claudecodex

claude-skills

20-category solo-SaaS-founder platform — autonomous engineering OS, 18+ agents, 117 doctrine rules, 20+ slash commands, production forge script, LLM eval harness, MCP registry, DO agent scaffolding, RAG pipeline, multi-tenant subdomain provisioning, full-document processing (DOCX/XLSX/PDF/PPTX), and 32 AI-tool platform variants. One-line prompts to deployed Cloudflare Workers products.

27 on GitHubby Brian Zalewskiv7.2.1Rutgersupdated 5 days ago

Not in a marketplace yet, so it loads for one session with --plugin-dir.

Plugin claude-skills in heymegabyte/agent-skills. Commands read from the repo's manifest — 5 days ago.

What it installs

Skills (25)

  • emdash-skills

    23-category product-building OS. CF Workers+Hono, React 19+Vite / Angular 22+Spartan, D1, Drizzle, Clerk, Square/Stripe. 149 reference docs, 28 agents.

  • operating-system

    Supreme policy layer governing all agent behavior. Autonomy, one-line prompt interpretation, speed standards, emphasis signal processing, cross-skill coordination, done definitions, conflict resolution. Loaded every prompt.

  • goal-and-brief

    Establish project thesis before first code. Infer product type from domain/folder/README. Identify users, business model, pSEO strategy, AI-native dev approach. Maintain PROJECT_BRIEF.md as source of truth.

  • preference-and-memory

    Captures and evolves user preferences with confidence levels. Maintains Voice of the Customer model with exact language, dissatisfaction and aspiration signals. Handles promotion/demotion, global vs project scoping, auto memory system, and Omi wearable data integration.

  • architecture-and-stack

    Cloudflare-first platform selection. Workers, D1, R2, KV, DO, Queues, Vectorize, Containers, Workflows, native Go CLIs and measured Rust/WASM acceleration. Default stack, override conditions, auth, data patterns and reliability.

  • build-and-slice-loop

    Use when implementing features or streaming OnePrompt site builds. Complete vertical slices with real content, strict TypeScript and Zod. Parallel section/data work, deterministic assembly, granular patches and immediate valid previews.

  • quality-and-verification

    5-level verification pyramid: static→unit→Playwright E2E (homepage-first, 6bp)→AI visual→post-deploy. 8-check quality gate. Multi-agent testing (functional/security/a11y/performance). Playwright v1.56+ AI agents (Planner/Generator/Healer, v1.63 current). WCAG 2.2 AA via axe-core v4.13. Percy+Chromat

  • deploy-and-runtime-verification

    MANDATORY deploy after every code change. Typecheck → deploy → purge CDN → E2E on production → visual verify → fix-forward loop. Workers Builds native CI/CD, D1 Time Travel PIT recovery, D1→R2 long-term backups, wrangler rollback, wrangler secrets management, structured observability, cross-browser

  • brand-and-content-system

    Extract real brands (Wayback for rebuilds). Copy system, headline/CTA rules, trust surfaces, legal pages, SEO+structured data, anti-AI-slop, microcopy, DESIGN.md, W3C DTCG tokens, pSEO 5 types, GEO/AI search.

  • experience-and-design-system

    Anti-AI-slop design system for distinctive, premium interfaces. Bold typography, dark-first #060610, fluid clamp() type, cascade layers + native nesting + container queries, OKLCH color, @starting-style, View Transitions API, DTCG tokens.

  • motion-and-interaction-system

    Meaning-first animation with 3-tier hierarchy. CSS scroll-driven (animation-timeline: scroll()), View Transitions API, @starting-style DOM-insert, container scroll-state queries, prefers-reduced-motion mandatory on all animations.

  • media-orchestration

    Section-by-section media planning and generation. Image generation (GPT Image 2 primary, built-in fallback), logo/icon generation (Ideogram v3 → favicon set), video generation (Veo 3.1), social preview images (OG 1200x630 + AI search optimization), stock photo curation (Pexels, Pixabay), critique/re

  • observability-and-growth

    Full instrumentation from day one. PostHog consolidates product analytics + feature flags + error tracking (one platform, one bill). GA4 via GTM (14-step automation, custom dimensions over events, server-side tagging). Sentry (deep error tracking + performance). Stripe (webhook-first with idempotent

  • independent-idea-engine

    Fierce autonomous internal co-founder. Bounded web research for evidence-backed improvements. Structured idea formulation with self-critique filter that rejects ideas not serving the goal. Auto-implements high-confidence aligned improvements, proposes medium-confidence ideas for approval. Evaluates

  • site-generation

    End-to-end AI website generation pipeline. Claude Opus 4.8 emits Bolt-style <boltArtifact> envelopes (multi-file, plan-first) that customize Vite+React+Tailwind templates from pre-researched business data. Pre-research via APIs, media acquisition, brand extraction, visual inspection via GPT Image 2

  • cinematic-website-prime-directive

    One-line-prompt → cinematic, gorgeous, functional, well-tested, deployed website. Pre-hydrated SPA + full PWA kit + JSON-LD rich snippets + third-party integrations. React 19+Vite default (Angular optional). 100 concrete improvements grouped into 10 categories that EVERY single-prompt site build mus

  • app-foundation

    Every delivered app — the non-inferable business requirements + exact stack/brand choices every build must satisfy. Loads on every app/site build.

  • visual-experience

    Gorgeous/cinematic requirements every delivered app's UI must meet — anti-slop premium bar, exact brand tokens, motion, logo/image quality, WCAG 2.2 visual accessibility.

  • content-seo

    Copy + discoverability requirements every delivered app must meet — real-brand extraction, anti-slop voice, per-page SEO/JSON-LD, pSEO, GEO/AI-search, truth/citations, competitor floor, i18n, trust surfaces.

  • functional

    What every delivered app must DO — anti-placeholder, complete features, working forms, psnotify notifications, feature flags, embarrassingly-easy UX, the feature catalog.

  • quality-performance

    Speed, accessibility, and testing bars every delivered app must clear — Core Web Vitals, WCAG 2.2 AA, TDD real-browser E2E, and the build-fail gates.

  • platform-delivery

    How every delivered app ships and stays up — Cloudflare-first hosting, prod-only (no staging), the deploy→prod-verify loop, atomic deploy + rollback.

  • trust-compliance

    Legal, security, privacy, and deliverability requirements every delivered app must satisfy — legal pages, PII/deletion rights, CSP/Trusted-Types/Zod, AI-agent security, RFC7807 errors, email domain auth.

  • cf-integrations-reference

    The consolidated, world-class Cloudflare + integrations reference — CF platform/data/AI-edge patterns, media pipeline, observability/growth, payments, and the site-generation pipeline. The non-inferable choices that build the greatest web apps.

  • openclaw-integration

Slash commands (36)

  • /claude-skills:agent-diversity-review

    Run the Agent Diversity Review gate and emit the result table

  • /claude-skills:bootstrap-status

    Report the Claude control-plane environment (auth mode, tooling, connectors, resolved target). Fires when you need to confirm the sandbox can deploy.

  • /claude-skills:claude-bootstrap

    Bring ANY repo into compliance with the shared Claude control plane so Claude Code on the web can run /ship autonomously.

  • /claude-skills:cloudflare-bootstrap

    Reconcile the Cloudflare agent fabric: official skills, API MCP, MCP Portal candidates, AI Search, Secrets Store, Dynamic Routes, Browser Run and telemetry.

  • /claude-skills:create-specialist-agent
  • /claude-skills:customer-changelog-check
  • /claude-skills:dashboard-cockpit
  • /claude-skills:deploy
  • /claude-skills:drift-check
  • /claude-skills:fast-fix
  • /claude-skills:final-review
  • /claude-skills:improve-lint
  • /claude-skills:install-lint-stack
  • /claude-skills:list-arcs
  • /claude-skills:multimedia-enrich
  • /claude-skills:plan-execute-verify-repair
  • /claude-skills:post-arc-retrospective
  • /claude-skills:prepare-multi-file-brief
  • /claude-skills:prepare-skeleton-brief
  • /claude-skills:process
  • /claude-skills:retro
  • /claude-skills:review-global-prompts
  • /claude-skills:rollback
  • /claude-skills:run-evals
  • /claude-skills:run-the-loop
  • /claude-skills:saas
  • /claude-skills:security-supply-chain
  • /claude-skills:self-improve
  • /claude-skills:session-recap
  • /claude-skills:ship
  • /claude-skills:skill-health
  • /claude-skills:skip-questions
  • /claude-skills:sync-claude
  • /claude-skills:update-agentskills
  • /claude-skills:vendor-rotation-calendar
  • /claude-skills:verify-production

Subagents (52)

  • a11y-auditor

    Universal access sentry and all-weather accessibility auditor. Guarantees WCAG 2.2 AAA compliance, flawless screen reader traversal, robust keyboard navigation, and total inclusivity.

  • accessibility-auditor

    Dedicated axe-core + Playwright accessibility agent. Navigates pages, runs WCAG 2.2 AA audits at 6 breakpoints, reports violations with fix suggestions, verifies remediation.

  • appsec

    Counter-intelligence and perimeter defense sentry. Enforces zero-trust boundaries, conducts continuous SAST/DAST scans, models attack surfaces, and neutralizes security threats.

  • architect

    Principal battle planner and systems architect. Enforces modularity, authors repo-maps, locks API contracts, and audits system boundaries.

  • backend-engineer

    Core systems and artillery officer. Engineers resilient backend APIs, distributed worker queues, Redis caching, microservices, and transaction boundaries.

  • browser-operator

    Browser reconnaissance and visual QA specialist. Drives real browsers via Stagehand, Playwright CDP, and cua-driver to execute live golden-path user flows, audit console/network telemetry, and certify 6-breakpoint visual fidelity.

  • ceo

    Supreme Commander and fleet orchestrator. Directs high-level strategy, multi-agent dispatch, cross-functional roadmaps, and budget oversight under Auftragstaktik.

  • changelog-drafter

    Reads git log since last tag, drafts CHANGELOG entry. Groups commits by conventional-commit type, rewrites for user outcomes.

  • changelog-generator

    Auto-generates changelogs from conventional commits. Parses git log since last tag, groups by type, writes user-outcome-focused CHANGELOG.md entries.

  • code-simplifier

    Simplifies code for clarity, consistency, and maintainability. Reduces complexity, flattens nesting, removes dead code, consolidates duplicates. Focuses on recently modified files.

  • completeness-checker

    Post-implementation verification agent. Runs Feature Completeness Engine, Zero Recommendations Gate, and visual verification. Only declares DONE when genuinely complete.

  • computer-use-operator

    Autonomous drone operator and robotic CUA sentry. Operates native desktop GUI applications (macOS, Windows, Linux) via cua-driver, captures accessibility trees, clicks coordinates, and verifies state.

  • content-writer

    Editorial and narrative warfare specialist. Authors high-converting landing page copy, technical blog posts, launch announcements, case studies, and GEO-optimized brand narratives.

  • cost-estimator

    Estimates Cloudflare Workers costs before deploying. Reads wrangler.toml, counts D1 tables/rows, estimates KV/R2 usage, calculates monthly cost, warns on free tier limits.

  • database-engineer

    Storage integrity and ordnance custodian. Protects database health, crafts forward-only zero-downtime migrations, indexes hot paths, and verifies disaster recovery.

  • dead-code-remover

    Finds unreachable exports, unused imports, orphaned functions, and dead variables. Greps project to confirm no references, then removes safely.

  • dependency-auditor

    Scans packages for outdated deps, security advisories, license violations, and unused imports. Proposes version bumps, runs tests after updates, generates prioritized upgrade report.

  • deploy-verifier

    Post-deploy smoke test agent. Verifies live URL, checks console errors, screenshots 6 breakpoints, runs axe-core, validates SEO tags, reports pass/fail with evidence.

  • devsecops

    Combat logistics and trench engineer. Provisions Cloudflare-native infrastructure, crafts hardened CI/CD pipelines, automates secret rotation, and guarantees zero-downtime shipping.

  • finops

    Resource rationing and quartermaster. Governs token economics, eliminates cloud waste, optimizes multi-model routing spend, and enforces budget accountability.

  • formatter

    Runs prettier + oxlint --fix on modified files. Ensures consistent formatting and lint compliance with zero human intervention.

  • full-stack-engineer
  • fullstack-engineer

    Forward combat engineer. Executes vertical feature slices end-to-end with flawless type safety, responsive UI, resilient API routes, and zero lint errors.

  • growth-strategist

    Psychological operations and territory expansion strategist. Drives organic traffic, engineers viral distribution loops, optimizes conversion funnels, and maps attribution telemetry.

  • hr-director
  • hr

    Head of People and Agent Operations (Fleet Personnel Governor). Governs agent fleet hierarchy, healthchecks, permissions, budgets, adapter configs, and skill assignments across Paperclip and OpenClaw.

  • incident-responder

    Sentry-triggered incident response agent. Reads error events, traces to source code, proposes fixes, creates branches, and opens PRs with the fix.

  • information-architect

    Topology reconnaissance and signal cartographer. Designs intuitive navigation hierarchies, canonical URL topologies, structured JSON-LD schemas, and comprehensive sitemaps.

  • media-orchestrator

    Combat camera and visual broadcast unit. Renders cinematic video with HyperFrames, produces motion graphics, generates voiceovers, masters audio, and delivers high-fidelity media assets.

  • meta-orchestrator
  • migration-agent

    Drizzle schema migration agent. Generates migrations from schema diffs, validates against D1/SQLite, tests rollbacks, ensures zero-downtime compatibility.

  • model-router

    Signal corps communications officer. Governs dynamic PACE model routing (Primary, Alternate, Contingency, Emergency), optimizes token velocity, balances provider quotas, and guarantees zero failovers.

  • motion-choreographer

    CSS animation and motion designer. Implements View Transitions API, scroll-driven animations, CSS keyframes, FLIP, staggered reveals, and reduced-motion respected animations.

  • performance-engineer

    Velocity benchmark and supersonic aerodynamics specialist. Drives time-to-first-render (TTFR) to sub-100ms, achieves 100/100 Lighthouse scores, and eliminates latency bottlenecks.

  • performance-profiler

    Runs Lighthouse audits, analyzes Core Web Vitals, suggests specific fixes with file:line references. Targets the house cinematic bar (LCP<=2.0s, CLS<=0.05, INP<=100ms per _kernel/standards.md#cwv); classifies against Google good/NI/poor bands.

  • product-manager

    Mission intent and tactical reconnaissance officer. Translates strategic briefs into crisp PRDs, user stories, acceptance criteria, and prioritized feature backlogs.

  • qa-verification

    Inspector general and ballistics specialist. Enforces zero-defect quality gates with automated Playwright, Vitest, contract verification, and visual regression suites.

  • refactorer

    Tech debt purge and mine clearance unit. Sweeps repositories to exterminate dead code, dismantle anti-patterns, restore modularity, and streamline codebases without altering behavior.

  • release-manager

    Deployment gate arbiter and air traffic controller. Orchestrates production releases, enforces SemVer, coordinates canary promotions, and maintains deployment safety.

  • renamer

    Semantic rename across codebase. Greps all references, updates imports and usages, renames file or symbol. Safe rename with verification.

  • resource-broker

    Maintains a normalized registry of legitimately-owned account resources (credits, quotas, free tiers, promos, expiring entitlements) with secret-REFERENCES only, and routes work cost-aware. Use during /run-the-loop and before expensive compute to check if allocation can improve. Never stores real se

  • security-reviewer

    OWASP Top 10 security auditor. Reviews for injection flaws, secrets exposure, auth bypasses, CSP issues, and vulnerable dependencies. Read-only — never modifies code.

  • seo-auditor

    Audits pages for technical SEO, Generative Engine Optimization (GEO), Schema.org JSON-LD correctness, Core Web Vitals, OpenGraph metadata, llms.txt compliance, and crawlability across the fleet.

  • sre

    Rapid incident response unit and SRE sentry. Enforces 99.99% availability, executes automated rollbacks, monitors real-time SLOs, and drives post-mortem root-cause analysis.

  • summarizer

    Intelligence debriefing officer and black box recorder. Distills high-density transcripts into crisp military debriefs, synthesizes After Action Reviews (AAR), and manages fleet memory compression.

  • support-dispatcher

    Battlefield medic and support triage dispatcher. Triages user-reported bugs, reproduces failure scenarios with minimal reproductions, categorizes severity, and routes to specialist squads.

  • swarm-dispatcher

    Parallel swarm coordinator and worktree wave dispatcher. Decomposes multi-repository backlogs into conflict-free worktree waves, dispatches parallel agent batches, and enforces merge-gate convergence.

  • technical-writer

    Combat field manuals and doctrine archivist. Authors authoritative, self-documenting technical documentation, OpenAPI specs, architecture guides, living READMEs, and SDK reference manuals.

  • test-writer
  • transcriber

    Transcribes a plan step into code, one file at a time. Reads the spec, generates the implementation, writes clean production code with no oversight.

  • ui-designer

    Visual experience vanguard and design system sentry. Crafts breathtaking, accessible interfaces adhering to the 16-state component matrix, 0.333s motion physics, and supreme aesthetic polish.

  • visual-qa

    Visual quality assurance agent. Screenshots pages at all breakpoints, uses AI vision to detect layout breaks, misalignment, text overflow, broken images, and design inconsistencies.

MCP servers (1)

  • cloudflare-api

    connects to: https://mcp.cloudflare.com/mcp

View source on GitHub agent.megabyte.space

Problems found in this repo's manifests

  • .claude-plugin/marketplace.json has no "plugins" array

Similar plugins

Professional UI/UX design intelligence for AI coding assistants. Includes searchable databases of styles, colors, typography, charts, and UX guidelines for React, Next.js, Astro, Vue, Nuxt.js, Nuxt UI, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, Jetpack Compose, Angular, Laravel, JavaFX, and Three.js.

7 skills

nextlevelbuilder/ui-ux-pro-max-skill 148,759

Autonomous /loop-driven task completion with learning, prediction, and progress tracking

2 skills · 2 commands · 1 agent

ruvnet/ruflo 81,589

firecrawl

claude

Web scraping and crawling powered by Firecrawl. Turn any website into clean, LLM-ready markdown or structured data. Scrape single pages, crawl entire sites, search the web, and extract structured information. Includes an AI agent for autonomous multi-source data gathering - just describe what you need and it finds, navigates, and extracts automatically.

3 skills · 1 MCP server

anthropics/claude-plugins-official 47,076

Autonomous experiment loop — optimize any file by a measurable metric. 5 slash commands (/autoresearch-agent:setup, /ar-run, /ar-loop, /ar-status, /ar-resume), 8 built-in evaluators, configurable loop intervals (10min to monthly).

6 skills · 1 agent · hooks

alirezarezvani/claude-skills 29,725

Persistent project planning files with lifecycle hooks that inject selected plan context. Automatic recovery uses project files only. Explicit catchup modes may read same-project local session records to emit aggregate counts or bounded nonce-framed excerpts. Optional gated mode can request continuation on capable hosts and never runs commands declared in Markdown. No network upload path. Installs across 60+ agents.

6 skills · 13 commands · hooks

OthmanAdi/planning-with-files 28,031

Language-specific expert agents with deep framework knowledge - Python, TypeScript, Go, Rust, Java, and more

VoltAgent/awesome-claude-code-subagents 26,513

Maintain claude-skills?

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.

claude & codex pluginslisted