Plugins

Skills for scaffolding pages, components, API hooks, and reviewing code in the ModernStores Next.js/Turborepo project

from kerinin/claude-modes

The modular monolith applied pragmatically: one deployable unit, strictly bounded modules with public APIs, isolated data, and TypeScript-ecosystem boundary enforcement. Composable with your own conventions.

Manages module-level architecture documentation in the simplified arc42 LITE format with MDRs and Agents.md files.

Build complete Proteos modules interactively: discovery → entities + permissions → pages/lists/menus → live preview (pro module serve) → hooks/actions/components → deploy.

Spec-driven TDD framework: brainstorm -> provable completeness gate -> RED-before-GREEN -> review, with a codebase knowledge graph, self-healing memory, token governance, and human-gated writes. Local-first, Apache-2.0.

Apply Rob Fitzpatrick's 'The Mom Test' framework to customer discovery work.

Orientation and entry point for working on a Momen project. Load first for any Momen app task — designing or changing the data model, UI, server-side action flows, permissions, payments, or data bindings, or reading runtime logs — then follow it to the right capability. For Momen projects only; not generic programming help.

Set up a local Monata simulation environment with pixi, a local circuit-tool conda channel, and ngspice plus OpenVAF verification.

Run your monday CRM in plain language. Build a pipeline from scratch, start the day with a ranked deal briefing, spin up a forecast dashboard, audit board health, clean up messy data in bulk, and turn meeting notes into deal updates. Every skill writes back into monday as a real update, doc, or dashboard. Built on the official monday MCP connector.

Main entry point — onboards you, builds your profile, and routes to the right skill.

Google Ads, Meta Ads — campaign setup, optimization, ROAS tracking.

Content pipeline with authenticity audit, headline impact matrix, and substance scoring.

Deep diagnosis when business is stuck — root cause, not symptoms. Includes execution coaching.

Find and validate profitable business ideas with competitive intelligence.

Revenue tracking, unit economics, financial reports — Stripe integration.

Manage atomic project learnings (~/.smtm/projects/{slug}/learnings.jsonl). Auto-loaded into every other money-* skill so the agent gets smarter across sessions instead of cold-starting.

24/7 autonomous operations with health scoring, canary monitoring, and safety guardrails.

Cold email sequences, partnership outreach, and lead generation with personalization.

Run all four reviewers (investor / customer / operator / skeptic), find agreement, surface only disagreements + taste decisions. One command = full plan-review gauntlet.

Build, deploy, QA test, and monitor an MVP with landing page, auth, payments, SEO/GEO.

Code review, security audit, performance check, accessibility — pre-launch quality gates.

Merge all saved states into a deliverable markdown report — share with co-founders, advisors, or your future self.

Resume from a prior saved state — pick up exactly where the last session left off.

Weekly business retrospective. Reads snapshots, learnings, skill-usage telemetry. Surfaces stalled hypotheses, unused skills, and one recommended focus for the coming week. Portfolio mode aggregates across all projects.

Customer-mode review. First-person verdict from the named ICP on whether they'd pay this price for this solution. Verdict modes: PAY NOW / PAY WITH FRICTION / WRONG POSITIONING / WRONG ICP.

VC-mode review of a business plan. Verdict modes: SEED VIABLE / LATER ROUND ONLY / BOOTSTRAP-ONLY / UNFUNDABLE. Five questions: founder-market fit, demand evidence, moat theory, TAM math, founder risk.

Solo-founder execution review. Verdict modes: SHIPPABLE NOW / SHIPPABLE WITH DESCOPE / NEEDS HIRE / WRONG STACK. Checks build complexity, ops load, runway, channel feasibility.

Devil's advocate review. Seven attack vectors, top-3 risk ranking, and the single avoided question the user has been polite about. Verdict modes: EXISTENTIAL RISK / SOLVABLE RISKS / LOW-RISK / WRONG QUESTION.

Checkpoint the current business state to disk for cross-session recall — never lose context again.