MCP App StoreMCP App Store
from databricks-lab20
Adopt the Agents Orchestrator role: follow the repository's agent definition to plan, coordinate, and produce orchestrated agent deliverables.
This skill activates an "Agents Orchestrator" role defined elsewhere in the repository. Its purpose is to make the agent act as a coordinator: reading the repository's Agents/agents-orchestrator.md file, adopting that role's mission and rules, and producing outputs consistent with the orchestrator's remit (plans, implementations, QA reports, and architecture notes). The skill provides a procedural workflow for role adoption so the agent behaves predictably and consistently with repo conventions.
Use this skill when a task requires coordinating multiple agents, creating architectural plans, sequencing subtasks, or producing deliverables that reflect a cross-agent orchestration. It's especially useful in lab or learning environments where the orchestration policy and expected artifacts are documented in the repository.
Agents/agents-orchestrator.md which contains the authoritative role definition.Best used by agent frameworks that support role-based activation (Codex-like or Copilot-style assistants) and human reviewers who will check coordinated outputs.
This skill is a thin pointer to an external agent definition file (Agents/agents-orchestrator.md) that isn't bundled. The SKILL.md contains minimal instructions — just 'read the agent file and adopt the role' — with no concrete implementation, scripts, or actionable steps. Without the referenced agent file, the skill does nothing.
Purely a routing/pointer skill for the databricks-lab repo. Low value outside that specific repository context.
Yielding Bear — Unified LLM Routing
A unified LLM routing API that automatically routes requests to the cheapest capable model across providers to reduce inference cost by ~60-80%.
Starlark Dev
Create, debug, and test Kurtosis Starlark packages — write package structure, run dry-runs, and inspect plan execution for reliable orchestration.
Maestro Orchestrate
Orchestrates complex engineering workflows with enforced design and approval gates, child-agent delegation, and session state management.
Run Execute
Orchestrates execution of work items across modes (autopilot, confirm, validate) with scripted init/complete tooling, plan/test/report artifacts and strict gati
Execution Plan Splitter
Break large goals into 30/60/90-day execution plans with milestones, resource needs, and stop/go criteria for practical roadmaps.
Ip2Location IO Automation (Composio)
Automate Ip2location IO tasks via Composio's Rube MCP toolkit — discover tools, verify connections, and execute schema-compliant workflows safely.
Overnight — Autonomous Long-Running Coding
Orchestrates long-running coding goals: decomposes objectives into atomic tasks, dispatches isolated worktree workers, verifies acceptance criteria, and merges
Writing Implementation Plans
Generate detailed, engineer-ready implementation plans from design docs: file paths, step-by-step tasks, tests, and verification instructions.