暂未收录效果图
查看技能说明evals-specify
tikalk
Extract eval criteria from product specs and production failure traces (bottom-up error analysis). Writes proposed criteria to .adlc/drafts/evals/.
OPENAGENTSKILL / DIRECTORY
为下一项任务找到合适的技能。探索适用于 Codex、Claude Code、Cursor 等 Agent 的工具。
4 Skills
搜索结果: 4
自 2026年10月14日 起统计本站返回的文件,仅统计登录账号;同一账号、同一 Skill 每个 UTC 日计一次。不含外站下载、复制命令或安装次数,数据可能延迟 5 分钟。
暂未收录效果图
查看技能说明tikalk
Extract eval criteria from product specs and production failure traces (bottom-up error analysis). Writes proposed criteria to .adlc/drafts/evals/.
暂未收录效果图
查看技能说明tikalk
Analyze evaluation results and close the loop. Specification failures create local CDRs to fix agent rules; generalization failures go to evaluator backlog.
暂未收录效果图
查看技能说明joeseesun
Research, create, improve, migrate, evaluate, package, install-check, govern, and safely publish qiaomu-flavored agent skills from workflows, prompts, transcripts, docs,…
暂未收录效果图
查看技能说明darkroomengineering
Turn proven session behavior into a skill, rule, profile, AGENTS.md diff, or team learning; artifacts seed /autoresearch evals. Triggers "harvest this workflow", "turn t…