8 plugins from public Claude Code marketplaces. Each one bundles skills, slash commands, agents, hooks or MCP servers that install together.
Daily-workflow skills for PMs: model routing, self-QA, prompt optimization, MCP context audit, project memory.
AI Evals for PMs: turn a product contract into a versioned four-surface suite covering outcomes, trajectories, end-to-end systems, and promised memory/state, with auditable PASS/FAIL/BLOCKED release evidence.
Scoped MCP 2026-07-28 migration review with cited rules, deployed-version context and explicit unknowns.
Recurring-workflow design with discovery, deduplication, verification, durable-state rules and scheduled prompt templates; enforcement belongs to the host runtime.
Agent-orchestration graph designer: qualifies loop versus graph, then produces bounded node, typed-edge, handoff, join, shared-state, recovery, budget, permission, verification, and human-approval contracts with synchronized visual, machine-readable, and runnable artifacts.
Voice-preserving product-writing editor: removes recognisable AI-writing patterns, protects facts and product judgment, and returns a clean draft with named edits.
Pre-build AI product decision contract: defines falsifiable assumptions, explicit kill thresholds, the cheapest decisive evidence plan, and a decision date before development starts.
Asks the 26 questions needed to build a model grader and nothing else: what the grader itself is, output shape, the eight integrity questions whose absence lets a model fake success, and the verdict rules. Tracks four gates per rule, exits on a buildability dry-run, and blocks freeze without a recorded trail.