Why this stack
The most common waste on research paths: three days tuning a model only to redo it because the data format was wrong, or running an experiment with zero record-keeping and forgetting the rationale a week later. This stack folds AI + data + docs together so reproducibility is part of the loop, not an afterthought.
Skills in this stack
Listed in recommended order. Each ships its original trust score and full install commands.
-
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. Trigger for 'improve this skill', 'improve /ai-plan', 'make /ai-review better', 'optimize all skills', 'batch improve skills'. Accepts a single skill name or 'all' for batch mode. Not for creating new skills from scratch; use /ai-scaffold instead. Not for platform audit; use /ai-ide-audit instead.
Open full docs & audit →Install command
Pick your agent and copy a single line.
Requires Claude Code CLI · Node 18+
-
Query Octopus observability platform — logs, alerts, traces, metrics, issues, services, LLM, RUM, events. Triggers on "logs", "alerts", "traces", "metrics", "octopus", "observability", "error tracking", "RUM", "LLM observability" CLI tool octo-cli for querying the Octopus observability platform (octopus.zhenguanyu.com). Covers logs, alerts, error tracking…
Open full docs & audit →Install command
Pick your agent and copy a single line.
Requires Claude Code CLI · Node 18+
-
Master creative specialized skill 38 with comprehensive coverage of concepts, implementation, optimization, and production best practices. Essential skill for professionals working in creative.
Open full docs & audit →Install command
Pick your agent and copy a single line.
Requires Claude Code CLI · Node 18+
-
Create a new Agent Zero agent profile (subordinate). Covers where profiles live (user / plugin-distributed / project-scoped), the agent.yaml schema, the prompt inheritance & override model, and optional profile-specific tools and extensions. Use for any "create/add/new agent profile" request.
Open full docs & audit →Install command
Pick your agent and copy a single line.
Requires Claude Code CLI · Node 18+
-
| llm-wiki 帮你构建一个持续增长的个人知识库。它不是传统的笔记软件，而是一个让 AI 帮你维护的 wiki 系统： 传统方式（RAG/聊天记录）的问题：每次问问题，AI 都要从头阅读原始文件，没有积累。知识库的价值在于知识被编译一次，然后持续维护，而不是每次重新推导。 Scripts located in scripts/ subdirectory. requires OpenAI / Anthropic API key; runs on Node.js. Works with Claude Code, Cursor, Cline and 23 more.
Open full docs & audit →Install command
Pick your agent and copy a single line.
Requires Claude Code CLI · Node 18+
-
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.
Open full docs & audit →Install command
Pick your agent and copy a single line.
Requires Claude Code CLI · Node 18+
-
基于官方 skill-creator 的增强版技能架构师向导，内置合规检查规则，支持两种使用模式： 创建新技能时使用，遵循以下流程： 跳过此步骤的条件：技能的使用模式已经非常清晰。 分析每个使用场景，确定需要的资源： | 类型 | 目录 | 用途 | 何时需要 | runs entirely locally; runs on Python. Works with Claude Code, Cursor, Cline and 23 more.
Open full docs & audit →Install command
Pick your agent and copy a single line.
Requires Claude Code CLI · Node 18+