story-context

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Story Context

故事上下文

Every spawn starts with a context decision. Get it wrong and the writer invents facts that contradict established canon, the critic misses a continuity issue because it never saw the relevant chapter, or the brainstormer explores territory the author already rejected.

The

/meridian-spawn

skill teaches the mechanics of

-f

--from

, and spawn commands. This skill teaches the judgment — what story context to pass, when to materialize decisions before spawning, and how much is enough.

每次Agent生成都始于上下文决策。如果决策失误，写作Agent会编造与既定设定矛盾的内容，评审Agent会因未看到相关章节而遗漏连续性问题，或者头脑风暴Agent会探索作者已否决的方向。

/meridian-spawn

skill 讲解了

-f

、

--from

和生成命令的机制。本skill则传授判断逻辑——应传递哪些故事上下文、何时在生成前将决策具体化，以及传递多少内容足够。

Choose the Right Mechanism

选择合适的机制

Three options, each for a different situation.

/meridian-spawn

has the command syntax; this section covers when to use which.

Files (
-f
) — when context already exists as files: chapters, outlines, wiki pages, style files, character state. Default choice because files are stable, inspectable, and survive compaction. Scope tightly — pass the files that matter, not everything.

Session history (
--from
) — when the agent needs decisions, reasoning, or brainstorm context that hasn't been written down yet. Session history captures the why behind choices — why the author picked this angle, what they rejected.

Materialize first — when context is too important to be ephemeral. If critical story decisions only live in conversation, write them to the kb or work directory before spawning. If a writer could accidentally contradict this context, materialize it. If it's supplementary background,

--from

is fine.

三种选项，分别适用于不同场景。

/meridian-spawn

包含命令语法；本节介绍何时使用哪种机制。

文件（
-f
）——当上下文已以文件形式存在时使用：章节、大纲、维基页面、风格文件、角色状态。这是默认选择，因为文件稳定、可检查，且不会在压缩中丢失。严格限定范围——只传递重要的文件，而非全部。

会话历史（
--from
）——当Agent需要尚未记录的决策、推理或头脑风暴上下文时使用。会话历史能捕捉选择背后的「原因」——作者为何选择这个角度，他们否决了什么。

先具体化——当上下文至关重要，不能仅为临时内容时使用。如果关键故事决策仅存在于对话中，在生成Agent前需将其写入知识库（kb）或工作目录。如果写作Agent可能意外与该上下文产生矛盾，就需要将其具体化。如果只是补充背景信息，使用

--from

即可。

What Each Agent Needs

各类Agent的需求

Writers

写作Agent

Writers need enough to stay in voice and on-canon, not everything ever written. The essential context:

Scene brief or outline — what happens in this scene, the beats to hit
Relevant style files — look at what exists in the styles directory and pick the files that match the scene. Character files for whoever appears, scene-type files for the kind of scene being written. Each style file is self-describing — read the top to know when it applies.
Continuity anchors — the immediately preceding chapter or scene (for flow), plus any chapters that establish facts this scene references. Two to four files, not the entire manuscript.
Character state — character files for characters who appear in the scene, especially if their emotional state or knowledge has changed recently

Tell the writer where to find more if it needs to explore — "the full arc outline is in the work directory, focus on the Route 1 section" — rather than attaching everything preemptively.

写作Agent需要足够内容来保持风格一致性和符合设定，但无需所有已撰写内容。核心上下文包括：

场景简介或大纲——本场景的情节走向、需要达成的关键节点
相关风格文件——查看风格目录中的内容，选择与场景匹配的文件。出现角色的角色文件、对应场景类型的场景文件。每个风格文件都有自我描述——阅读顶部内容即可了解适用场景。
连续性锚点——紧接的前一章或场景（保证连贯性），以及任何包含本场景引用事实的章节。2-4个文件即可，无需整个手稿。
角色状态——出现在本场景中的角色文件，尤其是当他们的情绪状态或认知最近发生变化时

告诉写作Agent如需深入探索可在哪里找到更多内容——「完整弧线路径大纲在工作目录中，重点关注Route 1部分」——而非预先附加所有内容。

Critics

评审Agent

Critics need the draft plus enough context to judge it against:

The draft being reviewed — always via
```
-f
```
The scene brief or outline — so the critic can check whether the draft achieved what it was supposed to
Relevant style files — so voice critics can compare against the target voice
Prior chapters for continuity — so continuity critics can cross-reference facts
Author intent — via
```
--from
```
if the orchestrator discussed direction with the author, or via materialized decision notes
Known issues — tracked issues if the critic should watch for specific recurring problems

评审Agent需要草稿以及足够上下文来进行评判：

待评审的草稿——始终通过
```
-f
```
传递
场景简介或大纲——以便评审Agent检查草稿是否完成预期目标
相关风格文件——以便风格评审Agent与目标风格进行对比
用于连续性检查的先前章节——以便连续性评审Agent交叉核对事实
作者意图——如果协调者与作者讨论过方向，可通过
```
--from
```
传递，或通过已具体化的决策笔记传递
已知问题——如果评审Agent需要关注特定重复问题，可传递已追踪的问题记录

Brainstormers

头脑风暴Agent

Brainstormers need constraints, not answers:

The question being explored — scoped tightly in the prompt
Established context that constrains the answer — character profiles, timeline, prior decisions that limit the design space
What's been rejected — so they don't re-propose dead ends

Don't pass too much — brainstormers that receive the full project history tend to produce conservative ideas that fit neatly into existing patterns instead of exploring fresh territory.

头脑风暴Agent需要约束条件，而非答案：

待探索的问题——在提示中严格限定范围
限制答案的既定上下文——角色档案、时间线、限制设计空间的先前决策
已被否决的内容——避免他们重新提出已被放弃的方案

不要传递过多内容——接收完整项目历史的头脑风暴Agent往往会生成保守的想法，完美契合现有模式，而非探索新领域。

Knowledge Maintenance

知识维护Agent

Chronicler: the chapter(s) to extract facts from via
```
-f
```
, plus existing canon files and timeline entries for deduplication
Base @kb-maintainer: the kb directory structure — it needs to see everything to rebuild connections
Base @kb-writer:
```
--from
```
pointing at the conversation to mine, plus kb paths for where to write findings

Chronicler：通过
```
-f
```
传递需提取事实的章节，加上现有设定文件和时间线条目以进行去重
Base @kb-maintainer：知识库（kb）目录结构——它需要查看所有内容以重建关联
Base @kb-writer：
```
--from
```
指向待挖掘的对话，加上知识库路径以指定结果写入位置

Cross-Phase Context

跨阶段上下文

Carry forward what a previous phase learned using

--from <prior-spawn-id>

. The revision writer benefits from seeing what the first-draft writer discovered. The critic benefits from seeing prior critique rounds.

Combine mechanisms when phases produce artifacts:

--from

for reasoning context,

-f

for the files the prior phase created.

使用

--from <prior-spawn-id>

传递前一阶段的学习内容。修订写作Agent能从查看初稿写作Agent的发现中获益。评审Agent能从查看先前评审轮次中获益。

当阶段产生成果时，可结合多种机制：

--from

传递推理上下文，

-f

传递前一阶段创建的文件。