mlsanityData to 14 Oct 2026

@skills: Attention is all you have

arXiv 2608.12610 ↗First posted 12 Aug 2026cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

There are 56,804 public agent skills today, and teams write many more privately. The dominant delivery model is installation: once installed, a skill's description remains in the system prompt, competing for fewer than 100 reliable trigger slots. This leaves the long tail with no practical path to use and forces teams' own playbooks to compete for the same scarce space. We observe that installation bundles three separable functions: content, persistence, and automatic triggering. Only the last requires prompt residency. We therefore propose @skills, an open protocol that separates them. A path addresses any skill, subtree, or collection, and reading a skill is sufficient to use it, so nothing is installed or made resident. The operation vendors a copy at the same path into a project's Git-tracked tree for adaptation and ownership. The operation adds one .gitignore-style line, the only element that costs prompt residency. A directory is a menu, making bundles ordinary directories rather than all-or-nothing units. The protocol requires no manifest, lockfile, or registration, and SKILL.md remains unchanged. @skills is additive, ships as an installable package, and turns any agent that can read files and run commands into a client through a single instruction file. Its open specification is at https://github.com/SylphAI-Inc/atskills and it is implemented in the AdaL CLI at https://adalagent.ai . Because paths address skills well but cannot find them, the protocol is paired with a free hub at https://atskills.one for corpus-wide search and ranking, repository-free hosting, private and team collections, and one-screen authoring. The hub is optional: gh: and local paths resolve without it, and indexed GitHub skills retain their gh: identities. Install less, use more.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 32 of its 55 references that are in the map. First posted on arXiv 12 Aug 2026.

Builds on

32 of 55 references.

References · 32

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  3. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
  4. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
  5. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  6. 2023SWE-bench: Can Language Models Resolve Real-World GitHub Issues?cited by 3,373
  7. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,212
  8. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,191
  9. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,947
  10. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
  11. 2024SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineeringcited by 1,737
  12. 2023Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injectioncited by 1,443
20 more
  1. 2021Calibrate Before Use: Improving Few-Shot Performance of Language Modelscited by 1,392
  2. 2023MemGPT: Towards LLMs as Operating Systemscited by 1,389
  3. 2024RULER: What's the Real Context Size of Your Long-Context Language Models?cited by 1,346
  4. 2023Gorilla: Large Language Model Connected with Massive APIscited by 1,332
  5. 2021Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivitycited by 1,135
  6. 2023ExpeL: LLM Agents Are Experiential Learnerscited by 876
  7. 2023Large Language Models Can Be Easily Distracted by Irrelevant Contextcited by 841
  8. 2021Learning To Retrieve Prompts for In-Context Learningcited by 648
  9. 2025LLMs Get Lost In Multi-Turn Conversationcited by 429
  10. 2024Agent Workflow Memorycited by 383
  11. 2023Formalizing and Benchmarking Prompt Injection Attacks and Defensescited by 364
  12. 2023LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Modelscited by 287
  13. 2025Model Context Protocol (MCP): Landscape, Security Threats, and Future Research Directionscited by 265
  14. 2024Same Task, More Tokens: the Impact of Input Length on the Reasoning Performance of Large Language Modelscited by 152
  15. 2024Found in the Middle: Calibrating Positional Attention Bias Improves Long Context Utilizationcited by 101
  16. 2025Model Context Protocol (MCP) at First Glance: Studying the Security and Maintainability of MCP Serverscited by 65
  17. 2023LLM Platform Security: Applying a Systematic Evaluation Framework to OpenAI's ChatGPT Pluginscited by 51
  18. 2024Serial Position Effects of Large Language Modelscited by 30
  19. 2024SysBench: Can Large Language Models Follow System Messages?cited by 28
  20. 2025How Many Instructions Can LLMs Follow at Once?cited by 20

Built on by

Not cited yet.