Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Persistent memory enhancement for AI agents. Store conversations, search memories with semantic retrieval, and recall context across sessions. Use this skill when you need to remember user preferences, past conversations, project context, or any information that should persist beyond the current session. Provides tiered access (abstract/overview/content) for efficient context management.
操作 KWeaver 知识网络与 Decision Agent — 构建知识网络、查询 Schema/实例、 语义搜索、执行 Action、Agent CRUD 与对话、Trace 数据分析。 操作 Skill 管理模块 — 注册 Skill、市场查找、渐进式读取、下载与安装。 操作 Vega 可观测平台 — 查询 Catalog/资源/连接器类型、健康巡检。 当用户提到"知识网络"、"知识图谱"、"查询对象类"、 "执行 Action"、"有哪些 Agent"、"创建 Agent"、"跟 Agent 对话"、"列出所有 Agent 模板"、"列出我创建的Agent"、 "列出私人空间的Agent"、"Skill"、"技能包"、"注册 Skill"、"安装 Skill"、"读取 SKILL.md"、 "数据源"、"数据视图"、"原子视图"、"Catalog"、"Vega"、 "健康检查"、"巡检"、"trace"、"证据链"、"数据流追踪"、"数据来源"、"数据怎么得到的"等意图时自动使用。
Run a dynamic-workflow script on a local Codex App Server — orchestrate many Codex / GPT agents (the agent / parallel / pipeline / phase / budget DSL) instead of Claude subagents, for codebase audits, large migrations, and multi-agent review or research. Give it one or two rough sentences and it compiles the right harness for you; add --multi for a supervised fleet of concurrent workflows. Manual-invoke only via /codex-workflows.
Harness patterns for coding agents — memory, permissions, context engineering, delegation, skills, hooks, bootstrap.
AI Agent Harness 设计模式 — 记忆、权限、上下文工程、委派、技能、 Hook、Bootstrap。中文版。
Review the current session for durable, non-obvious learnings worth persisting to .claude/ (rules, skills, or CLAUDE.md edits). Use when the user asks to extract/save/capture session lessons, or at the end of a session that produced corrections or surprising findings.
Audit and refine the project's `.claude/` rules and CLAUDE.md for conciseness, format consistency, correctness, and pull-its-weight tokens. Use when the user asks to review, refine, audit, lint, or clean up rules — or when a rule directory has grown enough that adherence is degrading.
Help the user create a new zot extension (slash command, LLM tool, or guard) in any language.
Use Mori CLI to enable agent-to-agent communication and coordination across Mori-managed panes. Use this whenever you need to launch a helper agent, send a message to another agent (Claude, Pi, Codex), read another agent's output, or coordinate multi-agent workflows. Prefer this over ad-hoc tmux whenever the task involves mori pane operations or agent-to-agent messaging.
Meta-skill for selecting and invoking the right workflow skill before acting; use when starting or switching task type to avoid bypassing required discipline.