eval-harness
[ 精选 ]
Eval Harness 是一种用于 AI 代码开发的评估框架
★ 171.1k
⑂ 0
正在浏览:
浏览和安装 Killer-Skills 目录中的数千个 AI Agent 技能。支持 Claude Code、Windsurf、Cursor 等。
LIVE
6
可用技能
6 可用技能
receiving-code-review
[ 精选 ]
本地化技能摘要： Core principle: Verify before implementing. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.
★ 174.8k
⑂ 0
verification-before-completion
[ 精选 ] 本地化技能摘要： Core principle: Evidence before claims, always. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.
★ 174.8k
⑂ 0
using-git-worktrees
[ 精选 ] 本地化技能摘要： Core principle: Systematic directory selection + safety verification = reliable isolation. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.
★ 174.8k
⑂ 0
finishing-a-development-branch
[ 精选 ] 本地化技能摘要： Core principle: Verify tests → Present options → Execute choice → Clean up. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.
★ 174.8k
⑂ 0
rules-distill
[ 精选 ] 本地化技能摘要： Applies the "deterministic collection + LLM judgment" principle: scripts collect facts exhaustively, then an LLM cross-reads the full context and produces verdicts. It covers ai-agents, anthropic, claude workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.
★ 171.1k
⑂ 0