ctx
为长期多会话协作提供规范化的单一事实源与工作路由策略。
搭建与管理面向多会话 AI 代理的活性单一事实源与文档生命周期。
把多次对话和散落文档收拢成一个轻量且活着的 single source of truth，根据文档的生命周期分门别类，方便长期维护与检索。在新项目搭建知识库、文档冗余冲突或不知道某条发现放哪儿时用，能把规格、决策、进展区分开来。特点是把资料路由到合适的子流程来合并、收编或产出规范，不让文档生锈或相互矛盾。
▸ 展开 SKILL.md 英文原文
Sets up and orchestrates a ctx knowledge base — a lean, living single source of truth for multi-session AI-agent work — and classifies any doc or finding by its lifetime, routing the work to the right companion skill. Use when starting or scaffolding ctx on a new project, when unsure where a finding belongs (spec vs decision vs progress vs scratch), when unsure which ctx skill handles a task, or when docs have sprawled into redundant, contradictory piles that need converging. Entry point for the collection; routes to ctx-adopt (existing repos), ctx-merge (converge sources), ctx-spec (specs and ADRs), ctx-progress (work tracking), ctx-report (reports for a human). For an existing/brownfield repo, use ctx-adopt instead.
帮我安装这个 skill：https://raw.githubusercontent.com/motiful/ctx/main/skills/ctx/SKILL.mdcurl -fsSL "https://raw.githubusercontent.com/motiful/ctx/main/skills/ctx/SKILL.md"# ctx — a living, spec-centered single source of truth
## The problem this solves
Long, multi-session AI-agent research/design produces documents that **rot** into a pile that is **redundant, contradictory, and stale**. Symptoms: docs multiply endlessly; changing one thing forces chasing a chain of edits across many docs; old docs go 50%-true/50%-false so you can't tell what's current; the process order feels chaotic ("research first or design first?"); dozens of review reports pile up and merging their conclusions becomes its own unsolved problem.
Root cause: organizing docs by **pipeline stage** (requirements→research→design→decisions→progress) leaves a persistent, editable, go-stale do