May 26, 2026 · San Jose, CA · Full day
LLM-based agents are rapidly moving from research demos to production systems—but their effectiveness hinges on the procedural knowledge they can access at inference time. Agent Skills are an emerging answer: structured packages of instructions, scripts, and references that augment agents without model modification.
A Skill is a SKILL.md file adopted across Claude Code, Gemini CLI, OpenClaw, Codex, and 30+ agent platforms. Eight focused Skills papers appeared in Feb–Mar 2026. An audit of 3,984 Skills found 37% contained security flaws. SkillsBench revealed that curated Skills improve pass rates by 16.2 points on average, yet self-generated Skills can hurt performance in nearly a third of tasks.
The field is moving fast and needs a dedicated venue. Agent Skills '26 brings together researchers and practitioners working on Skills design, benchmarking, optimization, security, and ecosystem infrastructure.
Program update: Agent Skills '26 received 103 submissions and accepted 45 posters and 6 oral presentations.
The workshop program spans skill applications, safety, evaluation, and learning, with accepted papers presented across poster and oral sessions.
Accepted papers are available now.
We invite contributions across the full lifecycle of Agent Skills, including but not limited to the topics below. This list is not exhaustive—we welcome submissions in any related area.
Accepted papers were reviewed across two tracks:
All submissions must be in PDF format, conform to the ACM SIGPLAN proceedings template, and use the following LaTeX document class:
\documentclass[sigplan,review,anonymous]{acmart}
Submissions are double-blind (author identities are hidden from reviewers). Please ensure your manuscript does not reveal author identities. We encourage releasing reusable artifacts (code, Skills, datasets) after acceptance.
This is a non-archival venue — accepted papers will not be included in the proceedings. Authors retain full rights to submit extended versions to archival conferences and journals.
Camera-ready deadline: Accepted authors should submit final versions by May 24, 2026 (AoE).
OpenReview →Continue the conversation after the workshop at the SkillsBench 1.0 Launch Party, presented by Google DeepMind.
BenchFlow, Google DeepMind, Kaggle, and Kernel Labs are bringing together researchers and practitioners working on skill design, benchmarking, optimization, security, and ecosystem infrastructure.
Interested in supporting Agent Skills '26? We welcome sponsorship at all levels. Please reach out at public@agentskills-workshop.org for details.
Email public@agentskills-workshop.org for submissions, logistics, or sponsorship.
