Compare named assets side by side on a common set of dimensions and return a structured benchmark with explicit evidence strength. Use for direct comparisons, for example 'how does X compare to the other IL-23s', 'benchmark these four programs'. Use identify-analogs when precedents to reason from are wanted rather than a head-to-head table.
安装
npx skills add MavenBio/maven-bio-plugin --skill benchmark-assetsnpx skills add MavenBio/maven-bio-plugin --skill benchmark-assets -a claude-code -gnpx skills add MavenBio/maven-bio-plugin --skill benchmark-assets -a codex -ggemini skills install https://github.com/MavenBio/maven-bio-plugin.git --path plugins/maven-bio/skills/benchmark-assetsgh skill install MavenBio/maven-bio-plugin benchmark-assetsgit clone --depth 1 https://github.com/MavenBio/maven-bio-plugin /tmp/MavenBio__maven-bio-plugin
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/MavenBio__maven-bio-plugin/plugins/maven-bio/skills/benchmark-assets ~/.claude/skills/benchmark-assets # Claude Code
cp -R /tmp/MavenBio__maven-bio-plugin/plugins/maven-bio/skills/benchmark-assets ~/.agents/skills/benchmark-assets # Codex, Cursor, Gemini CLI, Copilot, OpenCode