GitHub collection

heymegabyte/claude-skills

Imported from GitHub — is this yours?

18 skills imported from this repository.

Claude Skill

operating-system

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

LLM Mart

Claude Skill

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.

LLM Mart

Claude Skill

planning-and-research

Deep web research, competitor scanning, technology evaluation, and implementation planning. Decomposes work into vertical slices, identifies parallel workstreams, tracks assumptions with confidence levels, and designs the critical path for minimum wall-clock time.

LLM Mart

Claude Skill

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.

LLM Mart

Claude Skill

architecture-and-stack

Cloudflare-first platform selection. Decision trees for Workers, D1, R2, KV, DO, Queues, Vectorize, Containers, Sandboxes, Flagship, Agent Memory, Workflows v2. Default stack, override conditions, auth, data patterns, reliability.

LLM Mart

Claude Skill

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 observabi

LLM Mart

Claude Skill

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.

LLM Mart

Claude Skill

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.

LLM Mart

Claude Skill

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.

LLM Mart

Claude Skill

media-orchestration

Section-by-section media planning and generation. Image generation (GPT Image 1.5 primary, built-in fallback), logo/icon generation (Ideogram v3 → favicon set), video generation (Sora), social preview images (OG 1200x630 + AI search optimization), stock photo curation (Pexels, Pi

LLM Mart

Claude Skill

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-f

LLM Mart

Claude Skill

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

LLM Mart

Claude Skill

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-p

LLM Mart

Claude Skill

non-engineering-verticals

C-suite personas, compliance OS, PM domain, and finance domain skills for enterprise client work. Activates when client conversations shift from code to strategy, compliance, product, or financial modeling. Source: alirezarezvani/claude-skills C-suite + compliance tier.

LLM Mart

Claude Skill

document-processing

PDF/DOCX/XLSX/PPTX generation and parsing on Cloudflare Workers. Covers CF Browser Rendering → PDF, pdf-lib Worker-native generation, docx/exceljs output, pptxgenjs slides, and RAG-ready text extraction. Use cases: donor annual reports, SaaS invoices, tax receipts, financial repo

LLM Mart

Claude Skill

mcp-authoring

When to author an MCP server, architecture overview (tools/resources/prompts), stdio vs HTTP+SSE transport tradeoffs, registration in .claude.json. Sub-modules: stdio-server-template.md (full TS code), http-server-on-workers.md (Hono + SSE on CF Workers), forge-mcp-from-openapi.m

LLM Mart

Claude Skill

superpowers

Use when starting creative work, planning a multi-step task, isolating a workspace, wrapping a branch, or giving/getting code review. Not when the task is a one-line fix with no design surface.

LLM Mart

Claude Skill

emdash-skills

14-category product-building OS. CF Workers+Hono, Angular, D1, Drizzle, Clerk, Stripe. 94 reference docs, 18 agents.

LLM Mart

Commands (25)

  • /install-lint-stack — Bootstrap industry-leading lint+autofix+commit-hygiene stack on the current project. Drops in lefthook, oxlint, ESLint, Prettier, Stylelint, markdownlint, ruff, shellcheck, shfmt, yamllint, hadolint, actionlint, jscpd, knip, semgrep, gitleaks, commitizen + git-cz-emoji (emoji-mandatory commits), and semantic-release. Idempotent — re-runs upgrade safely. See rules/lint-doctrine.md. source
  • /list-arcs — Surface all retrospective documents with key shape metrics; compare arcs deliberately. source
  • /migrate-all-to-hardened — Batch-migrate every hardened MCP server in mcp-servers/ from its original source to its hardened counterpart in one sweep source
  • /migrate-skill — Generic skill-version migration — works for hardened/v2/experimental→stable promotions across MCP servers, skills, hooks, commands. Mirrors /migrate-to-hardened with broader detection. source
  • /migrate-to-hardened — Automate the unhardened → hardened MCP server cutover — build, smoke-test, register, and archive in one shot source
  • /multimedia-enrich — Progressive multimedia enrichment pass — add high-value audio/video/image/interactive to a site, run again and again source
  • /plan-execute-verify-repair — Run the autonomous-engineering operating loop on a task (plan→implement→verify→repair→report) source
  • /post-arc-retrospective — Capture the cumulative output of a /loop arc into a single auditable retrospective document; scans the heymegabyte-claude-skills plugin for modified files, categorizes by directory, counts LOC delta, extracts tool counts from MCP servers, and writes a timestamped report to retrospectives/ source
  • /prepare-multi-file-brief — Turn a comma-separated list of file paths into a fully structured Pattern A agent brief — ordered writes, per-file schemas, and a verification step baked in. source
  • /prepare-skeleton-brief — Turn Pattern B from agent-resilience-discipline into a one-keystroke agent brief for a single-file deliverable < 300 lines. source
  • /process — Chain the full Superpowers process flow — brainstorm → plan → worktree → build → review → finish — on one slash command source
  • /prune-mcp-tools — Reduce a forge-generated MCP server's tool surface. Comment out low-value tools (preserving reversibility), update the README tool count, and emit a pruning report. source
  • /register-forged-mcps — Scan ~/.claude/plugins/heymegabyte-claude-skills/mcp-servers/*/ and emit .claude.json registration JSON for each forged MCP server. Default is dry-run; use --apply to write to ~/.claude.json. source
  • /retro — Generate a timestamped arc retrospective from the past 7 days of git history in `~/.agentskills`. source
  • /review-global-prompts — Review ~/.claude/CLAUDE.md + rules for contradictions, stale guidance, duplication; consolidate source
  • /rollback-all-to-original — Panic-rollback button — reverses /migrate-all-to-hardened by restoring every MCP server from its archived original. Sequential to avoid ~/.claude.json collisions. source
  • /run-evals — Batch-run all LLM eval cases in tools/evals/cases/*.json; aggregate pass/fail, cost, regression vs last run; exit nonzero in CI mode source
  • /run-mcp-evals — Run golden-test eval suites against one or all MCP servers in mcp-servers/; compares actual tool responses to expected via exact-match + regex + min-count tiers; supports mock-mode so CI runs without API keys source
  • /saas — One-line SaaS — from a description, scaffold a complete CF-native multi-tenant SaaS (Hono + D1 + Drizzle + Better Auth + Stripe + shadcn) deployed to a real URL source
  • /security-supply-chain — Unified supply-chain audit. Checks GitHub Actions SHA-pinning (`sha-pin:check`), package.json git+https deps (per `no-gitlab-megabytelabs-deps` semgrep), gitleaks scan, and trufflehog verified-only sweep. Surfaces any tag-mutable, git-URL, or secret-exposed surface. Per rules/ai-agent-security.md § Supply chain. source
  • /self-improve — Run a learning pass after a major run; fold reusable lessons into global config source
  • /session-recap — Summarize recent CHANGELOG.md entries for context restoration. Parses the canonical heading shape `## YYYY-MM-DD — pass-N — summary`. Filters: last N (default 10), YYYY-MM date prefix, or "today". Supports --json for machine-readable output. source
  • /skill-health — Run quality-scores + token-budget + dep-graph, interpret results, flag missing budgets, orphans, and oversize skills source
  • /update-agentskills — Apply a reusable lesson to ~/.agentskills (rules/skills/templates/commands), backup + commit + push source
  • /vendor-rotation-calendar — Generate a quarterly vendor secret-rotation calendar for all load-bearing vendors; emit .ics + ROTATIONS-DUE-NEXT-30-DAYS table; optionally create Google Calendar events source