🏆 Elite GitHub Skills Hub
2026-05-19 · 10-round deep research · Deduplicated against 727 existing AGI-Super-Team skills Maintained by CRO · Feynman
🎯 When to Use
- "What are the best Claude Code skills repos?"
- "Recommend high-value skills for my project"
- "I want to install the top community skills"
- "Show me business/founder skills"
- "What skills should a solo founder install?"
📊 Tier S — Must-Install (>50K stars, ecosystem-level)
| # | Repo | ⭐ Stars | What It Does | Install |
|---|---|---|---|---|
| 1 | obra/superpowers | ~192K | TDD-driven agentic skills framework. 14 skills + 5 agents. "Iron Laws" methodology. Red-Green-Refactor for process docs. | /plugin install superpowers@claude-plugins-official |
| 2 | affaan-m/everything-claude-code | ~182K | Anthropic Hackathon winner. 28 agents + 119 skills + 60 commands. Cross-platform (Claude Code/Cursor/Codex/OpenCode). 620K+ installs. | /plugin install ecc@ecc |
| 3 | forrestchang/andrej-karpathy-skills | ~131K | Karpathy's LLM failure patterns → single CLAUDE.md. 70 lines, immediate behavior change. Think Before Coding / Simplicity First / Surgical Changes / Goal-Driven. | curl -o CLAUDE.md https://raw.githubusercontent.com/forrestchang/andrej-karpathy-skills/main/CLAUDE.md |
| 4 | garrytan/gstack | ~97K | YC CEO's setup. 23 specialist roles (CEO/Eng/Designer/Reviewer/QA/CSO/Release). Sprint workflow: Think→Plan→Build→Review→Test→Ship→Reflect. | git clone --depth 1 https://github.com/garrytan/gstack.git ~/.claude/skills/gstack && cd ~/.claude/skills/gstack && ./setup |
| 5 | mattpocock/skills | ~84K | TypeScript expert's 17 real-world skills from personal .claude directory. | npx skills@latest add mattpocock/skills |
| 6 | anthropics/skills | ~135K | Anthropic official. 17 first-party skills (PDF/DOCX/PPTX/frontend-design/MCP-builder/webapp-testing). | /plugin marketplace add anthropics/skills |
📊 Tier A — High Value (10K–50K stars)
| # | Repo | ⭐ Stars | What It Does | Install |
|---|---|---|---|---|
| 7 | hesreallyhim/awesome-claude-code | 43.4K | Most authoritative curated list. Skills/hooks/agents/orchestrators/plugins. | Browse & pick |
| 8 | addyosmani/agent-skills | ~42K | Google's Addy Osmani. SDLC full-lifecycle skills (perf/debug/arch/testing). | /plugin install agent-skills@addy-agent-skills |
| 9 | ComposioHQ/awesome-claude-skills | 34.5K | 850+ SaaS integrations + curated skills list. | Browse & pick |
| 10 | pbakaus/impeccable | 27.6K | AI frontend design language. 21 commands (audit/polish/critique/animate/distill). 277K+ installs. | npx skills add https://github.com/pbakaus/impeccable |
| 11 | OthmanAdi/planning-with-files | ~20K | Manus-style persistent markdown planning. Filesystem as "disk" (persistent) vs context as "RAM" (volatile). | npx skills add https://github.com/OthmanAdi/planning-with-files |
| 12 | alirezarezvani/claude-skills | 15.4K | 313+ skills: engineering/marketing/product/compliance/research/C-level advisory. | Browse & pick |
| 13 | supermemoryai/supermemory | ~16.7K | Cross-session persistent memory engine. MCP integration. State-of-art recall. | npm install supermemory-mcp |
| 14 | shanraisshan/claude-code-best-practice | 53.6K | Claude Code encyclopedia. Agents/commands/skills/hooks/MCP + 80+ tips. Reference implementation. | Browse & learn |
📊 Tier B — Notable (1K–10K stars, unique value)
| # | Repo | ⭐ Stars | What It Does |
|---|---|---|---|
| 15 | Lum1104/Understand-Anything | ~12K | Codebase → interactive knowledge graph. Multi-agent pipeline + web dashboard. |
| 16 | VoltAgent/awesome-agent-skills | ~5K | Official team skills (Anthropic/Google/Vercel/Stripe/Cloudflare/Netlify/Sentry). |
| 17 | VoltAgent/awesome-openclaw-skills | ~8K | 5,200+ curated OpenClaw skills from 13,729 community-built. |
| 18 | ruvnet/ruflo | ~51K | Multi-agent orchestration wizard. |
| 19 | 0xfurai/claude-code-subagents | ~2K | 100+ subagents, MIT, multi-language. |
💼 Business & Founder Skills (Dedicated)
| # | Repo | ⭐ Stars | What It Does | Best For |
|---|---|---|---|---|
| F1 | garrytan/gstack | 97K | 23 specialist roles incl. CEO review, office hours, CSO security audit | Technical founders |
| F2 | slavingia/skills | 7.5K | 10 skills from The Minimalist Entrepreneur: /find-community → /validate-idea → /mvp → /pricing → /grow-sustainably | Solo founders, first-time founders |
| F3 | forrestchang/andrej-karpathy-skills | 131K | 70-line CLAUDE.md: Think Before Coding, Simplicity First, Surgical Changes | Any builder |
📚 Anthropic Founder's Playbook (Reference)
Title: The Founder's Playbook: Building an AI-Native Startup Date: 2026-05-14 | Pages: 36 | Source: claude.com/blog/the-founders-playbook
Four-stage framework:
- Idea Stage: Validate problem exists (not whether you can build it). Use Claude as devil's advocate.
- MVP Stage: Agentic Coding + CLAUDE.md as architectural context doc. Define scope BEFORE building.
- Launch Stage: Automate the founder out of daily operations. Claude Cowork for workflows.
- Scale Stage: Workflow lock-in + compounding behavioral data = defensible moat.
Core insight: "Founder's role shifts from individual contributor to orchestrator of agents."
🚀 Recommended Minimum Stack
S-Tier (install today, every project):
forrestchang/andrej-karpathy-skills— 70 lines, immediate behavior changeanthropics/skills— Official baseline
A-Tier (pick one based on workflow):
obra/superpowers— if you want TDD methodologygarrytan/gstack— if you're a solo founder / team leadslavingia/skills— if you're building a business from scratch
B-Tier (add when you hit the pain):
supermemoryai/supermemory— cross-session memoryOthmanAdi/planning-with-files— complex task planningpbakaus/impeccable— frontend design quality
⚠️ Overlap with Existing Skills
| Category | Already in AGI-Super-Team (727) | New from This Hub | Overlap |
|---|---|---|---|
| SaaS integrations | 47+ | Mainly in ComposioHQ | High (90%+) |
| Agent patterns | 59 | superpowers/ECC/claude-flow | Low |
| Design | 0 | impeccable/frontend-slides | Zero |
| Business/founder | 46 (generic) | gstack/slavingia/karpathy | Low |
| Memory systems | Few | supermemory/claude-mem | Low |
| Knowledge graph | 0 | Understand-Anything | Zero |
Conclusion: New repos fill gaps in design, orchestration frameworks, memory, and knowledge graph — <15% overlap.
Last updated: 2026-05-19 | CRO·Feynman | 10-round deep research