system-prompt-tuning
Personal skills and workflows for Codex and GPT agents, turning repeatable judgment into reusable agent context.
Découvrez les compétences d'agent publiées, les flux de travail SKILL.md réutilisables et les modules prêts à être installés pour Claude Code, Codex et ChatGPT.
Personal skills and workflows for Codex and GPT agents, turning repeatable judgment into reusable agent context.
An open-source, code-first toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.
Agent skills for interacting with Railway
Aucune description n'est encore disponible pour cette compétence.
🏥 Hermes Agent Skill v2.0 - 通用可移植版,适用于 WorkBuddy/Claude Code/Cursor 等 AI Agent 平台
Aucune description n'est encore disponible pour cette compétence.
A collection of AI agent skills following the Agent Skills open format
🚀2.3x faster than MinIO for 4KB object payloads. RustFS is an open-source, S3-compatible high-performance object storage system supporting migration and coexistence with other S3-compatible platforms such as MinIO and Ceph.
Aucune description n'est encore disponible pour cette compétence.
Aucune description n'est encore disponible pour cette compétence.
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
A collection of specialized agent skills for AI infrastructure development, enabling Claude Code to write, optimize, and debug high-performance systems.
cursor/cc rules to facilitate the development of Domo Custom Apps
Aucune description n'est encore disponible pour cette compétence.
423 plugins, 2,849 skills, 177 agents for Claude Code. Open-source marketplace at tonsofskills.com with the ccpi CLI package manager.
Production-grade Agent Skills curated by the most experienced engineers around the world
Claude Code skill implementing Manus-style persistent markdown planning — the workflow pattern behind the $2B acquisition.
Build agent-ready APIs without splitting your server model. Define tools once, expose them as both HTTP endpoints and MCP tools.