Evaluate every user-facing output (errors, warnings, success results, reports, CLI output) for AI agent actionability. pflow is agent-first — every message must help an AI agent diagnose and fix the problem, and every result must be parseable for downstream reasoning.
$curl -o .claude/agents/review-agent-ux.md https://raw.githubusercontent.com/spinje/pflow/HEAD/.claude/agents/review-agent-ux.mdInstalls into the current project.
Install review-agent-ux by running `curl -o .claude/agents/review-agent-ux.md https://raw.githubusercontent.com/spinje/pflow/HEAD/.claude/agents/review-agent-ux.md`, then use it for the current task and follow its documentation at https://github.com/spinje/pflow.