A multi-agent pipeline that processed a document library in parallel under a fixed work plan, gated every wording change behind a human reviewer, wrote an audit log before touching any file, and resumed from its checkpoints after interruption.
Open-source agent skills implementing the agentskills.io specification. Portable across compatible harnesses.
Panel of five role-specialized skills (visionary, skeptic, operator, ethicist, subject expert). Each analyzes a decision independently; an orchestrator synthesizes the outputs and preserves dissent.
LLM evaluation harness using assertion-based LLM-as-judge under claude --bare clean-room isolation. Extends the agentskills.io single-skill eval pattern to multi-skill and orchestrator evaluation.
If you're building agent systems that need an audit trail and a human in the loop, email us and we'll see if it fits.