent runtime loops, card packs, MCP session lifecycle, tool-call count, or multi-agent orchestration patterns.

Modo de comunicação ultracomprimido. Reduz o uso de tokens em ~75% ao remover preenchimentos, artigos e formalidades, mantendo total precisão técnica. Use quando o usuário disser "sem rodeios", "seja conciso" ou "use menos tokens".

Use when diagnosing agent session history, interrupted tool loops, missing tool results, timing bottlenecks, or subagent trace correlation.

Create and edit JSON Canvas files (.canvas) with nodes, edges, groups, and connections. Use when working with .canvas files, creating visual canvases, mind maps, flowcharts, or when the user mentions Canvas files in Obsidian.

Inspect changed dbt assets, estimate blast radius, identify missing tests, and recommend the narrowest safe validation plan.

Create or refactor high-quality skills with lean frontmatter, progressive disclosure, and optional bundled helpers. Use when authoring reusable agent workflows.

Use to restructure code while guaranteeing that all existing tests continue to pass.

Use when evaluating prompts, LLM outputs, red-team suites, or model behavior with local eval configs and safe provider/cost controls.

Use to isolate a bug from a large application into a standalone, runnable script or single test case.