Vibe-Skills
foryourhealth111-pixel/Vibe-Skills
Intelligent Skill routing and workflow orchestration for AI agents — +21.12 pp reward, −29.6% tokens on SkillsBench with DeepSeekV4Flash-VE.
- 形态
- Skill 技能
- 安装
- 克隆到 skills 目录
- 需要密钥
- 否
- 近月下载
- —
- 最近推送
- 3 天前更新
项目说明
From README
English 中文 Latest stable release Quick start · Measured on SkillsBench Mean verifier reward: +21.12 pp Total tokens: -29.6% · Tool calls: -33.1% SkillsBench is a benchmark designed to evaluate whether AI agents can effectively use Skills to complete professional tasks across diverse domains.
Its purpose is to measure how much a model’s ability to solve complex real-world tasks improves when it is equipped with specialized Skills.
To evaluate performance in production-like environments where a large number of Skills are installed simultaneously, we adapted SkillsBench into a more realistic large-scale multi-Skill setting .
In the original SkillsBench setup, each task is provided only with the specialized Skill associated with that task.In our modified setting, every task is evaluated in a global environment containing all 195 specialized Skills , while all other experimental conditions r
安装方式
克隆到 skills 目录 · 安装无需配置
npx skills add foryourhealth111-pixel/Vibe-Skills该仓库 README 未给出可直接解析的安装命令,以上为按插件形态生成的参考写法。 执行前请以仓库 README为准。
为什么是这个分数
近 3 天仍在推送;README 未给出明确安装命令,需要自己读;装完即可用,无需额外配置;3803 stars,社区使用面较广。
- 维护活跃
- 96
- 实用度
- 84
- 生态热度
- 80
- 上手便捷
- 70
- 信号质量
- 100
- 数据置信度
- 100%
相关插件
dsh-Visual-Workflow
GZX2211/dsh-Visual-Workflow
可视化 Agent 编排平台|基于 DeepSeek Harness,支持 Workflow、Multi-Agent、元编排、MCP 与 Human-in-the-loop|Visual AI Agent orchestration platform for workflows, multi-agent teams, MCP and human-in-the-loop
agent-body
1420079678-ctrl/agent-body
Agent-Body 器官的解剖面板:在 harness 内部的 /anatomy 提供实时体征看板——器官、心跳、自愈账本、自训练计数与真实脉冲流,数据直接读自运行时文件而非誊写。仅 host 端,无客户端 bundle、无构建步骤。
RE-Framework
unknowbug/RE-Framework
Modular engineering methodology framework for AI agents — reverse engineering & software development (core + re-binary / re-code / swe modules).