elite-github-skills-hub
Curated hub of the highest-value GitHub skills/repos for Claude Code, Cursor, Codex, Gemini CLI, and OpenClaw. Links to 20+ elite repos organized by tier. Use when discovering, evaluating, or installing skills from the open-source ecosystem.
What this skill does
# 🏆 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](https://github.com/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](https://github.com/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](https://github.com/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](https://github.com/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](https://github.com/mattpocock/skills) | ~84K | TypeScript expert's 17 real-world skills from personal .claude directory. | `npx skills@latest add mattpocock/skills` | | 6 | [anthropics/skills](https://github.com/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](https://github.com/hesreallyhim/awesome-claude-code) | 43.4K | Most authoritative curated list. Skills/hooks/agents/orchestrators/plugins. | Browse & pick | | 8 | [addyosmani/agent-skills](https://github.com/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](https://github.com/ComposioHQ/awesome-claude-skills) | 34.5K | 850+ SaaS integrations + curated skills list. | Browse & pick | | 10 | [pbakaus/impeccable](https://github.com/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](https://github.com/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](https://github.com/alirezarezvani/claude-skills) | 15.4K | 313+ skills: engineering/marketing/product/compliance/research/C-level advisory. | Browse & pick | | 13 | [supermemoryai/supermemory](https://github.com/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](https://github.com/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](https://github.com/Lum1104/Understand-Anything) | ~12K | Codebase → interactive knowledge graph. Multi-agent pipeline + web dashboard. | | 16 | [VoltAgent/awesome-agent-skills](https://github.com/VoltAgent/awesome-agent-skills) | ~5K | Official team skills (Anthropic/Google/Vercel/Stripe/Cloudflare/Netlify/Sentry). | | 17 | [VoltAgent/awesome-openclaw-skills](https://github.com/VoltAgent/awesome-openclaw-skills) | ~8K | 5,200+ curated OpenClaw skills from 13,729 community-built. | | 18 | [ruvnet/ruflo](https://github.com/ruvnet/ruflo) | ~51K | Multi-agent orchestration wizard. | | 19 | [0xfurai/claude-code-subagents](https://github.com/0xfurai/claude-code-subagents) | ~2K | 100+ subagents, MIT, multi-language. | ## 💼 Business & Founder Skills (Dedicated) | # | Repo | ⭐ Stars | What It Does | Best For | |---|------|---------|-------------|---------| | F1 | [garrytan/gstack](https://github.com/garrytan/gstack) | 97K | 23 specialist roles incl. CEO review, office hours, CSO security audit | Technical founders | | F2 | [slavingia/skills](https://github.com/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](https://github.com/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: 1. **Idea Stage**: Validate problem exists (not whether you can build it). Use Claude as devil's advocate. 2. **MVP Stage**: Agentic Coding + CLAUDE.md as architectural context doc. Define scope BEFORE building. 3. **Launch Stage**: Automate the founder out of daily operations. Claude Cowork for workflows. 4. **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): 1. `forrestchang/andrej-karpathy-skills` — 70 lines, immediate behavior change 2. `anthropics/skills` — Official baseline ### A-Tier (pick one based on workflow): 3. `obra/superpowers` — if you want TDD methodology 4. `garrytan/gstack` — if you're a solo founder / team lead 5. `slavingia/skills` — if you're building a business from scratch ### B-Tier (add when you hit the pain): 6. `supermemoryai/supermemory` — cross-session memory 7. `OthmanAdi/planning-with-files` — complex task planning 8. `pbakaus/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*
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.