Multi-perspective adversarial analysis for any proposition. 3-5 agents (optimist, critic, pragmatist, + optional: alternative, pre-mortem) debate across rounds with cross-rebuttal and position tracking. Trigger: prism-debate, prism, /prism, 토론해줘, 검증해줘
Not in a marketplace yet, so it loads for one session with --plugin-dir.
Plugin prism-debate in JayKim88/claude-ai-engineering. Commands read from the repo's manifest — 1 month ago.
prism-debateMulti-perspective adversarial analysis. 3-5 agents view a proposition through different lenses — cross-rebutting across rounds with position tracking. Supports quick verdict, autonomous rounds, and user-participatory modes. Use when user says "prism-debate", "prism", "/prism", "토론해줘", "검증해줘", "반박해줘"
alternativeReframe the proposition and surface 2-3 genuinely different approaches outside the original binary framing
criticBuild the strongest possible case AGAINST a proposition — failure modes, risks, and counter-evidence
optimistBuild the strongest possible case FOR a proposition — steelmanning and best-case evidence
pragmatistGround a proposition in constraints, feasibility, and the key unknowns that must close before deciding
pre-mortemAssume the proposition was adopted and failed — work backward to identify the specific mechanisms of failure
synthesizerSynthesize a multi-agent debate (3-5 agents) into a final verdict with labeled evidence, counter-argument, preconditions, position evolution, and decision-log suggestion
25 senior-level frontend skills covering code quality, performance, design/UX, i18n, responsive design, testing, security, accessibility, operations, and architectural decisions. Each skill encodes a decision framework or audit procedure derived from production-grade references (Next.js, React, web.dev, OWASP, WCAG).
25 skills · 2 commands
22 senior-level backend skills covering API design, data modeling, reliability, async messaging, auth/authz, AI/LLM backends, observability, and architecture. Default stack: TypeScript + NestJS + PostgreSQL + Prisma + Redis + BullMQ + Supabase. Each skill is a framework-agnostic decision framework with stack-specific implementation notes, grounded in production references (Postgres docs, OWASP, microservices.io, Stripe, Anthropic).
22 skills · 2 commands
AI partner organization for solo entrepreneurs. 23 AI agents + You as CEO that plan, research, design, develop, market, and monetize your online service from idea to launch with sprint cycles
1 skill · 23 agents
현 시점에 무엇을 해야 할지 — 12명의 사상가 풀에서 상황에 맞는 5명이 자동 선택되어 분석합니다
1 skill · 14 agents
AI-powered career path analysis with 8-agent pipeline: resume analysis, market trends, skill gap assessment, and personalized roadmap
1 skill · 8 agents
Personalized wealth strategy system with 6 AI agents: financial diagnosis, market analysis, strategy generation, risk evaluation, and action roadmap (Korean)
2 skills · 1 command · 6 agents
Solve competition math (IMO, Putnam, USAMO) with adversarial verification that catches what self-verification misses. Fresh-context verifiers attack proofs with specific failure patterns. Calibrated abstention over bluffing.
1 skill
Multi-perspective code analysis covering architecture, security, and best practices
2 commands · 3 agents
32 engineering skills: architecture, frontend, backend, fullstack, QA, DevOps, security, AI/ML, data engineering, Playwright (9 sub-skills), self-improving agent, Stripe integration, TDD guide, tech stack evaluator, Google Workspace CLI, a11y audit (WCAG 2.2), Azure cloud architect, GCP cloud architect, security pen testing, Snowflake development, adversarial-reviewer, ai-security, cloud-security, incident-response, red-team, threat-detection. v2.8.1 audits senior-fullstack / senior-frontend / senior-backend against karpathy-coder + Matt Pocock — each ships a 7-question forcing-question library, 4 customization profiles (JSON), deterministic decision engine, composition map into POWERFUL specialists, plus cs-fullstack-engineer / cs-frontend-engineer / cs-backend-engineer orchestrator agents (context: fork) + /cs-fullstack-review, /cs-frontend-review, /cs-backend-review, /cs-engineer-grill slash commands.
35 skills · hooks
Comprehensive context engineering and harness engineering skills for production-grade AI agent systems: fundamentals, degradation patterns, compression, optimization, self-managed context (model-controlled live context editing), multi-agent coordination, long-horizon prompting (pseudo-formal task briefs for long-running and parallel agents), memory systems, tool design, filesystem context, hosted agents, evaluation, autonomous harnesses, self-improvement loops (RSI, meta-harnesses, evolutionary scaffold search), latent briefing (KV cache sharing between agents), project development, and cognitive architecture. Ships with a researcher operating system (rubrics, mechanism registry, claim provenance, run state machine, adversarial benchmarks, continuous loop).
19 skills
18 AI personas deliberate your hardest decisions — structured multi-round deliberation with genuine model diversity. One command: /council
2 skills · 18 agents
Discipline kit for coding agents: plan files with executable done-criteria, an automated develop-and-validate pipeline, adversarial code review with a security scan, and a completion gate that judges "done" by command output. 15 skills, 15 subagents and 5 Python hooks (session-start rule injection, sensitive-path guard, ruff/prettier auto-format, Stop-time lint and test run). No network calls, no MCP servers.
14 skills · 15 agents · hooks
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.