{"id":49609384,"url":"https://github.com/heymegabyte/claude-skills","last_synced_at":"2026-06-26T20:31:01.921Z","repository":{"id":352735733,"uuid":"1216267923","full_name":"heymegabyte/claude-skills","owner":"heymegabyte","description":"14-category autonomous product-building OS for 32+ AI coding tools. One-line prompts → deployed products.","archived":false,"fork":false,"pushed_at":"2026-06-24T23:10:12.000Z","size":7593,"stargazers_count":12,"open_issues_count":1,"forks_count":2,"subscribers_count":0,"default_branch":"master","last_synced_at":"2026-06-25T00:09:34.680Z","etag":null,"topics":["agent-skills","agents-md","agentskills","ai-agents","ai-coding","ai-rules","ai-skills","claude-code","claude-skills","cloudflare-workers","codex-skills","copilot-instructions","cursor-rules","developer-tools","gh-skill","hono","mcp","product-building","saas","vibe-coding"],"latest_commit_sha":null,"homepage":"https://claude.megabyte.space","language":"TypeScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/heymegabyte.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":"SECURITY.md","support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":"AGENTS.md","dco":null,"cla":null}},"created_at":"2026-04-20T18:30:10.000Z","updated_at":"2026-06-24T23:10:15.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/heymegabyte/claude-skills","commit_stats":null,"previous_names":["megabytespace/claude-skills","heymegabyte/claude-skills"],"tags_count":3,"template":false,"template_full_name":null,"purl":"pkg:github/heymegabyte/claude-skills","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/heymegabyte%2Fclaude-skills","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/heymegabyte%2Fclaude-skills/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/heymegabyte%2Fclaude-skills/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/heymegabyte%2Fclaude-skills/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/heymegabyte","download_url":"https://codeload.github.com/heymegabyte/claude-skills/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/heymegabyte%2Fclaude-skills/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":34832916,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-06-26T02:00:06.560Z","response_time":106,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["agent-skills","agents-md","agentskills","ai-agents","ai-coding","ai-rules","ai-skills","claude-code","claude-skills","cloudflare-workers","codex-skills","copilot-instructions","cursor-rules","developer-tools","gh-skill","hono","mcp","product-building","saas","vibe-coding"],"created_at":"2026-05-04T16:00:47.222Z","updated_at":"2026-06-26T20:31:01.914Z","avatar_url":"https://github.com/heymegabyte.png","language":"TypeScript","funding_links":[],"categories":["Frameworks","Skills","Source Catalog"],"sub_categories":["Development \u0026 Code Tools"],"readme":"\u003cdiv align=\"center\"\u003e\n  \u003ca href=\"https://github.com/heymegabyte/claude-skills\"\u003e\n    \u003cimg width=\"148\" alt=\"Emdash Skills\" src=\"https://raw.githubusercontent.com/heymegabyte/claude-skills/master/logo.png\" /\u003e\n  \u003c/a\u003e\n  \u003ch1\u003eEmdash Skills\u003c/h1\u003e\n  \u003cp\u003e\u003cstrong\u003eComplete solo-SaaS-founder platform for 32+ AI coding tools.\u003cbr/\u003eOne-line prompts → deployed products on Cloudflare Workers.\u003c/strong\u003e\u003c/p\u003e\n\u003c/div\u003e\n\n\u003cdiv align=\"center\"\u003e\n  \u003ca href=\"https://github.com/heymegabyte/claude-skills\"\u003e\u003cimg alt=\"GitHub Stars\" src=\"https://img.shields.io/github/stars/heymegabyte/claude-skills?logo=github\u0026logoColor=white\u0026style=for-the-badge\u0026color=060610\" /\u003e\u003c/a\u003e\n  \u003ca href=\"https://megabyte.space\"\u003e\u003cimg alt=\"Homepage\" src=\"https://img.shields.io/website?down_color=%23FF4136\u0026down_message=Down\u0026label=Homepage\u0026logo=home-assistant\u0026logoColor=white\u0026up_color=%232ECC40\u0026up_message=Up\u0026url=https%3A%2F%2Fmegabyte.space\u0026style=for-the-badge\" /\u003e\u003c/a\u003e\n  \u003ca href=\"https://github.com/heymegabyte/claude-skills/blob/master/LICENSE\"\u003e\u003cimg alt=\"License: Rutgers\" src=\"https://img.shields.io/badge/License-Rutgers-7C3AED?logo=open-source-initiative\u0026logoColor=white\u0026style=for-the-badge\" /\u003e\u003c/a\u003e\n  \u003ca href=\"https://github.com/heymegabyte/claude-skills/issues\"\u003e\u003cimg alt=\"Issues\" src=\"https://img.shields.io/github/issues/heymegabyte/claude-skills?logo=github\u0026logoColor=white\u0026style=for-the-badge\u0026color=00E5FF\" /\u003e\u003c/a\u003e\n  \u003ca href=\"https://www.npmjs.com/package/@heymegabyte/claude-skills\"\u003e\u003cimg alt=\"npm\" src=\"https://img.shields.io/npm/v/@heymegabyte/claude-skills?logo=npm\u0026logoColor=white\u0026style=for-the-badge\u0026color=50AAE3\" /\u003e\u003c/a\u003e\n  \u003ca href=\"https://jsr.io/@heymegabyte/claude-skills\"\u003e\u003cimg alt=\"JSR\" src=\"https://img.shields.io/jsr/v/@heymegabyte/claude-skills?logo=jsr\u0026logoColor=white\u0026style=for-the-badge\u0026color=7C3AED\" /\u003e\u003c/a\u003e\n\u003c/div\u003e\n\n\u003cbr/\u003e\n\n\u003cdiv align=\"center\"\u003e\n  \u003ccode\u003e19 categories\u003c/code\u003e · \u003ccode\u003e117 doctrine rules\u003c/code\u003e · \u003ccode\u003e20 agents\u003c/code\u003e · \u003ccode\u003e20+ slash commands\u003c/code\u003e · \u003ccode\u003e32 platform variants\u003c/code\u003e\u003cbr/\u003e\n  \u003ca href=\"https://claude.megabyte.space\"\u003e\u003cstrong\u003eShowcase Website\u003c/strong\u003e\u003c/a\u003e\n\u003c/div\u003e\n\n## What's New\n\n**Skills 17–19 + integration arc (2026-06)**\n\n- **Skill 17 — Non-Engineering Verticals** — C-suite personas, finance domain, compliance OS, PM domain. One OS, every function.\n- **Skill 18 — Document Processing** — DOCX/XLSX read-write, PDF generation + parsing, PPTX generation. Full pipeline, no manual exports.\n- **Skill 19 — MCP Authoring** — forge HTTP MCP servers on Workers, stdio MCP templates, OpenAPI→MCP forger. Publish to the registry in one command.\n- **20+ slash commands** — `/saas`, `/forge-from-openapi`, `/forge-webhook-handler`, `/generate-prp`, `/execute-prp`, `/run-evals`, `/audit-doctrine`, `/audit-mcp-fleet`, `/dashboard-cockpit`, `/drift-check`, and more.\n- **Production forge script** — `bin/forge-skill-from-openapi.mjs` generates a full SKILL.md + command scaffold from any OpenAPI spec.\n- **LLM eval harness** — `/run-evals` + structured rubrics + schema-validated results + regression tracking. AI-heavy behavior now has a repeatable quality gate.\n- **15 new doctrinal principles** — `state-is-the-enemy`, `fail-fast-build-fail-soft-prod`, `ttfr-north-star`, `sync-ui-async-backing`, `cost-per-request-accountability`, `inverted-abstraction-pyramid`, `one-way-two-way-doors`, `vendor-risk-tiering`, `data-residency-by-default`, `right-to-deletion`, `refund-automation`, `documentation-as-code`, `production-observability-default-on`, `hardware-aware-programming`, `webhook-receiver-architecture`.\n- **DO agent scaffolding** — Durable Objects as stateful AI agents via skill 19, wired to the MCP registry.\n- **RAG pipeline** — vectorize + D1 hybrid search documented in skill 05 architecture submodules.\n- **Multi-tenant subdomain provisioning** — Cloudflare custom hostnames + per-tenant D1 namespacing, baked into skill 05.\n- **5 new PreToolUse hooks** — permission-discipline enforcement before destructive tool calls.\n- **MCP server registry** — `/audit-mcp-fleet` catalogs, health-checks, and version-pins every MCP in your harness.\n\n\u003cbr/\u003e\n\n### When to Use\n\n| Building... | Skills Load | Install |\n|---|---|---|\n| **SaaS product** | 01-OS → 02-Brief → 05-Arch → 06-Build → 07-QA → 08-Deploy + all agents | `claude plugin install heymegabyte/claude-skills` |\n| **API / backend** | 01-OS → 05-Arch → 06-Build → 08-Deploy → 13-Observability | `npm i @heymegabyte/claude-skills` |\n| **Marketing site** | 01-OS → 09-Brand → 10-Design → 11-Motion → 12-Media | `npm i @heymegabyte/claude-skills` |\n| **Features on existing project** | 01-OS → 06-Build → 07-QA (skill router auto-selects from context) | `claude plugin install heymegabyte/claude-skills` |\n| **Just rules for your AI tool** | No skills — use a platform variant file directly | See [32 variants](#cross-platform-support-32-variants) below |\n\n## How It Works\n\n```\n┌─────────────────────────────────────────────────────────────────┐\n│                        YOUR PROMPT                              │\n│              \"Build a SaaS for dog walkers\"                     │\n└───────────────────────────┬─────────────────────────────────────┘\n                            │\n                            ▼\n┌─────────────────────────────────────────────────────────────────┐\n│                     SKILL ROUTER                                │\n│  Matches prompt → loads smallest useful subset of skills        │\n│  01-OS always loaded │ then 02-Brief → 05-Arch → 06-Build      │\n└───────────────────────────┬─────────────────────────────────────┘\n                            │\n              ┌─────────────┼─────────────┐\n              ▼             ▼             ▼\n        ┌──────────┐  ┌──────────┐  ┌──────────┐\n        │ ARCHITECT│  │ PARALLEL │  │ PARALLEL │\n        │  (Opus)  │  │  BUILD   │  │  VERIFY  │\n        │          │  │ 3-5 agents│  │ 3 agents │\n        │ repo-map │  │ frontend │  │ deploy   │\n        │ task graph│  │ backend  │  │ seo      │\n        │ seams    │  │ content  │  │ visual   │\n        └──────────┘  │ media    │  │ a11y     │\n                      │ tests    │  └──────────┘\n                      └──────────┘\n                            │\n                            ▼\n┌─────────────────────────────────────────────────────────────────┐\n│                      HARD GATES                                 │\n│  Playwright 6bp ✓ │ Vision ≥8/10 ✓ │ Lighthouse A11y ≥95 ✓     │\n│  axe-core 0 ✓ │ SEO GREEN ✓ │ 0 errors ✓ │ Flesch ≥60 ✓       │\n└───────────────────────────┬─────────────────────────────────────┘\n                            │\n                            ▼\n                    ┌──────────────┐\n                    │   DEPLOYED   │\n                    │ CF Workers   │\n                    │   + purged   │\n                    └──────────────┘\n```\n\n## Install\n\n```bash\n# GitHub Skills (recommended)\ngh skill install heymegabyte/claude-skills\n\n# Claude Code plugin\nclaude plugin install heymegabyte/claude-skills\n\n# npm (includes all 32+ platform variants)\nnpm i @heymegabyte/claude-skills\n\n# JSR\nnpx jsr add @heymegabyte/claude-skills\n\n# OpenAI Codex\ngit clone https://github.com/heymegabyte/claude-skills ~/.codex/skills\n\n# Manual\ngit clone https://github.com/heymegabyte/claude-skills ~/.agentskills\n```\n\n## Cross-Platform Support (32 variants)\n\nAuto-generated on every push to master. Each format uses native frontmatter for its tool.\n\n| Format | Path | Notes |\n|--------|------|-------|\n| **Cursor** (modern) | `.cursor/rules/emdash-skills.mdc` | MDC frontmatter: `alwaysApply: true` |\n| **Windsurf** (modern) | `.windsurf/rules/emdash-skills.md` | `trigger: always_on` |\n| **Augment** (modern) | `.augment/rules/emdash-skills.md` | `type: always_apply` |\n| **Copilot** (modern) | `.github/instructions/emdash-skills.instructions.md` | `applyTo: \"**\"` |\n| **OpenHands** | `.openhands/microagents/repo.md` | Plain markdown |\n| **Cursor** (legacy) | `.cursorrules` | Single-file format |\n| **Windsurf** (legacy) | `.windsurfrules` | Single-file format |\n| **Cline** | `.clinerules` | Single-file format |\n| **Copilot** (legacy) | `.github/copilot-instructions.md` | Plain markdown |\n| **Augment** (legacy) | `.augment-guidelines` | Single-file format |\n| **Aider** | `.aider-conventions.md` | Plain markdown |\n| **Zed** | `.rules` | Plain markdown |\n| **Codex** | `CODEX.md` + `.agents/skills/` | SKILL.md per category |\n| **Gemini CLI** | `GEMINI.md` | Plain markdown |\n| **Amp** | `AMP.md` | Plain markdown |\n| **Replit** | `replit.md` | Plain markdown |\n| **Devin** | `.devin/skills/emdash/SKILL.md` | SKILL.md with frontmatter |\n| **Goose** | `.goose/recipes/emdash-skills.yaml` | YAML recipe format |\n| **AGENTS.md** | `AGENTS.md` | Devin, Jules, Copilot, OpenHands |\n| **Amazon Q** | `.amazonq/rules/` | Directory format |\n| **JetBrains Junie** | `.junie/guidelines.md` | Plain markdown |\n| **Trae** | `.trae/rules/project_rules.md` | ByteDance IDE |\n| **Tabnine** | `.tabnine/guidelines/guidelines.md` | Directory format |\n| **Kilo Code** | `.kilo/rules/` | Roo Code successor |\n| **Roo Code** | `.roo/rules/` | Active until May 2026 |\n| **Continue.dev** | `.continue/rules/` | Directory format |\n| **JetBrains AI** | `.aiassistant/rules/emdash-skills.md` | Separate from Junie |\n| **Kiro** (AWS) | `.kiro/steering/emdash-skills.md` | Workspace steering |\n| **Void** | `.void/rules/emdash-skills.md` | Open-source VS Code fork |\n| **Qodo** | `QODO.MD` | PR-Agent auto-detects |\n| **Bolt.new** | `.bolt/promptfile` | Plain text instructions |\n| **Cursor BugBot** | `.cursor/BUGBOT.md` | Per-directory code review |\n\n## Skill Categories\n\n```\n          ┌──────────────────────────────────────────────┐\n          │              EMDASH SKILL MAP                 │\n          │                                               │\n          │   ┌─────┐  ┌─────┐  ┌─────┐  ┌─────┐       │\n          │   │ 01  │→ │ 02  │→ │ 03  │→ │ 04  │       │\n          │   │ OS  │  │Brief│  │Plan │  │Pref │       │\n          │   │  6  │  │  0  │  │  1  │  │  3  │       │\n          │   └─────┘  └─────┘  └─────┘  └─────┘       │\n          │                                               │\n          │   ┌─────┐  ┌─────┐  ┌─────┐  ┌─────┐       │\n          │   │ 05  │→ │ 06  │→ │ 07  │→ │ 08  │       │\n          │   │Arch │  │Build│  │ QA  │  │Ship │       │\n          │   │ 12  │  │ 26  │  │ 25  │  │ 10  │       │\n          │   └─────┘  └─────┘  └─────┘  └─────┘       │\n          │                                               │\n          │   ┌─────┐  ┌─────┐  ┌─────┐  ┌─────┐       │\n          │   │ 09  │→ │ 10  │→ │ 11  │→ │ 12  │       │\n          │   │Brand│  │ UX  │  │Motn │  │Media│       │\n          │   │  7  │  │  2  │  │  1  │  │ 10  │       │\n          │   └─────┘  └─────┘  └─────┘  └─────┘       │\n          │                                               │\n          │   ┌─────┐  ┌─────┐  ┌─────┐                  │\n          │   │ 13  │→ │ 14  │→ │ 15  │                  │\n          │   │Grow │  │Ideas│  │ Gen │                  │\n          │   │  7  │  │  0  │  │  9  │                  │\n          │   └─────┘  └─────┘  └─────┘                  │\n          │                                               │\n          │   Numbers = reference docs per category       │\n          └──────────────────────────────────────────────┘\n```\n\n| # | Category | Docs | What It Handles |\n|--:|----------|:----:|-----------------|\n| 01 | **Operating System** | 6 | Core policy, autonomy, parallelization, AI-native coding, output compression |\n| 02 | **Goal \u0026 Brief** | — | Product thesis from a domain name, business model inference |\n| 03 | **Planning \u0026 Research** | 1 | Competitive analysis, task decomposition, parallel workstreams |\n| 04 | **Preference \u0026 Memory** | 3 | Voice of Customer data, user preferences, behavioral psychology |\n| 05 | **Architecture \u0026 Stack** | 12 | CF Workers, Hono, Drizzle v1, Coolify, MCP, auth, API design, multi-tenancy |\n| 06 | **Build \u0026 Slice Loop** | 26 | Forms, search, blog, i18n, PWA, webhooks, admin, data tables, chat |\n| 07 | **Quality \u0026 Verification** | 25 | E2E, a11y, security hardening, perf, visual QA, adversarial, AI testing |\n| 08 | **Deploy \u0026 Runtime** | 10 | CI/CD, launch-day sequence, uptime, backup, changelog, GitHub CI fix |\n| 09 | **Brand \u0026 Content** | 7 | SEO engine, copy system, email templates, social automation |\n| 10 | **Design System** | 2 | Anti-slop design, dark-first, bold typography, CSS architecture |\n| 11 | **Motion \u0026 Interaction** | 1 | Scroll-driven animations, View Transitions, reduced-motion |\n| 12 | **Media Orchestration** | 10 | Image/video generation, AI prompts, compression, OG previews, diagramming |\n| 13 | **Growth \u0026 Observability** | 7 | Stripe billing, analytics, Sentry alerts, email, experiments, CRO |\n| 14 | **Idea Engine** | — | Autonomous research, evidence-backed improvement proposals |\n| 15 | **Site Generation** | 9 | Full-corpus rebuild, slot-first GPT Image 1.5 media, NotebookLM podcast/infographic/video, citations |\n| 16 | **Cinematic Website** | — | 100-rule prime directive: cinematic UX, PWA, JSON-LD, CWV, a11y, integrations, TDD, deploy |\n| 17 | **Non-Engineering Verticals** | 4 | C-suite personas, finance domain, compliance OS, PM domain — full-org coverage |\n| 18 | **Document Processing** | 4 | DOCX/XLSX read-write, PDF parse + generate, PPTX generation — zero manual exports |\n| 19 | **MCP Authoring** | 3 | HTTP MCP on Workers, stdio server templates, OpenAPI→MCP forger, registry publish |\n\n## Agents\n\n```\n         AGENT ROUTING BY MODEL TIER\n\n  ┌─────────────────────────────────────┐\n  │            OPUS (heavy)             │\n  │  Architecture │ Security │ Vision   │\n  │  Completeness │ Meta-orchestration  │\n  ├─────────────────────────────────────┤\n  │           SONNET (standard)         │\n  │  Build │ Test │ Deploy │ Debug      │\n  │  Migrate │ Profile │ Simplify      │\n  │  Dependencies │ Incidents │ CU-op  │\n  ├─────────────────────────────────────┤\n  │            HAIKU (fast)             │\n  │  Content │ SEO │ A11y │ Changelog  │\n  │  Cost estimation                    │\n  └─────────────────────────────────────┘\n```\n\n| Agent | Model | Effort | Purpose |\n|-------|:-----:|:------:|---------|\n| **architect** | Opus | max | Repo-map generation, task graphs, architectural seams |\n| **completeness-checker** | Opus | max | Zero Recommendations Gate — nothing ships incomplete |\n| **meta-orchestrator** | Opus | max | Cross-agent coordination and task graph execution |\n| **security-reviewer** | Opus | max | OWASP Top 10:2025, secrets exposure, CSP audit |\n| **visual-qa** | Opus | max | Screenshot all 6 breakpoints, AI vision layout detection |\n| **code-simplifier** | Sonnet | high | Reduce complexity while preserving all functionality |\n| **computer-use-operator** | Sonnet | high | Native macOS app automation via Computer Use MCP |\n| **dependency-auditor** | Sonnet | high | Package security, license compliance, update strategy |\n| **deploy-verifier** | Sonnet | high | Post-deploy smoke tests at 6 breakpoints |\n| **incident-responder** | Sonnet | high | Sentry-triggered triage, root cause, auto-fix PRs |\n| **migration-agent** | Sonnet | high | Framework/DB/API migration with rollback safety |\n| **performance-profiler** | Sonnet | high | Core Web Vitals analysis, bundle audit, runtime profiling |\n| **test-writer** | Sonnet | high | TDD-first Playwright E2E + Vitest units, stable selectors |\n| **accessibility-auditor** | Haiku | low | axe-core WCAG 2.2 AA audits and remediation guidance |\n| **changelog-generator** | Haiku | low | Conventional commit parsing, user-outcome release notes |\n| **content-writer** | Haiku | low | Marketing copy, microcopy, alt text, SEO content |\n| **cost-estimator** | Haiku | low | Cloudflare Workers cost forecasting and free-tier warnings |\n| **seo-auditor** | Haiku | low | Title, meta, H1, JSON-LD, OG tags, sitemap validation |\n| **notebooklm-orchestrator** | Sonnet | high | Podcast (ElevenLabs) + infographic + explainer video pipeline per site |\n\n## Hard Gates\n\nEvery deploy must clear all gates. No exceptions. No overrides.\n\n| Gate | Threshold | Tool |\n|------|:---------:|------|\n| E2E Tests | 0 failures @ 6 breakpoints | Playwright v1.59+ |\n| Visual QA | ≥ 8/10 | AI vision (Claude Sonnet 4.6 default; current OpenAI multimodal fallback) |\n| Accessibility | ≥ 95 | Lighthouse |\n| A11y Violations | 0 | axe-core |\n| SEO Score | GREEN | Yoast-equivalent |\n| Console Errors | 0 | Browser DevTools |\n| Placeholders | 0 | Content sweep |\n| Readability | Flesch ≥ 60 | Copy audit |\n\n## Stack\n\n```\n  REQUEST FLOW\n\n  Browser ──→ CF Workers ──→ Hono RPC ──→ Drizzle v1 ──→ D1/Neon\n     │              │             │              │\n     │         KV/Upstash    Zod valid.     Migrations\n     │              │             │\n     ├── Clerk (auth)        Turnstile\n     ├── Stripe (pay)        Resend (email)\n     ├── PostHog (analytics) Sentry (errors)\n     └── GA4/GTM (tracking)  Inngest (jobs)\n```\n\n| Layer | Technology |\n|-------|------------|\n| Hosting | Cloudflare Workers |\n| Backend | Hono RPC + `@hono/zod-validator` |\n| Frontend | Angular 21 + Ionic 8 + PrimeNG 21 (or vanilla) |\n| Database | D1 (edge) / Neon (Postgres) |\n| ORM | Drizzle v1 + Zod |\n| Cache | KV / Upstash Redis |\n| Auth | Clerk |\n| Payments | Stripe |\n| Email | Resend + Listmonk |\n| Jobs | Inngest |\n| Testing | Playwright v1.59+ + Vitest |\n| Lint | ESLint + Prettier |\n| Runtime | Bun |\n| Monitoring | PostHog + Sentry + GA4/GTM |\n\n## Templates\n\n| Template | Purpose |\n|----------|---------|\n| `acceptance-criteria.md` | Structured AC with testable conditions |\n| `adr-template.md` | Architecture Decision Records |\n| `brief.md` | Product brief from domain name |\n| `launch-checklist.md` | Pre-launch verification checklist |\n| `product-intent.yaml` | Machine-readable product definition |\n| `qa-report.json` | Structured QA output format |\n| `repo-map.md` | Codebase architecture map |\n| `saas-feature-manifest.md` | Complete SaaS feature matrix |\n| `session-learning.md` | Post-session knowledge extraction |\n| `starter-scaffold.md` | New project scaffolding guide |\n| `semgrep-rules/` | Custom Semgrep rules for codebase enforcement |\n| `task-graph.json` | Parallelizable task decomposition |\n\n## Tools\n\n| Script | Purpose |\n|--------|---------|\n| `bin/check-required-keys.sh` | API Key Gate helper — verifies per-mode required keys present, JSON output + audit log |\n| `bin/emdash-quick-lint` | Staged-file linting (ESLint+Prettier+ShellCheck) |\n| `bin/emdash-secret-scan` | Pre-commit secret detection via `detect-secrets` |\n| `bin/emdash-cost-check` | Quick Cloudflare cost estimate from wrangler.toml |\n| `scripts/discover-secrets.sh` | Inventory all available API keys across sources |\n| `scripts/gpt4o-vision-analyze.sh` | OpenAI multimodal screenshot analysis for visual QA (script filename predates the 2026-02 GPT-4o retirement; uses current GPT Image 2 vision per `platform.openai.com/docs/deprecations`) |\n| `scripts/validate-skills.sh` | Cross-reference validation for skill files |\n| `scripts/visual-tdd-loop.sh` | Automated screenshot→fix→verify loop |\n\n## Task Routing\n\nThe router loads the smallest useful subset per task — never the full 163 docs. See [`_router.md`](_router.md) for the complete routing table. This plugin ships 163 reference docs across 19 skill categories.\n\n| When you say... | Skills loaded |\n|-----------------|---------------|\n| \"Build a new project\" | 02 → 03 → 05 → 06 → 09 |\n| \"Add a feature\" | 05 → 06 → 07 |\n| \"Fix CI\" | 07 → 08 (especially `gh-fix-ci`) |\n| \"Deploy this\" | 08 (+ 09 if content changed) |\n| \"Polish the frontend\" | 09 → 10 → 11 → 12 |\n| \"Set up billing\" | 05/auth → 06/webhooks → 13/stripe |\n| \"Add analytics\" | 13 (+ 09/social if publishing) |\n| \"Brainstorm ideas\" | 03 → 14 |\n\n## Ideal Prompts\n\nCopy-paste these as-is. Each one routes through the skill graph and produces a deployed, gate-cleared product. The shorter the prompt, the more the skill engine infers — domain name alone is enough.\n\n### Build a SaaS from a domain\n\n```\nBuild acmebilling.dev — recurring subscription billing for indie SaaS founders. Stripe-native, Clerk auth, Inngest for retry workflows.\n```\n\n- **Skills** — 01 → 02 → 03 → 05 → 06 → 07 → 08 → 13\n- **Agents** — architect (Opus) → 5 parallel build agents → deploy-verifier + seo-auditor + visual-qa\n- **Gate fires** — API Key Gate checks `STRIPE_*`, `CLERK_*`, `INNGEST_*`, `CLOUDFLARE_API_KEY` (global) before any scaffold\n- **Output** — live Worker on `acmebilling.dev` with checkout, dashboard, webhook handler, Sentry + PostHog + GA4 wired\n\n### Rebuild an existing site\n\n```\nRebuild brianzalewski.com — pull current site from Wayback if dead, keep every page, modernize design, ship to CF Workers.\n```\n\n- **Skills** — 01 → 02 → 09 (brand extraction) → 15 (full corpus + media+video extraction + grammar audit) → 07 → 08\n- **Agents** — architect → content-writer + visual-qa + seo-auditor\n- **Gate** — every original URL = 200 or 301; logo retention; theme match; favicon set via real-favicongenerator\n\n### Spin up a portfolio from one line\n\n```\nMake me a portfolio site at brian.dev — I'm a principal engineer, AI builder, Megabyte Labs founder.\n```\n\n- **Skills** — 01 → 02 (founder inference) → 09 → 10 → 11 → 12 → 14 (auto-suggests project tiles + impact stats) → 07 → 08\n- **Optional pairing** — if a flagship SaaS exists, portfolio links to it as primary work\n- **Output** — dark-first single-page with hero + work + writing + contact\n\n### Local-business site (NAP + reviews + map)\n\n```\nBuild paterson-dental.com — family dental practice in Paterson NJ, online booking, insurance verification, Spanish/English.\n```\n\n- **Skills** — 01 → 02 → 09 → 10 → 13 (local conversion patterns: phone_click, direction_click, booking_click)\n- **Gate** — `GOOGLE_MAPS_API_KEY` + `GOOGLE_PLACES_API_KEY` required\n- **Output** — full-width Maps embed, NAP schema.org `LocalBusiness`, OpenTable/Booksy embed, Twilio SMS booking\n\n### Non-profit with donation flow\n\n```\nBuild sjsk.org — community clothing distribution for SJSK in Newark, donor portal, impact counter, tax receipt PDFs.\n```\n\n- **Skills** — 01 → 02 → 09 → 13 (Stripe-first GiveDirectly UX)\n- **Gate** — `STRIPE_*` keys\n- **Output** — Donate CTA in nav, recurring + one-time, Resend tax receipts, impact counters with IO+rAF roll-in\n\n### Brainstorm before you build\n\n```\nWhat's the highest-ROI thing I can ship this week? Read PORTFOLIO.md, scan current projects, propose 3 ideas with confidence scores.\n```\n\n- **Skills** — 14 (idea engine) → bounded web research → self-critique filter\n- **Output** — 3 evidence-backed proposals with `apa_citation` per claim, viral coefficient + AI search visibility scoring, auto-implements `confidence ≥ 0.85` aligned ideas\n\n### Add a feature to an existing project\n\n```\nAdd a magic-link auth flow to acme.dev — passwordless email via Resend, Clerk session, redirect to /dashboard.\n```\n\n- **Skills** — 05 (architecture decision) → 06 (build slice) → 07 (Playwright E2E homepage-first)\n- **Agents** — test-writer (failing test FIRST) → implementation → deploy-verifier\n\n### Debug a wedged pipeline\n\n```\nprojectsites.dev workflow stuck on site_id 47 for 3 hours. Diagnose, fix, retrigger.\n```\n\n- **Skills** — 08 (deploy/runtime) → 07\n- **Rule loaded** — `failed-pipeline-protocol.md` (5 canonical failure modes)\n- **Sequence** — detect via D1 query → diagnose root cause (CHECK constraint? timeout? OOM?) → fix → verify in isolation → mint session → retrigger via direct worker URL → background monitor\n\n### Ship a content-driven blog at scale\n\n```\nGenerate 50 programmatic SEO pages for acme.dev — integration|comparison|use-case|template|location templates, GEO-optimized, citations.\n```\n\n- **Skills** — 09 (pSEO 5 types + GEO + sourced facts via APA citations) → 06 → 07\n- **Output** — 50 unique routes, no templated copy, every quantitative claim cites APA 7th source, Schema.org `Article` with `citation:CreativeWork[]`\n\n### One-line magic\n\n```\nghost.megabyte.space\n```\n\n- **Skills** — 01 (one-line prompt mode inference) → 02 → 05 → 09 → 10 → 11 → 12 → 07 → 08\n- Domain alone routes to a complete product\n- Gate fires\n- Brand extracted from existing infrastructure\n- Curated dark/neon aesthetic from `~/Snapchat/best/` 622-shot reference\n- Logo from Ideogram\n- Deployed to CF Workers\n\n### Prompt patterns that work\n\n| Phrase | Effect |\n|--------|--------|\n| `boil the lake` | Force complete-not-shortcut mode for the next decision |\n| `parallel everything` | Decompose first, spawn 3-5 agents per phase |\n| `skip api key gate` | Bypass key check (rare — deploys will likely 500) |\n| `recommendations loop until zero` | Keep finding+fixing until no rec remains |\n| `chain MCPs` | Use meta-orchestrator across 19+ services |\n| `homepage-first` | Reset E2E flow to start at `/` and click through |\n| `boil X, flag Y` | Do X completely; surface Y as issue |\n| `make it shorter` | Reduce 40-60% (Brian's #1 most-used phrase, 670+ logged uses) |\n| `the whole thing` | Never truncate — full file output |\n| `Now ...` | Chain to previous task, don't reset context |\n\n## Philosophy\n\n- **Distribution \u003e Technology** — The best tool nobody knows about is the worst tool. Auto-create repos for new skills. Integrate into every ecosystem. Broadcast widely.\n- **Boil the Lake** — When completeness costs minutes more than a shortcut, do complete. Boil lakes, flag oceans.\n- **TDD Always** — Failing test first → implement → pass. Real user flows. Homepage first. Click through UI. Never `page.goto()` for internal navigation.\n- **One Person + AI = Twenty** — The barrier is gone. What remains is taste, judgment, and willingness to do the complete thing.\n\n## Can You Make This Better?\n\nSeriously — [open an issue](https://github.com/heymegabyte/claude-skills/issues/new?title=Improvement%20suggestion\u0026body=I%20think%20this%20could%20be%20better%20if...) or submit a PR. Some things we're thinking about:\n\n- **More skill categories?** Is 15 the right number or are we missing something?\n- **Better agent routing?** Should model assignments shift as Claude evolves?\n- **Templates you wish existed?** What boilerplate do you write over and over?\n- **Skills for other stacks?** This is CF Workers + Angular today. What else?\n- **Prompting patterns** that consistently produce better results?\n\nIf you've built something similar, stolen ideas from here, or just have opinions — we want to hear it. The whole point is that this gets better every day.\n\n## License\n\nCopyright (c) 2024-2026 [Brian Zalewski](https://megabyte.space) / [Megabyte Labs](https://megabyte.space). [The Rutgers License](LICENSE).\n\nTL;DR — It's free. Use it. But if it helped you, be cool about it and [send what feels right](mailto:hey@megabyte.space). We made this and we'd like to eat.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fheymegabyte%2Fclaude-skills","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fheymegabyte%2Fclaude-skills","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fheymegabyte%2Fclaude-skills/lists"}