ctx-merge
适合需要保留来源证据并可控解决冲突的知识管理场景。
聚合外部数据时可能导致敏感信息泄露，请注意数据来源。
把分散来源汇聚为统一知识库，并显式记录溯源与冲突选项。
把分散的研究笔记、子代理输出和审计报告汇聚成一个可维护的知识库，同时明确记录每条结论的溯源和去向。在合并多份文档、整合同类研究或收尾决策周期时会用到。不会悄悄丢信息：保留冲突选项并用可见的处置台账把结论路由到唯一归属，方便人来判断和决策。
▸ 展开 SKILL.md 英文原文
Converges many scattered sources — dated research notes, subagent outputs, audit reports, revision cycles — into one living source of truth without silently dropping or distorting anything, routing each conclusion to exactly one home via a visible disposition ledger and surfacing conflicts as choices for a human. Use when merging or consolidating notes/reports into a ctx source of truth, integrating subagent research, synthesizing multiple audit reports, or closing a decision cycle where alternatives existed. Not for writing a single fresh doc from scratch — use ctx-spec.
帮我安装这个 skill：https://raw.githubusercontent.com/motiful/ctx/main/skills/ctx-merge/SKILL.mdcurl -fsSL "https://raw.githubusercontent.com/motiful/ctx/main/skills/ctx-merge/SKILL.md"# ctx-merge — Converge Without Losing or Distorting
> Routing destinations (spec / decisions / scratch) follow the lifetime model in [`../ctx`](../ctx/SKILL.md).
## Execution Procedure
```
converge(sources) → living_kb_update + conflict_choices
# STEP 1 — Extract (provenance starts here)
claims = []
for src in sources:
claims += extract_atomic(src) # each conclusion decontextualized, tagged {source, span}
# STEP 2 — Cluster + relate (map-reduce, NEVER a recursive prose merge)
clusters = cluster_paraphrastic(claims) # dedupe equivalents
for c in clusters:
relate(c) # entail → keep one + merge provenance
# neutral/complementary → keep both