A developer's audit of migrating Claude Code skills to OpenCode reveals that skills often degrade silently, with harness-specific frontmatter fields such as allowed-tools and model pinning being dropp…
JetBrains' AI team measured an 8.5% output token reduction from the Caveman Claude Code skill on real agent workloads, not the 65% claimed in its viral tagline, with cost savings around 10% and qualit…
Adding a single skill to an LLM agent reliably improves task performance, but by the time a fourth skill is active, the cumulative gain shrinks to a fraction of what two skills produced, according to …
JetBrains tested the Caveman token-compression skill on Claude Code 2.1.200 and found it saves only about 8.5% of output tokens on real agentic tasks, far below the advertised 65%. The skill, which fo…
A good AI agent skill is a compact package of procedural expertise that fixes a repeatable failure, loads only when relevant, and earns its place against a matched evaluation, according to three recen…
JetBrains AI tested the rtk (Rust Token Killer) CLI proxy, which claims to cut agent tokens by 60–90%, and found that most agent bytes never touch the hook, with measured token savings far below adver…
Researchers introduce SkillCorpus, a framework that aggregates, curates, matches, and evaluates open-source SKILL.md files for LLM agents, filtering ~821,000 crawled skills into 96,401 organized by a …
SkillsBench, an arXiv benchmark published in February 2026, found that curated skills boosted average task pass rates from 33.9% to 50.5% across 87 tasks and 18 model-harness configurations, with heal…
JetBrains tested the viral 'Caveman' prompting style for AI coding assistants and found it reduces token usage by only 8.5%, far less than the claimed 65%. The technique trims conversational padding b…
Ai2 released Tmax-27B on 23 June 2026, an open-weight terminal-agent model built on Qwen3.6-27B that scores 43% on Terminal Bench 2.0 and 69% on TB Lite. The dense 27B model outperforms the sparse 397…
Researchers have developed MUSE-Autoskill, a framework that enables large language model agents to continuously improve their task-solving abilities by creating, reusing, and refining skills through a…