By bpainter
Thirty technology and engineering specialists spanning architecture (composable, cloud, backend), engineering (frontend, mobile, design systems, DevOps, QA), AI/ML (AI engineering, agentic workflows), data (data engineering), security, technical writing, and content modeling — plus task-focused workflows for Next.js scaffolds, shadcn components, Tailwind tokens, accessibility audits, design implementation, component specs, and shadcn registry authoring — plus seven Next.js 16 deep dives (routing, server/client, cache + Suspense, server actions, errors/loading, performance/Web Vitals, config/security). One agent (software-engineering-agent) for general framework-level orchestration, with handoffs to vercel-agent and contentful-agent in adjacent plugins for platform-specific work. Four slash commands wire the Next.js skills into repeatable workflows: /nextjs-bootstrap, /nextjs-feature, /nextjs-upgrade, /nextjs-audit. Plugin-shared references include modern-javascript-essentials (ES2026, Temporal, iterator helpers, Set methods) and architecture-patterns-2026 (the ten patterns + MACH overlay).
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Audit an existing Next.js 16 codebase against May 2026 best practices — seven checks across routing, server/client, caching, server actions, errors/loading, performance, and config/security, with a prioritized fix plan
Bootstrap a new Next.js 16 project with our conventions — App Router, TS strict, Tailwind, shadcn, cacheComponents on, proxy.ts security headers, env validation, and the seven Next.js skills' defaults baked in from day one
Add a new Next.js 16 feature with the right cross-skill sequencing — route + server/client split + caching + actions + errors + perf, in the order that produces a coherent, well-shaped feature on first try
Migrate a Next.js 14 or 15 codebase to Next.js 16 — async params, middleware-to-proxy rename, cacheComponents adoption, deprecated API sweep, with codemods where they exist and manual review where they don't
Audit a screen, component, or flow for WCAG 2.2 AA conformance and remediate the findings — keyboard navigation, focus management, screen-reader semantics, contrast, motion, touch targets, error handling, and forms. Covers automated tooling (axe, Lighthouse, Storybook a11y addon) plus the manual passes that automation can't replace. Use this skill any time the user is auditing for accessibility, fixing a specific a11y finding, preparing for an external audit, or asking "is this accessible," even when "WCAG" or "a11y" isn't said. Trigger whenever accessibility is the question so the audit goes beyond the automated tools' false sense of completeness.
Design, build, and optimize intelligent multi-agent AI systems using production-ready frameworks like OpenAI Agents, LangGraph, and Claude's toolchain. Build autonomous workflows that orchestrate complex tasks through tool use, memory management, and agent coordination—not simple chatbots, but scalable enterprise automation.
Design, train, and deploy machine learning systems from research to production—transformers, LLMs, computer vision, forecasting, and beyond. Build end-to-end ML systems with strong data foundations, reproducible experiments, robust evaluation, and observable deployments at scale.
Design scalable, maintainable backend systems using modern architecture patterns—API-first design, microservices, event-driven systems, and cloud-native approaches. Build platforms that handle growth, enable teams, enforce security, and evolve gracefully without architectural rewrites.
Design scalable, secure, and cost-efficient cloud architectures across AWS, Azure, and GCP. Architect multi-region systems, migration strategies, and cloud-native patterns that balance performance, reliability, compliance, and cost—strategy-driven design, not component tinkering.
Uses power tools
Uses Bash, Write, or Edit tools
The Composable DXP plugin marketplace for Claude. 18 plugins, 182 skills, packaged for Claude Code (CLI), Claude Desktop (Cowork mode), and drag-and-drop install.
Marketplace name: composable-dxp (the value in .claude-plugin/marketplace.json)
Repo: https://github.com/bpainter/composable-dxp-claude-marketplace (public, personal)
# Cowork (Git URL — Cowork requires Git, not local paths)
claude plugin marketplace add https://github.com/bpainter/composable-dxp-claude-marketplace.git
claude plugin install <plugin>@composable-dxp
# Claude Code (also accepts the local path)
claude plugin marketplace add "/Users/bermon.painter/Library/CloudStorage/OneDrive-Slalom/Slalom Second Brain/80_Skills_and_Agents"
claude plugin install <plugin>@composable-dxp
For full install paths (Cowork, Claude Code, drag-and-drop), see INSTALL.md.
80_Skills_and_Agents/
├── README.md # this file (conventions and structure)
├── INSTALL.md # how to install the marketplace and plugins
├── .claude-plugin/
│ └── marketplace.json # marketplace manifest — lists every plugin
├── Memory/ # cross-cutting working memory (CLAUDE.md, people, glossary, etc.)
│ # NOT a plugin — read by Claude every session
├── Plugins/ # built .plugin files (build artifacts)
│ └── <plugin>.plugin
└── <plugin-name>/ # one folder per plugin SOURCE (e.g., obsidian/, claude/)
└── ... (see "Plugin layout" below)
The marketplace itself is a single Claude plugin marketplace. Tools that consume marketplaces (Claude Code CLI, Claude Desktop via Cowork) read .claude-plugin/marketplace.json to discover what's installable.
Memory/ is not a plugin. It's the user's working memory and shared knowledge base, read every session by Claude, and shared across all plugins.
Plugins/ holds built artifacts — the .plugin files (renamed ZIPs) that get dragged into Claude Desktop's Personal Plugins panel for install. The source of each plugin lives in its own folder at the marketplace root (e.g., obsidian/, claude/); the .plugin files in Plugins/ are derived from those sources via the build process described in INSTALL.md.
Every plugin under this marketplace follows this exact shape. Deviations break tooling.
<plugin-name>/ # plugin SOURCE (lives at marketplace root)
├── README.md # plugin overview for humans
├── .claude-plugin/
│ └── plugin.json # plugin manifest for Claude (only `name` is required)
├── references/ # plugin-wide shared references (optional)
│ └── <plugin>-foundations.md
├── skills/ # auto-discovered by Claude
│ ├── <plugin>-<skill-name>/ # one folder per skill
│ │ ├── SKILL.md # required — frontmatter (name, description) + body
│ │ └── references/ # skill-specific deep references (typical, 1–3 files)
│ │ └── <topic>.md
│ └── ... (more skills)
├── agents/ # auto-discovered by Claude (workers)
│ └── <plugin>-<agent-name>.md # single file per agent, Claude Code agent format
└── commands/ # slash commands (optional)
└── <command-name>.md
| Piece | Required? | Purpose |
|---|---|---|
README.md | recommended | Plugin overview, opinion, roadmap, written for humans browsing the repo |
.claude-plugin/plugin.json | required | Manifest Claude reads. Only name is strictly required; version, description, author, keywords, license are optional. Don't include empty optional fields (e.g., "homepage": "") — they fail manifest validation |
references/ | optional | Plugin-wide shared references at the plugin root. From a SKILL.md, cite as ../../references/<file>.md |
skills/ | optional | Skills (one folder per skill, each with a SKILL.md). Auto-discovered by Claude |
skills/<skill>/SKILL.md | required if folder exists | The skill itself — YAML frontmatter (name, description) + body |
skills/<skill>/references/ | optional | Skill-specific deep references (frameworks, checklists, examples). From the SKILL.md, cite as references/<file>.md |
agents/ | optional | Workers that act on user data — Claude Code agent file format (one file per agent) |
commands/ | optional | Slash commands — single Markdown files with description: frontmatter and a body that names the skill or workflow to invoke |
A plugin can have any combination of skills, agents, and commands. Empty folders are fine if you intend to fill them later.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimnpx claudepluginhub bpainter/composable-dxp-claude-marketplace --plugin software-engineeringClaude tooling skills for Cowork and Claude Code. Two skills: claude-plugin-creator scaffolds new plugins (folder structure, manifest, .plugin build, Cowork install) with empirically-established validation rules; claude-orchestrator designs the orchestration layer for new Cowork projects (CLAUDE.md routing, multi-phase commands, agent teams). One slash command (/plugin-help).
Seven behavioral-economics specialists grounded in canonical sources — Kahneman's Thinking Fast and Slow, Thaler & Sunstein's Nudge, Ariely's Predictably Irrational, and Wendel's Designing for Behavior Change — plus Slalom's 6-stage Behavioral Design Model. Six ready-to-use templates: Behavioral Profile, Choice Architecture, Nudges/Biases, Intervention Design, Use-Case Scoring, Use-Case Validation.
Eleven innovation specialists grounded in canonical sources — Christensen's Innovator's Dilemma, Dyer/Gregersen/Christensen's Innovator's DNA, Furr & Dyer's Innovator's Method, Doblin's Ten Types, Ramanujam & Tacke's Monetizing Innovation, Innovation Lab Excellence, Kelley's Ten Faces, Catmull's Creativity Inc, Dyer/Furr/Lefrandt's Innovation Capital, Rogers's Driving Digital Strategy, Tushman/Anand's Why Digital Transformations Fail, and Kane et al's Technology Fallacy — plus HBR Must-Reads on Innovation and Design a Better Business. Skills cover strategy, portfolio governance, value engineering across horizons, JTBD discovery, lean validation, ten-types diagnosis, willingness-to-pay monetization, lab design, disruption analysis, creative leadership/political capital, and digital transformation. One agent (innovation-agent) sequences them. Eight slash commands (audit, strategy, portfolio, discover, validate, value-case, charter, disruption-test) provide high-leverage recurring operations. Six templates: Three Horizons canvas, Ambition Matrix, JTBD Interview Guide, Ten Types diagnostic, Value Engineering canvas, Innovation Charter.
Leadership coaching, people-management, hiring, meetings and cadences, goal-setting, transitions, and stoic perspective. Seven specialized skills under one orchestrating agent. The two original skills (executive coach for neurodivergent leaders, people-leader for everyday craft) are joined by skills for hiring, meetings & cadences, onboarding & transitions, goals & OKRs, and stoic perspective. Each skill carries deep reference files distilled from canonical leadership texts — Hire With Your Head, The First 90 Days, Radical Focus, Drive, Good to Great, The Coaching Habit, Never Split the Difference, Meeting Design, The Effective Manager, Managing Humans, The Manager's Path, A Guide to the Good Life, How F*cked Up Is Your Management, Peopleware, Scaling Teams, Performance Appraisal Phrase Book, Exactly What to Say, How We Talk, Radical Candor, and 7 Habits.
Six brand specialists: strategy (positioning, narrative, voice, audience), naming (five-category framework, six-step process), identity-system (logo direction, color, type, photography, iconography), voice-tone (attributes with not-X pairings, tone register matrix, filler-words bans), guidelines-composer (9-chapter deliverable, sized to brand context), and audit (drift detection across identity, voice, surface application, governance). Outputs feed the design plugin and marketing plugin.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
Comprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns