From pmstack — PM Toolkit for the AI Era
Feature-by-feature comparison of two or more products with built-in eval design and runnable execution. Use when the PM wants to compare specific features across products (e.g., "compare GitHub Copilot vs Cursor", "how does our pricing stack up against X and Y", "evaluate these two AI coding tools head-to-head"). Use pmstack-competitive instead for market-positioning analysis (audience, value prop, white space).
How this skill is triggered — by the user, by Claude, or both
Slash command
/pmstack:pmstack-compareThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Produce a feature-by-feature comparison plan, eval design, and execution method, in three sequential phases with one explicit user confirmation gate.
Produce a feature-by-feature comparison plan, eval design, and execution method, in three sequential phases with one explicit user confirmation gate.
Goal: gather raw material so dimensions emerge from products, not from your priors.
Output: a brief raw-data summary. Do not write the comparison yet.
Goal: derive comparison dimensions from Phase 1, then propose a measurement plan.
/run-eval command for the user to run themselvesoutputs/compare-<products-slug>-<YYYY-MM-DD>-plan.md.Only after confirmation:
outputs/eval-compare-<products-slug>-<YYYY-MM-DD>.yaml./run-eval and write findings to outputs/compare-<products-slug>-<YYYY-MM-DD>-findings.md./run-eval command + env vars the user needs to set first.Analytical, direct. Lead with what's surprising. Hedge appropriately on facts you couldn't fully verify.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.
npx claudepluginhub ryanalberts/pmstack --plugin pmstack