Run independent multi-agent build and review flows with OPC
Use OPC as a Claude Code skill to select a task flow, dispatch specialist roles, enforce independent review, and gate builds, audits, and release checks.
npx skills add agentskillexchange/skills --skill run-independent-multi-agent-build-and-review-flows-with-opc
npm install -g @touchskyer/opc; the package postinstall copies the skill files to ~/.claude/skills/opc/. Manual install is git clone https://github.com/iamtouchskyer/opc.git followed by copying the repo to ~/.claude/skills/opc.Use OPC when a coding task needs structured execution plus independent evaluation inside Claude Code: code review, build-verify flows, full-stack feature work, pre-release checks, or unattended multi-unit loops. The operator invokes `/opc ` or `/opc loop `, OPC selects a flow, dispatches specialist roles, records handoffs, and uses its harness to enforce review independence, cycle limits, gate verdicts, and required evidence. The scope boundary is Claude Code task orchestration and quality gating for a project workspace; it is not merely an npm package, a generic agent framework, or a replacement for normal development tools.
What this skill actually does
Inputs and prerequisites: Claude Code, Node.js 18+, npm, Git, project test commands where available.
Setup notes: Install with npm install -g @touchskyer/opc ; the package postinstall copies the skill files to ~/.claude/skills/opc/ . Manual install is git clone https://github.com/iamtouchskyer/opc.git followed by copying the repo to ~/.claude/skills/opc .
Source and verification boundary: use https://github.com/iamtouchskyer/opc as the canonical reference before running the workflow; keep commands, API calls, CLI usage, and generated outputs reviewable against that upstream source.
Framework fit: publish this as a Claude Code workflow only when the operator can invoke the documented toolchain directly, rather than treating the upstream project as a generic product listing.