PluginProject and product management
pmstack
Design, run, and monitor AI product evaluations from a PM workflow.
- Stars
- 5
- Forks
- 1
- Updated
- Updated Jul 7, 2026
MIT
Design, run, and monitor AI product evaluations from a PM workflow.
pmstack lets product managers build an evaluation lifecycle inside Claude without starting from an ML engineering dashboard. Its commands turn observed failures into task suites, graders, pass bars, and runnable YAML, then score a real target, review failed transcripts, and watch for regressions after model changes. PRDs, customer-signal synthesis, briefs, and launch checks are included, but the differentiator is making AI evals directly usable by PMs.
Resource types
Use cases
Platforms
Assess founder involvement, delegation, hiring, and operating cadence with structured diagnostics.
Preserve project context and progress across Claude Code sessions.
Runtime
Capabilities
Public GitHub facts last synced Jul 10, 2026.
Manage Claude Code projects with gated plans, resumable sessions, and shared state.
Evaluate product feasibility across technology, cost, compliance, operations, and schedule.