하나의 Skill, 완전히 새로운 가능성. 다음 워크플로를 찾아보세요.
demystifying-rl-tool-agents
Comprehensive recipe for RL-training tool-using agents spanning reward design, data synthesis, model scaling, and algorithm selection. Seven ranked findings: scale-dependent rewards (curriculum for 1.5B–3B; dense for 7B), semi-sparse 'Macro' rewards balance specialization/transfer, 1K-sample sweet spot with 4:3:3 difficulty mix. Achieves SOTA on TravelPlann…
personal-squad
User-level AI agents that travel with you across projects
suede-newsroom
Suede-owned editorial pipeline for agent-run content: six roles with written contracts, one inspectable record that travels between them, and a distribution stage that gives every asset its own argument instead of a shorter draft. Use when content agents return generic, duplicated, or unsourced work, when one flagship piece has to carry a week of distributi…
travelagenttasksai
Access 174+ AI-powered skills for travel agents, travel advisors, and tour operators. Use when: user asks about trip itineraries, client bookings, travel insurance, supplier management, package pricing, destination research, client communications, or any travel agency administration task.
An independently imported catalog with original authors, licenses and source links. Classification is not a security audit.
Sources and import coverage