From Reasoning Protocols
Critique a plan, spec, or architecture decision before committing to implementation. Spawns an adversarial reviewer agent to surface invalid assumptions, missing edge cases, underspecified integrations, and over-engineering. Trigger phrases - "review this plan", "critique this spec", "challenge this design before I build it", "adversarial plan review", "stress-test this plan".
How this skill is triggered — by the user, by Claude, or both
Slash command
/reasoning-protocols:plan-reviewThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Adversarial critique of a plan, spec, or architecture decision before
Adversarial critique of a plan, spec, or architecture decision before implementation begins. Four phases: assumption inventory, adversarial review across six categories, severity assignment, and integration notes. Produces findings grouped by severity with concrete suggested resolutions.
This protocol runs as the plan-review agent. The agent follows the full
phase procedure autonomously, using the sequentialthinking MCP tool for
phases marked (Sequential-thinking required).
/reasonvalidation_tier: Fallbackartifact (required): Path to or content of the plan, spec, or architecture documentfocus_areas (optional): Specific areas or concerns to prioritize during reviewfindings: Array of {finding, category, severity, resolution}assumption_inventory: Assumptions with confidence ratings (High / Medium / Low)summary: critical_count, important_count, minor_count, validation_tier/reason for full composition guidance, pattern selection, and pipeline specifications.npx claudepluginhub zaynram/cowork-marketplace --plugin reasoning-protocolsProvides UI/UX resources: 50+ styles, color palettes, font pairings, guidelines, charts for web/mobile across React, Next.js, Vue, Svelte, Tailwind, React Native, Flutter. Aids planning, building, reviewing interfaces.
Fetches up-to-date documentation from Context7 for libraries and frameworks like React, Next.js, Prisma. Use for setup questions, API references, and code examples.