MCP App StoreMCP App Store
from pos-sprint8
Orchestrate natural-language vendor searches: parse requests to structured JSON, rank candidates from Baserow, and summarise feedback with an LLM for hiring or
Find Vendor is an end-to-end orchestrator that turns a manager's natural-language request into a structured search and ranked candidate list. It parses the request into a JSON schema, queries Baserow customer/vendor tables, runs ranking scripts, and produces an LLM-powered summary of candidate strengths, risks, and specialty matches. Outputs are formatted for chat and saved to temporary files for follow-up.
Use this skill when a manager describes the specialist they need in plain language (translation, editing, proofreading, or domain-specific tasks like game genres/franchises). It's useful for sourcing contractors, shortlisting candidates, and preparing concise comparative summaries for decision-making.
Designed to run where Python and MCP/Baserow access are available; integrates with MCP tools and expects environment variables for Baserow. Best used in agent hosts that can run external scripts and call mcp__baserow__list_rows.
This skill has not been reviewed by our automated audit pipeline yet.
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
Overnight — Autonomous Long-Running Coding
Orchestrates long-running coding goals: decomposes objectives into atomic tasks, dispatches isolated worktree workers, verifies acceptance criteria, and merges
tmux Remote Control
Control tmux sessions for interactive TTYs: send keystrokes, capture panes, orchestrate parallel coding agents, and monitor output safely.
Build Unplanned Feature
Orchestrates ad-hoc feature development: requirement gathering, planning, implementation and validation across task-planning, implementation, and validation loo
AI Pair Collaboration
Orchestrates a small heterogeneous team of AI agents (author/developer + Codex reviewer + Gemini reviewer) to produce and review content or code in a coordinate
Box0 (b0)
Run and coordinate parallel AI sub-agents locally or on a server to delegate reviews, tests, research, and other specialist tasks.