让智能体自动创建可复用的技能，无需预先开发。
SkillFab: An Agent-Native Skill Production Platform
- 智能体运行时发现缺功能就生成新技能，按需启动开发流程。
- 通过Git提交证据和维护者审核，确保技能可追溯、可恢复。
- 支持人、脚本、外部智能体共享状态，统一协作平台。
SkillFab 是一个原生面向智能体的平台，用于将缺失的能力转化为经过审查、可复用的智能体技能。运行时，智能体首先搜索可复用技能；当无合适技能可用时，未满足的能力即成为需求驱动的首要问题，无需预先存在仓库或实现分支。开发过程由 SkillFab 管理的仓库、经 Git 接入的提交证据、维护者评审及注册发布共同完成。同一生命周期通过 Web、REST 和 MCP 接口暴露，使人类、脚本和外部智能体在共享状态上协作，而非各自独立的任务日志。当前系统采用作用域内 Git 推送地址、原生范围提交摄入、工作流状态读取与事件历史记录，使长时间运行的智能体任务具备可审查性和可恢复性。本文阐述平台模型、架构、已实现能力，并展示三个案例：端到端操作系统检测技能执行、将运维实践转化为可复用技能知识的 Docker 研究包，以及外部优化案例，展示改进后的技能制品如何作为可审查、版本化的提交进入 SkillFab。部署地址：https://skillfab.ai。
原文摘要 · Abstract (English)
SkillFab is an agent-native platform for turning missing capabilities into reviewed, reusable Agent Skills. At runtime, agents first search for reusable skills; when no adequate skill exists, the unmet capability becomes a demand-first issue before any repository or implementation branch needs to exist. Development then proceeds through a SkillFab-managed repository, Git-ingested commit evidence, maintainer review, and registry publication. The same lifecycle is exposed through web, REST, and MCP surfaces, so humans, scripts, and external agents operate on shared state rather than separate task logs. The current system uses scoped Git push URLs, native range commit ingestion, workflow-state reads, and workflow-event histories to make long-running agent work reviewable and recoverable. We document the platform model, architecture, implemented capabilities, and three case studies: an end-to-end OS-detect skill run, a Docker research package that converts operational practice into reusable skill knowledge, and an external optimization case showing how improved skill artifacts can enter SkillFab as reviewable, versioned submissions. Deployment: https://skillfab.ai.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。