为什么是这套组合
研究路径上最常见的浪费是：花了三天调通模型，结果数据格式不对要返工；或者实验跑出来了，但没有任何记录，过两周自己都忘了为什么这么调。这套栈把 AI、数据、文档三类绑在一起，强制把记录与复现也当作工作流的一部分。
栈内技能
按推荐顺序排列。每条都附原始信任分与完整安装命令，可单独复制。
-
Improves an existing skill based on real project pain (prior eval corpora under .ai-engineering/evals/, Engram cross-session observations, LESSONS.md, decision-store, instincts, proposals) by analysing the failure pattern, rewriting SKILL.md, and emitting the proposed delta as a PR comment only — no auto-merge.
查看完整文档与审计 → -
Query Octopus observability platform — logs, alerts, traces, metrics, issues, services, LLM, RUM, events.
查看完整文档与审计 → -
Master creative specialized skill 38 with comprehensive coverage of concepts, implementation, optimization, and production best practices.
查看完整文档与审计 → -
Create a new Agent Zero agent profile (subordinate).
查看完整文档与审计 → -
| llm-wiki 帮你构建一个持续增长的个人知识库。
查看完整文档与审计 → -
Use when publishing a SKILL.md-style agent skill across uGig, sh1pt, GitHub/gists, and follow-on skill marketplaces such as ClawHub, Goose, LobeHub, Kilo, Skillstore, FreeMyGent, ClawMart, Manus, VS Code Agent Skills, and Moltbook.
查看完整文档与审计 → -
技能架构师向导与审查工具，整合官方 skill-creator 流程与内置合规检查。
查看完整文档与审计 →