Control center / Discover
Discover Browse by category instead of drowning in search results. Every category opens a submenu of subcategories with live counts, and checking one narrows the grid to exactly that slice.
◑ Verified against GitHub · scores pending
Sort by: Best match Skill installs Stars Downloads Last updated Forks Name ↓ DescType: Filter by entry type All types MCP Server Claude Skill Agent Repository Tool Trust: Filter by trust evidence Any trust state Crown eligible Trust checked Audit conflict Maturity: Filter by maturity Any maturity Stable Active Experimental Slowing 4 shown
All (4) ◎ Marketing (0)↗ GTM & Growth (0)✎ Design (0)⛨ Security (1)▶ Video & YouTube (0)⌘ Development (0)⌕ Data & Research (0)⑂ Automation (0)⚡ Token & Cost Optimization (0)◆ AI Agents (1)◐ LLM Ops & Observability (2)◇ RAG & Knowledge (0)
⛨ Security1 Browse subcategories → aquasecurity ★ 8.1k Tool experimental Checks Kubernetes clusters against the CIS Benchmark.
Best match because its name, category, capabilities, or owner matches “benchmark”. Adoption and trust break close ties.
Stars 8.1k
Downloads —
Updated 2026-07-30
Skill installs — Trust pending Momentum not matched
Cloud & IaC Security
◆ AI Agents1 Browse subcategories → princeton-nlp ★ 20k Agent active Autonomous software engineering agent designed to solve real GitHub issues in SWE-bench.
Best match because its name, category, capabilities, or owner matches “benchmark”. Adoption and trust break close ties.
Stars 20k
Downloads —
Updated 2026-07-27
Skill installs — Trust pending Momentum not matched
$ pip install sweagentCopy Coding Agents
◐ LLM Ops & Observability2 Browse subcategories → EleutherAI ★ 14k Repository experimental Unified framework for evaluating language models across hundreds of benchmark tasks.
Best match because its name, category, capabilities, or owner matches “benchmark”. Adoption and trust break close ties.
Stars 14k
Downloads 1512k
Updated 2026-07-13
Skill installs — Trust pending Momentum not matched
$ pip install lm_evalCopy Evals
openai ★ 19k Repository experimental Framework for creating and running evaluations on large language models and systems.
Best match because its name, category, capabilities, or owner matches “benchmark”. Adoption and trust break close ties.
Stars 19k
Downloads 2.5k
Updated 2026-04-14
Skill installs — Trust pending Momentum not matched
$ pip install evalsCopy Evals