Toolshed
An agent capability and operations platform comprising 112 reusable skills plus executable services, MCP integrations, scheduled workflows, approvals, monitoring, and recoverable deployment.
Overview
Toolshed is the capability and operating layer I built around agent runtimes such as OpenClaw. It packages 112 verified top-level skills together with executable services, MCP integrations, scheduled workflows, shared state, approval boundaries, monitoring, and multi-host deployment. OpenClaw is an upstream runtime the platform integrates with—not a platform I claim to have authored.
The Problem
An agent demo can call a tool once. An operating capability platform has to make hundreds of heterogeneous workflows discoverable, repeatable, permission-aware, observable, and recoverable across machines without letting automation outrun ownership or safety boundaries.
The Solution
Built a portable skills and services layer spanning research, commerce, prediction, browser automation, voice, infrastructure, and content. MCP tools, scheduled execution, shared state, approval gates, alert routing, and deployment workflows run across Mac and NVIDIA Jetson hosts. Health checks, circuit breakers, canaries, drift tripwires, reconciliation, audit trails, and rollback controls keep operations bounded.
Key Results
112 verified top-level skills
MCP and scheduled execution
Approval and audit boundaries
Recoverable multi-host operations