Agents15d ago
First Empirical Study on Agent Skill Evolution Reveals Concrete Rules in SKILL.md Boost Agent Correctness
In modern coding agent ecosystems (such as Claude Code, Cursor, Cline, and Antigravity), Agent Skills—specialized instruction files like SKILL.md and CLAUDE.md that dictate project architecture, commands, and rules—are continuously revised by developers alongside source code. Yet the concrete impact of these revisions on agent behavior and inference cost has remained largely unquantified. In a comprehensive empirical audit (arXiv:2610.04832), researchers analyze 2,608 first/last revision pairs across 3,159 Skills to measure the effects of revisions across 21 foundation models and four sandboxed coding agents. The study reveals that 55% of revisions alter specific rules or procedures. Adding a concrete rule raises compliance in single answers by +0.41 across open-weight models, increases required action adherence by +0.23 across sandboxed agents, and improves final task correctness by +0.10 in blind evaluations. Critically, these gains are overwhelmingly driven by rules that specify explicit CLI commands or exact file paths, whereas abstract stylistic guidance offers negligible lift. The paper also documents the performance and token trade-offs of dynamic on-demand skill loading.
Tooling25d ago
NVIDIA DOCA Agent Skills on GitHub: verified API/hardware contracts lift 65-prompt checklist pass from 19% to 100%
On 2026-10-01 NVIDIA published DOCA AI agent skills on NVIDIA/skills: SKILL.md packs with real API signatures, hardware capability checks, and build constraints for Flow, GPUNetIO, PCC, RDMA, and more. Vendor 65-prompt eval: 19% checklist items without skills vs 100% with; RDMA demo used 73% less handwritten code and 46% fewer hardware commands. Installable into Claude Code, Codex, and other coding agents.
Release16d ago
OpenClaw v2026.10.1: installed-skill search, MCP Apps beside chat, full backups to R2; 2,425 PRs from 402 contributors
OpenClaw v2026.10.1 (3,055 commits, 2,425 PRs, 402 contributors) lets agents search installed skills on demand instead of loading the whole library into the prompt, opens compatible MCP Apps beside chat with in-pane approvals, adds full backups to external storage or Cloudflare R2, and lets the packaged Mac app run without a separate Node install.
Discussion & Comments
0Sign in to join the discussion
Connect with AI developers to exchange benchmark insights.