paper-with-me

홈 › Papers

SkillFab: An Agent-Native Skill Production Platform

2026-07-04 · Anjie Xu, Yifeng Cai, Yi Li, Zixing Wang, Zhiyu Zhang, Jingfan Chen, Ruohan Xu, Leye Wang arxiv

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.

📄 PDF Abstract BibTeX arXiv:2607.03780

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

EdgeFM: Efficient Edge Inference for Vision-Language Models

2026-04-30 · Mengling Deng, Yuanpeng Chen, Sheng Yang, Wei Tao 외 arxiv

Vision-language models (VLMs) have demonstrated strong applicability in edge industrial applications, yet their deployment remains severely constrained by requirements for deterministic low latency and stable execution u…

MediaClaw: Multimodal Intelligent-Agent Platform Technical Report

2026-05-14 · Shaoan Zhao, Huanlin Gao, Qiang Hui, Ting Lu 외 arxiv

MediaClaw is a multimodal agent platform built on the OpenClaw ecosystem. Its core design follows a three-layer architecture of unified abstraction, pluginized extension, and workflow orchestration. The system is intende…

Evaluating Skills, Not Just Agents: Agentic Continuous Evaluation of Skills

2026-08-20 · Christopher Kevin, Narendran Raghavan, Jean-Francois Puget, Roshni Malani 외 arxiv

Enterprise agent programs are moving from prototypes into production, where reusable skills, tools, and workflow packages must be reviewed with evidence rather than prose. Current gates often scan these artifacts for str…

Managing Procedural Memory in LLM Agents: Control, Adaptation, and Evaluation

2026-06-22 · Julia Belikova, Rauf Parchiev, Evgeny Egorov, Grigorii Davydenko 외 hf

Procedural memory is increasingly used to improve LLM agents on recurring workplace tasks, yet its ability to produce reusable skills remains poorly understood. We introduce AFTER, a benchmark of 382 realistic enterprise…

SkillWiki: A Living Knowledge Infrastructure for Agent Skills

2026-06-15 · Dingcheng Huang, Yuda Ding, Bingshuo Liu, Qingbin Liu 외 arxiv

While knowledge is managed through Wikipedia and software through GitHub, agent skills still lack an infrastructure for large-scale production, governance, and evolution. SkillWiki is a living knowledge infrastructure th…